
Sign up to save your podcasts
Or


What is the MOSAIC-NLP project around structured and unstructured EHR data? Why is structured data not really enough for drug safety studies? And to what degree is NLP speeding up access to data and research results? We will learn all that and more in this episode of Research in Action with Dr. Darren Toh, Professor at Harvard Medical School and Principal Investigator at Sentinel Operations Center.
www.oracle.com/health
www.oracle.com/life
www.sentinelinitiative.org
--------------------------------------------------------
Episode Transcript:
00;00;00;00 - 00;00;26;14 What is the MOSAIC and LP project around structured and unstructured data? Why is structured data not really enough for drug safety studies? And to what degree is NLP speeding up access to data and research results? We'll find all that out and more on this episode of Research in Action. Hello and welcome to Research in Action, brought to you by Oracle Life Sciences. 00;00;26;14 - 00;00;50;14 I'm Mike Stiles. And today our guest is Dr. Darren Toh, professor at Harvard Medical School and principal investigator at Sentinel Operations Center. He's got a lot of expertise in Pharmacoepidemiology as well as comparative effectiveness research and real-world data. So, Darren, really glad to have you with us today. Thank you. My pleasure to be here. Well, tell us how you wound up where you are today. 00;00;50;14 - 00;01;26;22 What what attracted you in the beginning to public health? Good question. So I trained in pharmacy originally, and I got my Masters degree in Pharmaceutical Outcomes Research at a University of Chicago, Illinois, Chicago. And it's where I first learned about a field called Pharmacoepidemiology, which sort of very interesting to me because I like to solve problems with methods and data and pharmacoepidemiology. 00;01;26;22 - 00;02;00;29 It seems to be able to teach me how to do that. So I got into the program at the Harvard School of Public Health, and when I was finishing up, I was deciding between staying in academia and going somewhere and getting a real job. And that's when I found out about an opportunity within my current organization and I've heard great things about this organization. 00;02;00;29 - 00;02;29;26 So I thought I would give it a try. And the timing turned out to be perfect because when I joined, our group was responding to a request for proposal for what is called a mini sentinel pilot, which ultimately became the sentinel system that we have today. So I've been involved in the Sentinel system since the very beginning or before we began. 00;02;29;28 - 00;03;02;25 And for the past 15 years I've been with the system and the program and because I really like its public health mission and I'm also very drawn to the dedication of FDA, our partners and my colleagues to make this a successful program. Well, so now here you are, a principal investigator. What exactly is the Sentinel Operations Center? What's what's the mission there and what part do you specifically play in it? 00;03;02;27 - 00;03;52;26 Sentinel is a pretty unique system because it is a congressionally mandated system. So the Congress passed what is called the FDA Amendments Act in 2007. And within that FDA, the Congress asked FDA to create a new program to complement FDA existing systems to monitor medical product safety and more specifically, the Congress, US FDA, to create a post-market risk identification and analysis system that will be using data from multiple sources that will cover at least 1 million lives to to look at the safety of medical products after they are approved and marketed. 00;03;52;28 - 00;04;33;07 So in response to this congressional mandate, FDA launched what is called a Sentinel initiative in 2008 and in 2009 as I mentioned, FDA issued its request for proposal to launch the Mini Sentinel Pilot program, and the program grew into the sentinel system that we have today. So it's for my involvement. It sort of grew over time. So when I joined, as I mentioned, we were responding to this request for a proposal and we were very lucky to be awarded the contract. 00;04;33;09 - 00;05;04;05 So when it was starting, I serve as a one of the many epidemiologists on the team and I led several studies and I gradually took on more leadership responsibility and became the principal investigator of the Sentinel Operations Center in 2022. So I've been very fortunate to have a team of very professional and very dedicated colleagues within the operations center. 00;05;04;05 - 00;05;27;26 So on a day to day basis, we work with FDA to make sure that we can help them answer the questions they would like to get addressed. And we also work with our partners to make sure that they have the resources that they need to answer the questions for FDA. And most of the time I'm just the cheerleader in chief just to share my colleagues and our collaborators. 00;05;27;28 - 00;06;11;23 Now that's great. And and then specifically, there's the Mosaic NLP project that you're involved with. What is that trying to achieve and what are the collaborations being leveraged to get that done? So Sentinel Systems has always had access to medical claims data and electronic health record data or year data. One of the main goals for the current sentinel system is to incorporate even more data, both structured and unstructured, into the sentinel system and to combine it with advanced analytic methods so that FDA can answer even more regulatory questions. 00;06;11;25 - 00;06;40;09 So the Mosaic and NLP project was one of the projects that FDA funded to accomplish this goal. So the main goal of this project is to demonstrate how billing claims and data from multiple sources when combined with advanced machine learning and natural language processing methods, could be used to extract useful information from unstructured clinical data to perform a more robust drug safety assessment. 00;06;40;11 - 00;07;21;18 When we tried to launch this project, we decided that we would issue our own request for proposal. So there was an open and competitive process, and Oracle, together with their collaborators, were selected to lead this project. So I want to talk in broad or general terms right now about data sharing, the standards and practices around that. It kind of feels silly for anyone to say it's not needed, that we can get a comprehensive view and analysis of diseases and how they're impacting the population without it. 00;07;21;20 - 00;07;46;15 NIH is on board. It updated the DMS policy to promote data sharing. You know, the FDA obviously is leaning into this. So is data sharing now happening and advancing research as expected, or are there still hang ups? So I think we are making good progress. So I think the good news is data are just being accrued at an unprecedented rate. 00;07;46;17 - 00;08;28;21 So there are just so much data now for us to potentially access and analyze. There's always this concern about proper safeguard of individual privacy. And through our work, we also became very appreciative of other considerations, for example, the fishery responsibilities of the delivery systems and payers to protect patient data and make sure that they are used properly. So you mentioned the recent changes, including in data management, ensuring policy, which I think are moving us in the right direction. 00;08;28;26 - 00;08;56;23 But if you look closer at the NIH policy, it makes special considerations for proprietary data. So I would say that we have made some progress, but access to proprietary data remains very challenging. And the FDA, the NIH policy doesn't actually fully resolve that yet. When you think about the people who do make that argument for limited data sharing, they do mostly talk about what you just said about patient privacy. 00;08;56;23 - 00;09;25;20 IT proprietary data. Pharma is especially sensitive to that, I would imagine. So how do we incentivize the reluctant how can we ease their risks and concerns or can we? Yeah, it's a tough question. I think that this require a multi-pronged approach and I can only comment on some aspects of this. So I would say that at least based on our experience, the willingness or ability to share data often depends on the purpose. 00;09;25;23 - 00;09;55;29 That is, why do we need the data? Many data partners participate in Sentinel because of its public health mission, and our consideration is how would the data be used again, Is there proper safeguard of patient privacy and institutional interest? There are other ways to share data. For example, instead of asking the data to come to us, we can send analysis to where the data is. 00;09;56;06 - 00;10;34;22 And that is actually the principle follow by federated system like Sentinel. So we don't pull the data centrally. We send an analysis to the data partners and only get back what we need it. And it's usually in the summary level format. So that actually encourages more data sharing instead of less sharing. I would say that recent advances in some domains, such as tokenization and encryption, might also reduce some concern about a data sharing, a patient privacy concerns in academic settings. 00;10;34;29 - 00;11;24;26 We've been talking a lot about days, for example, for individual who collect the data and the people I propose to offer them authorship or proper acknowledgment if they are willing to share their data. But that is not sufficient in many cases outside of academic settings. If you look at what is happening in the past ten years or so, there are now a lot of what people call data aggregators that are able to bring together data from multiple delivery systems or health plans, and they seem to be able to develop a pretty effective model to convince the data provider to share that data in some way. 00;11;24;29 - 00;11;55;28 And a way to do that could be to help these data providers to manage their data more efficiently or to help them identify individuals who might be eligible for clinical trials. More quickly. So there are some incentives that we could think of to allow people to to share that data more openly but personally, I think that scientific data should be considered public good and hopefully that will become a reality one day. 00;11;56;00 - 00;12;23;21 Yeah, that's really interesting because it sounds like it's both a combination of centralized and decentralized tactics in terms of of data sharing and gathering. Why is it so important to use unstructured data in pharmacoepidemiology studies? And does NLP really make a huge difference in overcoming the limitations and extracting that data? So in the past, I think that that's true. 00;12;23;21 - 00;12;58;07 Now, many pharmaco epidemiologic studies rely on data. They are not collected for research purposes. So we use a lot of medical claims, data that are maintained by payers. We use each our data that are maintained by delivery systems. So this data are not created for research purposes and much of this data, at least for claim, is data stored in structured format using established coding systems like ICD ten. 00;12;58;10 - 00;13;39;06 Coding system and structured data sometimes are not granular enough for a given drug safety study and certain data or set of variables that are required for claims reimbursements or other business purposes might not be collected at all. And people felt that, well, maybe the information that we need could be extracted from unstructured data because as part of clinical care, the physicians or nurse practitioner or the health care provider might include that information in the notes, but use user data also pretty messy, especially that unstructured data. 00;13;39;08 - 00;14;05;25 So instead of going through the unstructured notes manually to extract this information manually, technique by natural language processing could help us do this task much more efficiently so that we can mind a larger model of unstructured data. Well, obviously, when it comes to real world evidence, you're a fan. Tell us what excites you about using it to complement clinical research. 00;14;05;25 - 00;14;42;07 Get us more evidence based insights and help practitioners make better decisions. Yeah, that's a great question. Yes, I'm a fan of so I personally don't quite like the dichotomy between conventional, randomized, controlled trial and real world data studies because they actually sit along a continuum. But is true that conventional randomized trials cannot address all the questions in clinical practice. 00;14;42;09 - 00;15;30;17 So that's where real data and real data studies come in, because real data like we discussed come from clinical practice. So they capture what happens in day to day clinical practice. So if we are thoughtful enough, we will be able to analyze the data properly and generate useful information to fill some of the knowledge gap. The truth is we have been using real data throughout the lifecycle of medical product development for many years now, ranging from understanding the natural history or burden of diseases to using real data as controls for single arm trials, and that we have been doing this before the term real data became popular. 00;15;30;19 - 00;15;57;11 So I see real data to complement what we could do in conventional randomized trials. So real data studies don't replace clinical trials. I see them to be complementary, and real data studies sometimes are the only way for us to get certain evidence. We already talked about Mosaic and LP that project, but I kind of want to go a little deeper with it. 00;15;57;11 - 00;16;42;02 The idea is to tackle the challenges of using link data structured and unstructured at scale. Tell us about a use case for that project and why it was chosen for this project. We actually, Cerner proposed to use the association between Montelukast, which is an asthma drug and neuropsychiatric events as a motivating example. It is also important to note that the project is not designed to answer this particular safety question, because if you look at the label of Montelukast, there's also already a box warning on neuropsychiatric events. 00;16;42;02 - 00;17;18;26 So FDA already has some knowledge about this being a potential adverse event associated with the medication. The reason why or recalls is has proposed this project was because we actually did look at this association in a previous sentinel study that only used structured data, although the study provided provided some very useful information. We also recognized that certain information that we needed was available in such a data, but may be available in unstructured data. 00;17;18;28 - 00;17;42;18 So if we are able to get more data from unstructured data, we might be able to understand this association better. So that's why this motivating example was chosen. Well, this is an Oracle podcast and Oracle is involved in Mosaic, so I think it's fair to ask you about the technology challenges that are involved in what you're trying to do. 00;17;42;19 - 00;18;17;24 What does the technology have to be able to do for you to experience success? So Mosaic in LP is I was at a very ambitious project because it is using an LP to extract multiple variables that are important for the study. That includes the study outcome, which when you look at it, is a composite of multiple clinical outcomes and it's also trying to extract important covariates that could help us reduce the bias associated with real data study. 00;18;17;26 - 00;19;01;24 So I think technology comes in well is powerful in many ways. First, thanks to technology, the project is able to access very large amount of data from millions of patients who seek care in more than 100 healthcare delivery systems across the country. So this was hard to imagine maybe ten or 15 years ago. But now we have access to lots and lots of data at our fingertips because of advances in technology, because of the large amount and the complexity of the data methods side and LP becomes even more important. 00;19;01;26 - 00;19;33;19 And for this project, we are also particularly interested in whether an LP algorithm developed in one year trial system could be applied to another system, which has been a challenge in our field because each year our system is created very differently. So one, an algorithm that works in one system might not work in another. So we are hoping that through advanced methods and technology, we will be able to address this problem. 00;19;33;21 - 00;19;57;15 So without this technology advances, we might not be able to do this study as efficiently as we could all So the task might might not be possible. So where are we going with this? I mean, let's say the project is a success. What will that mean in terms of the FDA's goals and how NLP gets applied in medical therapeutics safety surveillance? 00;19;57;18 - 00;20;38;03 The hope is that Sentinel system can answer even more questions than it can address today. And the way that we are trying to accomplish that is to see whether or how this complex, unstructured data, we combine it with advanced analytic methods can help us answer questions that could not be addressed by structured data alone. I think through this project we also learned a lot about how the challenges associated with analyzing a very large amount of data from multiple sources. 00;20;38;06 - 00;21;11;14 Again, service data is compiled from more than 100 systems, so it is big but also very complex. And in many of our studies we really need that large amount of data just to be able to answer the question because we may be focusing on rare exposures or real come. So you really need to start with very large from our data just to get to maybe the ten patients that are taking a medication. 00;21;11;17 - 00;21;44;15 And what you learn with Mosaic, can that get applied to addressing other public health issues like disparate ease and asthma diagnosis and treatment, especially when you think about diverse groups? Yeah, that's a great question. So is the project is not designed to address these important questions, but if we are able to better understand the completeness of social drivers of health in these data sources, then we will be able to leverage this data to answer these questions in the future. 00;21;44;18 - 00;22;04;26 I think about how a project like this gets a evaluated at various steps along the way. I guess that's my question. How I mean, what what methods are used to ensure the validity of real world evidence? So the good news is in the past few decades we have been using real data, even though we might not be using the term. 00;22;04;28 - 00;22;36;22 So there's been a lot of progress in the field to improve the validity of Real-World Data studies. So we now have a pretty good framework to identify fit for purpose data, and we also have very good understanding of appropriate design and analytic methods. So to target trial emulation and propensity score methods. So this project and many other projects in Sentinel are following this principle. 00;22;36;24 - 00;23;14;03 And one thing to also note that this project is also following the overall sentinel principle in transparency. So everything we do will be in the public domain to allow people to reproduce, so replicate the analysis. So the protocol is available in public domain, and when we are done with the study, everything will be made publicly available. So that's one way to make sure that the the work at least is reproducible or replicable. 00;23;14;05 - 00;23;43;00 And through that process, we hope to be able to improve the validity of this study. And what about comparisons? How do you compare the results from different data sources like claims data, structured data? You know, I extracted unstructured data, all of that. How was that done, the comparisons? So if you're talking about the Mosaic and LP study, so we have a pretty structured approach to address that question. 00;23;43;02 - 00;24;13;14 So we are using this proven principle of changing one thing and keeping everything else fixed to see what happens. So the project will start by using only claims data to replicate the previously done Sentinel study. And then we are going to add on such data to see whether the results are different. And then we add on an LP extract that unstructured data one at a time to see whether the results change. 00;24;13;21 - 00;24;40;24 So by fixing everything else to be constant and changing one thing, we'll be able to assess the added value of each how data, both structure and structure. And that's how we are going to do it within the Mosaic and LP study. And then what about scalability? How would you make sure the NLP models that you develop are scalable and transportable across all these different health systems of which there are many? 00;24;40;27 - 00;25;10;10 Yeah. The question again is about transport ability. So one thing that is unique about this study, as we briefly discussed earlier, was that the the survey yesterday to actually come from multiple healthcare systems. So the end up models that we are developing will be trained in tune on a sample of patients from this system and not from a single hospital network. 00;25;10;10 - 00;25;42;18 So at the development phase, we are already taking into account the potential diversity of different delivery system. And as part of this project, we also include another delivery system to apply and test the method as part of the transport ability assessment. So we are doing that to make sure that the LPI models that we are developing for this project will be useful for other system as well. 00;25;42;20 - 00;26;12;29 Unknown There is a larger question about computational resources, so that will be the issue that would still need to be addressed because a train and tuning this and NLP models within such a huge amount of data requires a lot of computing resources. So that is something that we could only partially address in our study. But if we want to apply or do the same thing in our system, that would be something to consider. 00;26;13;02 - 00;26;43;13 We talked a little bit about the collaboration with your tech partner, but these things usually have so many stakeholders and disciplines and silos. Tell us first why collaboration is a good thing and unavoidable anyway, and then what the challenges of collaboration are. Maybe some tips on how to best make them work. The problems that we face, at least many of the problems that I face quite complex and they require expertise from multiple domains. 00;26;43;13 - 00;27;18;19 So that calls for collaboration from multiple stakeholders. And we always have our blind spots. So we only see things in a certain way and we always miss things. So that's why I think collaboration is important. But it's really hard sometimes because we all have our priorities and perspectives and sometimes they don't align. And I also learned throughout the years that we don't communicate enough and we may also not have time to communicate or we may be under pressure to deliver. 00;27;18;21 - 00;27;47;21 So all of that sort of contribute to the challenges of collaborating effectively, especially when you collaborate across disciplines, because we might be using different languages to mean the same thing or use the same term to describe different things. So even though we can all speak the same language less English, we might not be talking about the same thing and not communicate at all. 00;27;47;21 - 00;28;17;25 Because because we are using different joggers and terminology. So that has been tough. But I think we are getting better. And so I think that it is for us within the center of operation center, we try to communicate honestly and respectfully and we try to understand different perspectives and we try to find common ground. And but I think ultimately what brings us together is that we have a shared common goal. 00;28;17;27 - 00;28;44;17 A lot of the work that we do. So for music and NLP, we are all trying to answer the same question, which is that how do we use unstructured data and advanced analytic methods to answer safety question? So once we apply on this common goal, things become easier because we start to understand each other better or be able to communicate more effectively. 00;28;44;19 - 00;29;19;16 Just out of curiosity, what are the different stakeholders involved in Mosaic? Who falls on the roster? we have people from different disciplines, so we have experts in natural language processing and artificial intelligence. We have epidemiologists, both statisticians, clinicians, we experts in psychiatric conditions and respiratory disease. We have data scientists, we have engineers, we have project managers. So it's a very big group of individuals with different expertise in this project. 00;29;19;18 - 00;29;46;14 Well, you probably noticed Oracle's really thrown itself into and committed huge resources to health and life sciences. Things got really exciting with the acquisition of Cerner and Cerner and Visa. What's Oracle doing right and what do you think it should be doing to make itself even more valuable in health and life sciences? Well, this is a great but very difficult question, so I cannot comment too much what Oracle is doing or will be doing. 00;29;46;17 - 00;30;23;06 But I can say more generally that there have been a number of technology companies that have tried to foray into health or life sciences. I would say with mixed results. And one reason is that our health care system remains highly fragmented and complex, so it takes a lot of energy to break the status quo. So you probably know that we were one of the last countries in the world to transition from ICD nine to ICD ten coding system, and we are soon going to move into the ICD 11 system. 00;30;23;06 - 00;31;00;05 So I'll be interested to see whether the US is ready for that. And that again, is maybe a reflection of just how complex and fragmented our system is and disruptive innovation and I think are great, but they may or may not translate into successes when they applied to health care. That is not to say tempesta mistake. I'm actually pretty optimistic that the perspectives and solutions and ideas brought by technology companies could help us solve a lot of problems that we have today. 00;31;00;07 - 00;31;31;26 But I think that it will be good to engage people who will be struggling with these issues early on and to work together with them to develop solutions that are not just good on paper, but also feasible in practice. So at least in my very limited experience, we have seen some very cool technology that ended up not being useful for health care just because it's very hard to change what people have been doing. 00;31;31;28 - 00;31;56;09 So again, disruptive innovations are good, but sometimes it's just very hard to adopt, at least not quickly enough for for us to see meaningful changes. Yeah, that's really fascinating. It's, you know, it is disruptive innovation, but it's not always applicable to the to the goals you're pursuing. But it does feel like technology where that's concerned, the future is coming at us faster and faster. 00;31;56;11 - 00;32;32;21 So what are the technologies that are most interesting to you? Is it A.I. or what big advances in public health do you see coming? Maybe sooner than we thought. Yeah. Yeah. You know, I feel like you said some of this came too fast. Like, I wish I. And closer to retirement, I don't worry about this. But so even though I say disruptive innovation sometime might not work in health care, but I will say generative A.I. seems to be a recent exception. 00;32;32;24 - 00;33;10;14 So I would say that generative is definitely on the list of things that surprised me in a very nice way. I will also say that the continue fast accrual of better real data is also something that excites me and the continue recognition or increased recognition of the potential real data of. It's also something that I think is good to have for things that came sooner than I found it again, generative. 00;33;10;19 - 00;33;44;13 AI So if you ask me when, we'll be ready for generally. AI Last year or two years ago, I would say not yet, but now we in the era where everything seems possible. So I remain extremely optimistic about generative in some of these last language models that will help us analyze unstructured data even more efficiently. Well, therein it's deeply fascinating and exciting stuff. 00;33;44;14 - 00;34;10;27 Thanks again for letting me pester you with these questions. If our listeners want to learn more about Sentinel, Operation Center or Mosaic or you, what's the best way for them to do that? So Sentinel has a poverty website where we post everything that we do. So is Sentinel initiative dot org. So I am a member of the Department of Population Medicine at Harvard Medical School. 00;34;10;29 - 00;35;00;16 So our website's population is a thought, but these would be two places that would be very informative for audience. Who wants to know more? All right. We appreciate that. And to our listeners, go ahead and subscribe to the show. Feel free to listen to past episodes because they are free. There's a lot to learn here. And if you want to learn more about how Oracle can accelerate your own life sciences research, just go to Oracle dot com slash life dash sciences and we'll see you next time on Research in Action.
How can patients and their families become more integral in the clinical research process? How can patient-led research become more accepted in the scientific community? How are inspiring groups forging new, collaborative paths for science and medicine, and reshaping how medical research is conducted? We will tackle those questions and much more in this episode with Amy Dockser Marcus, a Pulitzer Prize-winning journalist and author of the recently published book, "We the Scientists: How a daring team of parents and doctors forged a new path for medicine." Amy is a veteran reporter at the Wall Street Journal and won her Pulitzer Prize for Beat Reporting in 2005 for her series of stories about cancer survivors and the social, economic, and health challenges they faced living with the disease. She has covered science and health at the Journal for years, and she also earned a Masters of Bioethics from Harvard Medical School.
--------------------------------------------------------
Episode Transcript:
00;00;00;00 - 00;00;24;19
How can patients and their families become the centers of research? What is open science and who are citizen scientists? We'll explore those questions and more on this episode of Research and Action in the lead in. Hello and welcome back to Research and Action, brought to you by Oracle Life Sciences. I'm your host, Mike Stiles, and our guest is Amy.
00;00;24;19 - 00;00;48;22
Dr. Marcus That's right, that Amy Marcus, the Pulitzer Prize winning journalist, reporter at the Wall Street Journal, a Pulitzer Prize, was won for her series of stories in 2005 about cancer survivors and the social and financial challenges of living with cancer. Her beat, as you would imagine, has long been science and health. And she holds a master's of bioethics from Harvard Medical School, and she's an author.
00;00;48;22 - 00;01;04;26
Her book is We The Scientists How a Daring Team of Parents and Doctors Forged a New Path for Medicine. So this should be interesting as we talk about collaborative, open science and the rise of citizen scientists and patient led research. So thanks for being with us, Amy.
00;01;05;01 - 00;01;06;22
I'm happy to speak with you today.
00;01;06;22 - 00;01;26;29
Great to have you. In your new book, you take readers through some really, frankly, heart wrenching experiences that patients and their families have gone through with a rare and devastating disease called Niemann-pick. Hopefully I'm pronouncing that correctly. Tell us about the book and that disease and what fascinated you about this story.
00;01;27;14 - 00;02;01;21
The origin of the book really is a personal story, which is my mother got diagnosed with a rare type of cancer. And when I tried to do research on her behalf, I started to learn how challenging it is to develop drugs for rare diseases. After she passed away, I took some time off from the Journal. I had a research grant from the Robert Wood Johnson Foundation and I started traveling around the country looking to see if there were new models that might accelerate drug discovery.
00;02;01;29 - 00;02;25;21
And during the course of that research, I was introduced to a group of parents whose children have this rare and fatal genetic disorder, NIEMANN-PICK type C disease. It's a cholesterol metabolism disorder, so the cholesterol doesn't get out of the lysosome and that compartment in the cell and it starts to build up and it causes all kinds of problems.
00;02;25;21 - 00;02;52;12
And the children eventually lose the ability to walk and to talk and to feed themselves. But the parents that I met wanted to do something novel. They had found a group of scientists and researchers and clinicians and even some policymakers in the government that wanted to work together as partners and to see if they could accelerate the search for a cure or an effective therapy for an epic disease.
00;02;52;19 - 00;02;58;11
And they let me follow along during the course of that partnership for over ten years.
00;02;58;24 - 00;03;05;24
That's amazing that you got that kind of insight. And what did you learn over the course of that ten years?
00;03;06;22 - 00;03;34;15
Well, I was really interested in how they saw the production of science in a different way. They all wanted to try to save or extend the children's lives The disagreements lay in. How do you go about prioritizing drugs? What amount of risk is a patient or a patient's family willing to take compared to the level of risk that a doctor or scientist wants the patients to take?
00;03;34;15 - 00;03;54;14
These sorts of tensions arose, I think, in part because they were modeling a new method of where the patients expertise was considered as valuable or even at the center of this of this project. And that's not usually how it is.
00;03;54;14 - 00;04;09;09
But that's rare, right? I mean, in our in the culture of our health care system, it's not really common that the patients input or the patients families input is invited at all.
00;04;09;19 - 00;04;34;11
Yeah, I think that that you're right about that. I mean, the traditional way of setting things up is that the scientists devise the hypotheses and they then construct trials in conjunction with clinicians and sometimes with pharmaceutical companies, of course. But in this particular collaboration that I was describing, the drug was not in the hands of a pharmaceutical company.
00;04;34;11 - 00;04;59;06
It was widely available. And so the partnership was truly about, you know, going to be conducted at the NIH. And therefore it gave the parent and the families, I think, more leeway to do this experimental idea. What if we all recognized each other's expertise? What if we all saw each other as equal partners? What if we got to weigh in?
00;04;59;13 - 00;05;20;24
Not in once. You've already set up the clinical trial, but at the very, very outset, when you're simply going through the scientific literature to come up with potential compounds, when you're thinking about what might work, when you're trying to prioritize what to do first, second and third, all of those things where patients don't always have a voice. But in this case they really did.
00;05;21;07 - 00;05;43;16
You know, we just had Hilary Hannah Ho on the show. She's secretary general of the Research Data Alliance, and we talked about open science and open data and how important all that is to getting the scientific breakthroughs that will actually help people and get to those breakthroughs faster. But open science can kind of be polarizing. There's some confusion around what exactly it means.
00;05;43;23 - 00;05;48;14
How would you define or describe open science and citizen scientists?
00;05;48;27 - 00;06;34;22
Yeah, I think that's a really good point, that there isn't one sort of accepted name and that there are many names and people use different phrases when they're thinking about different things. For me, I used the term patient LED research and I often use the term citizen science. And what I meant by that was, again, what we've been talking about from the outset, which is a recognition that the patient, the patient experience should be at the center of everything, a recognition that the patient and the families are experts, that they have the ability not only to be beneficiaries of scientific knowledge, but also creators of scientific knowledge.
00;06;34;27 - 00;06;46;15
And to me, that shift the idea that you can be a creator of scientific knowledge is the fundamental one that needs to happen if we're going to really reach the goals that I think we all want to reach.
00;06;46;29 - 00;07;11;10
So here's something we highlighted in your book. Quoting here Science is inherently a social enterprise. Yet too often scientists operate behind closed doors, removed from the very people they intend to help. That's struck me as kind of a mike drop statement with a lot of truth to it. But did the pandemic change anything? Was the work still removed from those patients on ventilators and ICU?
00;07;11;20 - 00;07;52;04
So I do make a point in the book to draw some parallels between the various patient led research movement experiences that I describe and the COVID 19 pandemic, and in particular the group of patients that call themselves long COVID patients, where they're suffering symptoms for many, many months. I argue that COVID allowed us in real time to to recognize that anyone can be an expert and that now that is something that it was easier to see during the pandemic because there was a novel virus, there weren't established experts yet.
00;07;52;14 - 00;08;25;28
And so while doctors and scientists and the government were scrambling to try to help patients, I think they also saw themselves for the first time as part of this effort to understand the disease. Together, there wasn't already an understanding of COVID 19. And so what I say in the book is that we can draw from from that experience and sort of take that part of it forward where we say patients should be at the center of things.
00;08;26;06 - 00;09;07;01
Patients are experts. Patients are able to identify things that many scientists or doctors didn't have time to recognize because they were they had to focus on trying to save lives and, you know, working in a vacuum at that point. So there also was a sense of urgency. Like one of the things that I was struck by during the pandemic as a as a science reporter was that scientists were able to put their papers online right away on these websites before it had gone through the full peer review process because it was recognized is so essential to get this information out there as quickly as possible.
00;09;07;09 - 00;09;29;16
And everyone understood that maybe there were going to be some mistakes. It wasn't fully vetted, but it was out there. Not only was it publicly available to the doctors and scientists who are also studying it, it was publicly available to patients and people who are simply interested. And long COVID patients organized themselves, did research on themselves, and they also published their papers on these websites.
00;09;29;16 - 00;09;43;22
I think those types of models where patient researchers can be contributors and can benefit from the information to fuel their own research, I think that should move forward and is it shouldn't be just a relic of the COVID 19 pandemic.
00;09;44;07 - 00;10;05;03
But what isn't there a risk of chaos a little bit? Because we're always told, hey, whatever condition you have, don't go Googling it on the Internet. You'll just go down a rabbit hole and, you know, worry about all these conditions that you may or may not have. So what is the risk of, like you said, mistakes and wrong information being published?
00;10;05;13 - 00;10;27;11
Well, even the traditional peer review process in science publishes papers that turn out to have mistakes in them. Papers are retracted all the time. And there is a well-known phenomenon that peer reviewed papers sometimes the results can't be replicated. I mean, that's the problem for science. I don't think that's a problem just for having patient researchers get involved.
00;10;27;28 - 00;10;54;27
I also think that the advice not to Google something is both old fashioned at this point and probably unrealistic given that almost all of us are connected in some way through the Internet. My sort of idea, rather, is that let's use the Internet and other methods to become better partners. Let's share good quality information online that people have access to.
00;10;55;06 - 00;11;20;20
Let's form partnerships where we can collaborate, where among experts, the people that I was talking to and interviewing and spending time with the parents, they weren't saying, Hey, we're trying to go it alone. We know everything. No, the opposite. What they were saying is we have very relevant and valuable information. We are experts because we live with this disease and we know what level of risk we're willing to tolerate.
00;11;20;20 - 00;11;43;28
And we do our own research. But we need partners who can also help us fill the gaps where we don't have knowledge. We want to collaborate with scientists, we want to collaborate with clinicians treating our children. We want to collaborate with government scientists who have access to data and and robots and things that we're not going to have in lab equipment that we don't have access to.
00;11;44;06 - 00;12;02;19
So no one's saying, go down a rabbit hole by yourself. What people are arguing is let's find ways to pool information, and by pooling everyone's information, we can sort through more quickly what's good, what we think is good, but might turn out not to be good later. And what can benefit all of us.
00;12;03;04 - 00;12;20;02
Yeah, and from a technology standpoint, gathering that data and organizing it and working with it is becoming more possible than ever. COVID should have scared our health system out of its mind. Did it? And is that leading to any systemic changes in science and health?
00;12;20;15 - 00;12;46;19
Well, I'd like to focus on what my book was focusing on, which is can a group of patient activists and scientists and clinicians and government policymakers working together make changes to the system? And I think the answer is yes. You can make changes to the system. The patient researchers that I was talking to and the families I was talking to, they built on activist patient work that had gone before.
00;12;46;19 - 00;13;10;06
And there have been responses in the past. HIV activists were able to influence the FDA to pass the accelerated approval rule that now allows drugs to be approved more quickly. And I think that, you know, compassionate use program that FDA has the patients in my family, the patients in my book and the families benefited from that as well.
00;13;10;17 - 00;13;48;01
So there have been changes along the way. But I think what my book is arguing for, and I think this message came out of the COVID 19 pandemic as well, is that even with all the changes that have been made in the past, the patient experience is still not at the heart of the system. And I think that's the message that all of these families are saying put the patient experience at the heart of things, and then you will see that the system, when you configure the system around the patient centric experience, you'll see that it will work in a different way and an I think, a better way.
00;13;48;02 - 00;13;50;02
But we need to run that experiment.
00;13;50;17 - 00;14;12;20
So we mentioned the concept of citizen scientists. That's what we've been talking about. These are people that pursue what they pursue, driven by mostly love and urgency for their kids, which is just a whole different level of motivation than most researchers have. I think you have a few stories about, you know, people like Chris and Hugh Hempel and and some others that went through this experience.
00;14;13;02 - 00;14;34;21
I want to make a point here that I think also is really important for people to understand who are listening to this. The parents in my book and you know, you cited Chris and Hugh, they were definitely among the pioneers who did this. And there was Phil and Andrea Morella, and there were also Darrel and Mark Poppea who are who are part of this, too.
00;14;34;21 - 00;14;57;29
And many, many other parents. I mean, the Parseghian Research Foundation and the National Niemann-pick Disease Foundation, all family driven. The people who are doing this. Yes, they are driven by their love of their children. They are driven by a sense of urgency. But they're not going to the FDA and saying, Hey, please pass and approve a drug because we love our children.
00;14;58;05 - 00;15;24;05
Please pass and approve a drug based on our emotion. No, not at all. They want to give effective drugs to their children. What they are saying is we are creating scientific knowledge and we think that that should be part of this approval process, that should be part of the drug development process. I just want to give some examples that I cite in the book where the parents were creators of scientific knowledge.
00;15;24;24 - 00;16;07;11
You had parents who read the scientific literature, published scientific literature, called up. The scientists interviewed the scientists came up with hypotheses themselves that they proposed to scientists, contributed to the two scientific experiments, coauthored papers that were published in the peer reviewed scientific literature. You know, went to the NIH regularly to have meetings where they helped contribute to assessing and prioritizing which compounds should go first in terms of advancing them into clinical trials, contributed their thoughts on the risk benefit analysis in devising the clinical trials.
00;16;07;22 - 00;16;34;28
One of the parents went to an FDA sponsored workshop for how to file an orphan drug designation, which is part of the approval process and the long process to getting approval for rare disease drugs. And went to the workshop, participated in the workshop, presented scientific data to the regulators, met with the regulators, and earned an orphan drug designation for one of the compound Cyclodextrin that got moved forward.
00;16;35;07 - 00;16;46;24
So yeah, they have a sense of urgency and yes, they love their children and want to save their lives, but they're producing real scientific knowledge and I really hope that that people take that message away from reading the book.
00;16;47;10 - 00;17;08;15
So those are great examples of exactly what citizen scientists do that sets them apart from just patients who are not doing that level of research, that depth of research. You talk about Chris Austin and the book, and I'm going to read another quick excerpt here, The Promise of Genetics to Deliver new interventions, new drugs and new treatments for patients is not going to happen.
00;17;08;15 - 00;17;27;28
Chris told his boss, unless there's some way to get through the valley of death. Francis gave Chris a green light to pursue his vision. So the boss in that excerpt is former National Institutes of Health director Francis Collins. What is the Valley of Death and Chris's role in citizen led research?
00;17;28;06 - 00;17;54;21
Great. No, that's a great question. So Chris Austin is a Harvard Medical School trained neurologist, also with a background in genetics who worked at pharmaceutical companies as well, and then found his way to the niche where he worked for Dr. Collins and became also a director of one of the institutes at NIH called Ed Katz, the National Center for Advancing Translational Science.
00;17;55;06 - 00;18;23;29
And one of the sort of green lights he got from Dr. Collins was to set up a lab that would have robots that were sort of at the same type of robots that pharmaceutical companies have that would work around the clock and could rapidly screen drugs to try to find compounds that might work for diseases. And what Chris Austin's idea was is that let's screen these vast libraries.
00;18;24;04 - 00;18;50;06
Let's find some drugs that might be promising, and let's also find patient partners. Let's find scientist partners, and let's then try to take all this data and move it forward together. One of the hypotheses that Chris Austin said he had as a scientist was can drug development go faster if patients and families are part of that process from the very beginning?
00;18;50;18 - 00;19;17;02
And one of the things that Chris Austin was trying to get around is this valley of death, which is this, you know, where compounds kind of go to die. You have a great idea as a scientist. But how do you get that idea from the bench to the clinic and to a patient's bedside? And the Valley of Death is just all the various obstacles that end up making it hard to develop a drug.
00;19;17;13 - 00;19;39;21
Some of it can be scientific. You know, you test it in a in a mouse or an animal, you test it in the lab and it turns out to be toxic for the cells or the amount of drug that you need to give to a person is so high it's not realistic or a drug company decides they want they don't want to put any money into it anymore or it gets or a drug company gets bought and they don't want to pursue it anymore.
00;19;39;21 - 00;20;02;08
And there's a million things that happen in the Valley of Death. But Chris Austin's vision was if we can involve patients and families as partners, along with scientists and drug developers and government officials from the beginning, maybe we can get things out of the Valley of Death, or maybe we can fail faster and find the successful compounds more quickly.
00;20;02;25 - 00;20;22;23
Yeah, a big takeaway from your book is the need to build bridges between science and citizens. But and we talked touched on this a little bit. You can't sacrifice scientific rigor or safety. So what are the challenges to building these bridges? What's holding that process back, especially when it does come to drug discovery and clinical trials?
00;20;23;09 - 00;20;47;05
So I think that there is a variety of issues that make it challenging to build bridges. For one thing, there's often a tension between, you know, people who are sick or are advocating on behalf of people who are sick, who really want to focus on the here and now. They they really need something to help their loved one right now.
00;20;47;19 - 00;21;22;19
And often, you know, clinical trials are an experiment. And when you enroll in a clinical trial, you're told this is not designed for the benefit of you. This is designed to benefit future patients. And therefore, it's not a treatment and it's not the equivalent of clinical care. And that can be a source of frustration and tension. And often also when research crews are doing research, they weigh the risk benefit assessment of moving drugs forward differently than people who are trying to you know, solve a problem now.
00;21;23;00 - 00;21;48;14
So I think that and that came up in this partnership in my book. It came up in this partnership in my book a lot. And yet I think each side was able to get a sense of what the points were, what the what the tensions were. But again, in my opinion, one of the ways that they overcame this divide was by both sides saying patient centric medicine is the way to go.
00;21;48;15 - 00;22;16;29
Patient centric science is the way to go. There are ways to collect data in a rigorous manner that can both benefit patients now and also not stop you from insights that will lead to benefits in the future. There are ways to come to terms with that. Some people have a higher acceptance of risk than others. I mean, we see movement towards that already right now.
00;22;17;01 - 00;22;23;01
I think that one of the messages of my book is to try to accelerate that even further.
00;22;23;25 - 00;22;37;19
Well, to that point, you say in the book, government and agencies like the FDA and NIH have a vested interest in helping these science and citizen partnerships succeed. Do they understand that? And what role should government be playing to move this forward?
00;22;38;01 - 00;22;57;01
Well, government is not one person. You know, so but I think that the book shows that there are people in the government who were partners with the patients and the families and the scientists and the clinicians. I mean, this whole book is about a partnership. And Chris Austin, although he's no longer in the government, he left the government.
00;22;57;10 - 00;23;28;05
He was in the government at the time, and he was a partner with these people. So I think that the government has shown in the book that, you know, and outside of my book, obviously interest in investing in new ways to do science, interest in investing in new ways to accelerate science, the government is supposed to represent the interests of the people, and the people's interest is in being healthy and in and trying to find solutions for drugs.
00;23;28;14 - 00;23;56;15
So in the book, I do talk about how the patients and the families in my book were able to directly talk to FDA regulators. Some of the parents went to workshops that the FDA was sponsoring. They had conversations with FDA regulators. I think those types of workshops are really novel and they really are fruitful because they allow the families and the patients to really think like scientists and to produce science as they can and should do.
00;23;56;16 - 00;24;21;16
They want to produce science. And I think also one of the messages that Chris Austin gave at representing the NIH was that the NIH is here to be your partner, and we're open to coming up with novel ways of accelerating science. So I think that there's there's openness to doing this, but of course, always more can be done.
00;24;21;17 - 00;24;51;16
I mean, patients have a sense of urgency, and that's the message that they bring to the government all the time. I mean, in the book, I, I describe FDA advisory committee hearings that are held when the FDA isn't sure about the data and they want to have a public hearing about it. And many of the parents and families showed up and gave testimony not just about their thoughts and their opinions, but about the data that they had gathered, the science that they were generating, that they wanted to share with the FDA and be heard.
00;24;52;00 - 00;25;16;13
What role does Rules Framework's guidelines play and what we're talking about here? I think you even your former advisor, was part of a group of scientists that worked on this framework. And the platform for patient led research, I think was spearheaded by that advisor, former advisor and a group of scientists. What's the infrastructure that needs to be put in place for this to work?
00;25;17;08 - 00;25;46;03
So, yes, So the advisor that you were referring to, Effie Diana was my advisor in my bioethics program and she does a lot of pioneering research on patient led research movements. And she and a group of collaborators, scientists and, and social scientists and clinicians and, and policymakers got together and tried to devise what they called a new social contract.
00;25;46;13 - 00;26;14;17
What they argued is, is that patient led research is a novel form of research that doesn't fit into the traditional regulatory standards that have guided, you know, clinical trials and human subjects research up until now. And that's because the traditional methods of regulation are based on the idea that scientists are going to be leading the research and doctors are going to be leading the research.
00;26;14;26 - 00;26;42;04
And that still is the traditional model. And they usually are leading the research. And in those cases, they often have more information and more power than the traditional patient or human subject. So Effie and her collaborators weren't arguing. We're arguing that the traditional rules should be thrown out because obviously patients do need protection and human subject research does need regulatory guidance.
00;26;42;11 - 00;27;17;26
But what she and the others were saying is let's also think about these new ways of doing research and how we can get scientists and clinicians to accept the results. That patient led research arrives at. And one of the ways she and the others said is let's come up with ways that patient researchers can seek ethical guidance. Let's put tools online that they can use so that they can devise experiments in ways that approach the rigor that traditional scientific experience experiments do.
00;27;18;06 - 00;27;52;04
Let's generate research that's of benefit to the people now, but also can be useful in guiding treatments in the future. Let's make a path towards publishing their data in peer reviewed journals. Let's make them part of the peer review process. I mean, you do have journals now that have patient researchers participating in peer review of scientific papers. And you have groups like Pachauri that ask scientists and patients to collaborate together on experiments.
00;27;52;13 - 00;28;24;24
So I think I think what she and the others were getting at is the current contract that we have may still be fine in certain circumstances, but isn't set up to address this new kind of research that's being done. And if we want it to be generalizable, scientific knowledge, which is always the gold standard, then we need to work together to help all of the partners to do better research that meets the standards that we can all except.
00;28;25;09 - 00;28;40;27
When you kind of make the promise of patient led research obvious. But, you know, how many times do we see things with great promise get tied up in knots? Is a paradigm shift likely? And if so, how long of a runway is that going to need?
00;28;41;15 - 00;29;01;11
I mean, I don't know how long it's going to take, but if there is a message in my book, if there is a message from the people that I focused on in my book, I mean, they've been working together for more than ten years. They've made a lot of progress, but they're not where they want to be yet.
00;29;01;20 - 00;29;23;29
So that's a long time. And I think that they want to go faster. I think the message of long COVID patients is we need to go faster. I think the message of HIV activists and breast cancer activists and disability activists is we need to go faster. And I don't think that you need to change a paradigm in a day.
00;29;24;12 - 00;29;53;19
Paradigms, by definition, take time to change, and they involve a lot of debate and discussion, dissension. And that's what happens in a society. People have different, different views. But I think what we're getting at here as a society is that patients need to be at the center of any paradigm that exists and that if everyone works together towards that goal, they may not agree how to get to that.
00;29;53;24 - 00;30;14;21
They may have different ideas on how to ensure that the science is rigorous and works. But if they keep this notion always at the center that the purpose is, is patient centered science, then I do think that you can end up with a paradigm that works better for more people.
00;30;15;16 - 00;30;27;10
One of the chapters in your book is Cathedral of Science, and in it a professor at Harvard. Had you read the story Cathedral by Raymond Carver. Why did they have you read that? And how does that relate to what we've been talking about?
00;30;28;04 - 00;30;55;26
Yeah, I mean, I say in the book that when we were told to read Cathedral by Raymond Carver, I was really surprised because usually in in my bioethics classes when we talk about stories and narrative bioethics, many of them involve sort of cases drawn from real life and cathedrals, really a quiet story that involves a married couple that seems to be drifting apart.
00;30;56;06 - 00;31;16;24
And the wife invites a friend who happens to be a blind man to come and stay with her and her husband. And the husband's a little bit jealous of the relationship that this person has with his wife and he doesn't really know what to say to him. And the wife goes to sleep and leaves these two men alone watching TV together.
00;31;17;00 - 00;31;38;19
And they start to watch a program about the building of a cathedral. And the narrator says to the blind man, Have you ever seen a cathedral? Do you know how to build a cathedral? And the blind man says, Let's draw one together. And the two of them construct a cathedral together. The man places his hand on the husband's hand, and they draw that cathedral.
00;31;38;27 - 00;32;01;23
And at the end of creating this cathedral, it's the blind man who says, Let's put some people inside, inside the cathedral. What's a cathedral without people? And I thought about this story all the time as I was spending time with the families and the scientists, because so many of the scientists were products of the Cathy trial of science.
00;32;01;23 - 00;32;34;13
They were the products of the best medical schools. They worked at the NIH. They I mean, they they really were, you know, part of this edifice that's been constructed and that has benefited so many people. And one of the things I kept thinking about is how do we put more people in this cathedral? I mean, that's really one of the messages that came through in this partnership that the parents and families and scientists and doctors and government officials were constructing a cathedral without people isn't really what you're looking for.
00;32;34;20 - 00;32;52;05
You're you're looking to use the power of science and research to help people. That's should be the goal of everything. And that's really the message I took from this story, that it touched me in just such a fundamental way. And it wasn't even a story about science.
00;32;53;27 - 00;32;57;18
As literature often does. That inspires us in many different ways.
00;32;57;21 - 00;32;58;20
Absolutely.
00;32;58;27 - 00;33;20;02
What did I miss? I mean, what is it that our listeners should know that you cover in the book that's important for them to know or some way that they can help or participate in this kind of effort? Or is there something that a follow up book might cover, something that you think needs additional exploration?
00;33;20;11 - 00;33;53;25
Well, I mean, I think that the message of the book is that we can all be scientists, right? I mean, it's in the title. We, the scientists, and I chose a title that echoes We the People, because I wanted people to think about the fact that what works best is a partnership. What works best is when we all come together and try to bring our different visions forward and to come up with something that will benefit all of us.
00;33;54;07 - 00;34;15;25
I think, you know, one of the things that I was struck by during during the research, not only for this book, but also when I, you know, covering health and science as a reporter is that all of us really are patients. We're either patients now or we were in the past or we will be in the future, or we love people who are patients.
00;34;16;04 - 00;34;50;28
We're advocates for those people, even if we're a doctor or a scientist, we're often on the other side of the table either trying to advocate for people we love or because we're patients. And so I think we all have a vested interest in creating a system that works well for all of us that remembers that we need treatments and that we that we need science and that all of us are experts in our own lives and that we can do research in a way that can contribute to advancing health and wellness for us all.
00;34;50;29 - 00;34;56;00
So I feel like that's the message that I hope is the takeaway of the book.
00;34;56;12 - 00;35;03;10
Well, I'm pretty sure there are listeners who are interested in the book and getting it or getting in touch with you. How can they do that?
00;35;04;00 - 00;35;26;00
So there are a variety of ways to get in touch with me. My email is publicly available. It's Amy Marcus at WSJ dot com. I'm on Twitter at Amy D Marcus. You can go into the bookstore and get the book, you know, in person, or you can order it online. You can get it from bookshop. You can get it from Powells.
00;35;26;00 - 00;35;32;18
You can get it from Amazon, Barnes and Noble. I mean, they're, you know, any, any, any place online. You can order the book.
00;35;32;26 - 00;36;03;05
Great. We appreciate that. And we want to thank you for being faithful listeners to Oracle Life Sciences, Research and Action. As always, we invite you to subscribe so you don't miss a single episode. And also maybe tell your friends and colleagues about the show as well. And we'll be back next time with more research and action.
How can an extensive collection of real-world data help find more diverse and better participants for clinical trials? How do we create a continuously learning ecosystem that helps bridge the gap between clinical research and clinical care? And what are the biggest challenges to patient record standardization and personalized healthcare? We will learn that and more in this episode with Dr. Lu de Souza, Vice President and Executive Medical Officer of the Learning Health Network, which is a division of Oracle. Dr. de Souza leads a team that seeks to help health organizations integrate clinical research into everyday care. That means addressing clinical discovery cost, time, and patient inequities. She's also a huge advocate for real-world data and bringing technology to bear for true healthcare advancements. Dr. de Souza has years of experience in health informatics and was the most recent CMO of Cerner in North America. She practiced pediatric hospital and emergency medicine until 2020 and has held multiple leadership and teaching positions.
--------------------------------------------------------
Episode Transcript:
00;00;00;01 - 00;00;25;21
How can an extensive collection of real-world data help find diverse participants for clinical trials? Are some organizations already using the concepts of a continuously learning ecosystem. And what are the biggest remaining challenges to patient record standardization and personalized health care? We'll find all that out and more on today's Research in Action episode.
00;00;27;05 - 00;00;47;23
Hello and welcome to Research in Action, brought to you by Oracle Life Sciences. I'm Mike Stiles and our guest today is Dr. Lu de Souza, vice president and executive medical officer of the Learning Health Network, which is a division of Oracle Life Sciences. In a nutshell, Dr. de Souza leads a team that seeks to help health organizations integrate clinical research into everyday care.
00;00;48;03 - 00;01;11;28
That means addressing clinical discovery, cost time and patient inequities. She's also a huge advocate for real-world data, bringing technology to bear for true healthcare advancements. Dr. de Souza has years of experience in health informatics and was the most recent CMO of Cerner in North America. She practiced pediatric hospital and emergency medicine until 2020 and has held multiple leadership and teaching positions.
00;01;12;12 - 00;01;16;03
Dr. de 'Souza, thank you so much for taking the time to be our guest today.
00;01;16;14 - 00;01;20;12
Now Thank you, Mike. It's really a pleasure to be here. And please feel free to call me Lu.
00;01;21;02 - 00;01;29;21
There's a lot of ground to cover here. But first, let's just find out about you. What was the life path that brought you to where you are today and doing what you're doing today?
00;01;30;15 - 00;01;55;05
You know, as you mentioned, I am a pediatrician who focused on taking care of sick kids in the hospital and the emergency department. And I really loved my job. But like many doctors, I felt frustrated by the inefficiencies of health care. And I felt very frustrated with the limitations of time and data that we suffer both of those things are super essential to make the fast decisions that we need to make.
00;01;55;23 - 00;02;16;20
So I started thinking about technology and the role that it could play in solving some of these foundational issues. And also, you know, we always want to see how many more patients we can help. So I felt like the pivot would allow me to take care of patients in a different way, but at higher numbers. It was not easy decision.
00;02;16;20 - 00;02;41;20
It was very hard for me to leave full time pediatrics, so much so that I stubbornly continue to practice for the first ten years that I was full time at Cerner. But at the time that I was considering joining Cerner, my mother's breast cancer was misdiagnosed and that happened because of inequities, fragmentation in care and a lack of standardization that exists today.
00;02;42;00 - 00;03;08;03
Eventually, she turned out okay with that. But these missteps and delays in diagnosis led to a much more aggressive course of treatment and the complications that came with it. But this experience really sealed the deal for me. I felt like there was a lot of work that I could contribute to so that led me to my career in informatics that started with EMR implementations and technology enabled process improvement.
00;03;08;28 - 00;03;30;25
Then ten years later, my cancer warrior mom was diagnosed with a different cancer. This one was rather rare and aggressive, and we quickly found that there was not enough research to support any specific type of treatment for her and that the survival rate for anything that they could try was pretty low. And that was not good enough for her.
00;03;31;07 - 00;03;57;05
She decided to forego treatment and instead focus on having better quality of life for the remainder of the year that she was with us all of nine months. In stories like that, Mike, are super common. Many of our listeners, I'm sure, have gone through something like it and as devastating as it is, these life experiences also help shape us and they bring these opportunities that we hadn't considered.
00;03;57;19 - 00;04;25;17
And sure enough, only a few months after her passing, the Learning Health Network was founded and I was asked to help out and I was immediately drawn to its mission and vision and the impact that it could have in cases like my mom's. So it took a little bit of time to get here. But last year I was able to take on a full time role with Learning Health Network, and I'm just super excited to be a part of this awesome team that brings transformation to research.
00;04;26;07 - 00;04;29;03
Okay. And tell us what the Learning Health Network is.
00;04;29;09 - 00;05;01;06
All right. So I'm going to start with the why and why it was created and paint this picture for for everyone to understand how important this is today. Clinical discovery. So how we get to medicines and treatments and different diagnostics is still a major challenge for life sciences and health care organizations. And because these two sectors of our industry are mostly siloed from one another, it's a very onerous process for patients and providers to participate in clinical trials.
00;05;02;01 - 00;05;27;13
Even myself as a doctor who understands the language of medicine had a really hard time finding out what types of trials were available to my mom, just as an example. So for context here, when we're bringing a new drug to market, it takes approximately 17 years and it costs an average of $2.5 billion. That those are crazy numbers, right?
00;05;27;22 - 00;05;59;13
And the biggest driver of that time and cost is getting to the patients, identifying the right patients, recruiting them and enrolling them into these trials. And about 20% of these clinical trials fail because they cannot recruit enough patients. And overall, only 3% of our population participates in these studies. Of course, 3% of the population cannot be representative of the diversity that we have here in United States or across the globe.
00;06;00;02 - 00;06;30;04
So the Learning Health Network was created to help solve these problems with the concept of these patients are in everyday care, and that's where trials need to go. We need to bring research into everyday practice. The Learning Health Support Network is a partnership between Oracle and health systems that we serve, and these organizations contribute their de-identified data to serve as the fuel for research and clinical discovery.
00;06;30;18 - 00;06;59;09
So this data set is called the Oracle Real World Data, and I'll call it our RWD from now on to to make it easier. And it's one of the largest datasets in the world like this in exchange for that data contribution, which we're immensely grateful for, Oracle provides these organizations the access to the data set so that they conduct they can conduct their own research, and we provide that at no cost.
00;06;59;21 - 00;07;22;05
We also do all of the heavy lifting for them, so it doesn't take any effort on their side to get the data there to make it de-identified and normalized. We do all of that work and then we offer a variety of benefits for them depending on where they are in the course of doing research, whether it's data science or clinical trials and so on.
00;07;22;22 - 00;07;58;05
So the Oracle Real World Data is home of about 108 million active longitudinal records from all over the United States, covering about 2600 facilities. And this membership comes from a variety of organizations. These whole systems can be large, multistate and academic centers all the way down to critical access hospitals. And this combination, this this composition of membership is intentionally done and balanced by us.
00;07;58;05 - 00;08;37;11
So they're very similar in numbers. And that becomes our superpower by having data from such a wide range of facilities and such diverse communities, and means that people who never had access to clinical research near their homes can now be represented in this dataset and represented in a lot of research that gets done. And it also means that this research, a big data set, matches fairly well to the US Census and brings that much needed diversity that we're lacking in clinical trials today, and that helps decrease the the health and research inequities.
00;08;38;01 - 00;09;03;26
How we do this is again, by using the dataset to find the patients. So we find patients that are good matches for trials, and then we find trials that are good matches for those sites and for that community. And the data can also be leveraged like I said before, by organizations to drive or derive clinical insights by using data science and the tools that Oracle provides.
00;09;03;26 - 00;09;05;10
That is us in a nutshell.
00;09;05;28 - 00;09;28;17
I think there's a lot of people listening that would be really surprised to find out the thing that slows down getting new drugs and new treatments to market isn't necessarily like bureaucracy or red tape or lack of scientific knowledge. I think people would be surprised to find out the real problem is being able to find and get people and a diverse group of people to participate in these clinical trials.
00;09;28;17 - 00;09;32;09
So that's probably what adds great value to this dataset, right?
00;09;32;29 - 00;09;54;27
Yeah, I mean, the things that you mentioned definitely are barriers that we have to cross as well. But it was surprising to me as well as I entered into this space. Just as an aside. One of the reasons it's so important for clinical research to be embedded into care is because we people, patients, we trust our health care providers.
00;09;55;10 - 00;10;09;15
You know, these are the people that we listen to and take advice from. So the studies have shown that the majority of patients that enter clinical trials or accept to participate are because those trials were discussed by their providers.
00;10;10;05 - 00;10;15;00
And what's your role in it? What what constitutes a really good week or a month for you?
00;10;15;15 - 00;10;47;21
As the executive medical director, my main responsibility is really to the health system. Members. I have a team, a super awesome team of clinical researchers that ensures these members gain value from their incredible data contribution and also know how to leverage it. We provide programing around them so that they can learn, collaborate, network and so on, and I also lead our clinical research strategy and operations, which is focused on two major components.
00;10;48;03 - 00;11;26;12
One is bringing the funded research opportunities to the members that want to have clinical research research programs, funded opportunities, meaning they come from life sciences organizations and cross, and also helping these organizations that are smaller to become research ready. So these are organizations that don't today have a program or are beginning and they need more support. The second major focus is breaking down the silos that exist today between clinical research and care delivery, and that will help drive the awareness, the efficiencies, the safety.
00;11;26;21 - 00;11;46;12
It will help us improve that patient recruitment into trials and so on. Now, boy, my my day to day changes quite a bit. So a good week or a month is hard to describe, but I would tell you that a really good day is when one of our community, Rural Health Hospitals, is awarded a study that we facilitated.
00;11;46;23 - 00;12;10;29
And because we know that those patients will be represented, that community will be represented in research and they will gain access to cutting edge medical interventions. It feels really good to know that we played a part in that and another really good day is also when our members use this data set to gain insights that lead to positive patient outcomes and that we're blessed to hear about that quite often.
00;12;11;01 - 00;12;19;04
Our Learning Health Network members have published over 500 peer review articles using this data set.
00;12;19;17 - 00;12;32;11
Best case scenario if the Learning Health Network gets its job right, how can that change how health care data, The gathering and use of real world data is used to improve patient outcomes and health care policy?
00;12;32;23 - 00;13;19;26
Yeah, I would just reiterate a couple of things. With the Learning Health Network and its real world data, we'll have real data in real time deriving insights to lead to better care and better outcomes in the continuously learning ecosystem. We'll be able to quickly restudy and improve upon those longstanding medical practices we have today. So the word restudy is really important because we do have a lot of medical practices today that are gold standard and they're based on old research or based on research that didn't include certain populations, didn't include the necessary diversity or, you know, certainly the composition of us as human beings has changed.
00;13;19;26 - 00;13;43;22
So it is very important to ensure that we're still providing the best care and we can use the data for that. And that also will decrease these existing disparities and drive us closer to personalized care. The future also would look like we no longer will take so many years to complete clinical trials because we're going to know where the patients are for specific studies.
00;13;44;01 - 00;14;11;18
We're all going to know what those studies are more important to take to specific communities and patient populations. And and I think that is going to alleviate a lot of that, not just the time, but also the cost, because these costs are, you know, also what driving the cost of medications for our patients or interventions. Let's see, we'll be able to get to a more predictive and prescriptive models of care.
00;14;12;04 - 00;14;37;24
So understanding not just what happens with an individual now and how to take care of that problem, but also understanding what's likely to happen to Mike based on data points that we have on you today and behaviors. And this way we're able to intervene in the product in a proactive way. Imagine being able to predict and prevent a heart attack from happening three years from now.
00;14;38;05 - 00;15;10;24
All of these things are in our reach today. And the good news is that we're not too far from them. In fact, our our member organizations, the ones that are using the the real world data, are already experiencing practice and research transformation. But we certainly need to scale this up, scale this approach, and hopefully we'll get to a point in which the medical community will trust more on approaching research in this way and it becomes more the standard of care of how we discover and apply changes.
00;15;11;11 - 00;15;18;04
And I also think there is going to be a lot of other possibilities of this data set brings that we haven't necessarily conceptualized yet.
00;15;18;23 - 00;15;23;23
So follow up question You mentioned that organizations are already doing this. Can you give us an example or two?
00;15;24;19 - 00;15;50;12
Sure, sure. I'll give you two of my favorite examples, not just because I'm a pediatrician, but also because less than 20% of all U.S. research funding is dedicated to children. This is a highly underrepresented population in research, just by sheer numbers, which means that patient recruitment in trials is even harder. And conducting those trials in the traditional way is much more challenging.
00;15;50;28 - 00;16;24;20
So these two examples come from very proliferates users of real world data. And in these are pediatric hospitals. The first example comes from children's health of Orange County in California, where they have used RWD and machine learning to create what is the first published pediatric readmissions algorithm. So it's an algorithm that gives us a risk of readmissions for patients that were in the hospital or presented to the hospital, and they were able to accomplish that in the matter of months.
00;16;25;03 - 00;16;51;14
They then incorporated this risk score into the clinical workflows. They put it right inside of their Oracle, Cerner EMR, and they saw a 10% decrease in readmissions in the first two years, which is just commendable. You know, it doesn't just improve the quality of of these kids, but in today's healthcare, this change also amounted to $2.7 million in cost avoidance.
00;16;51;28 - 00;17;18;23
Everyone knows how expensive it is for hospitals when a patient is readmitted. The other example is Children's Mercy Hospital. Their research team leverages the rural data for a lot of projects, and this one is really near and dear to me because I worked in the E.R. with children. They looked at adolescents with migraine headaches that were presenting to the emergency department with these headaches and how they were being treated.
00;17;19;03 - 00;17;44;29
And what they found is that 23% of these kids across 180 AEDs were receiving opioids. I want to repeat that because that's really important to us. 23% of these children were repeating were receiving opioids as the first line of treatment, and that is not necessarily the best treatment for them. It is a misuse of the medication. And it's very aggressive.
00;17;44;29 - 00;18;23;20
And, you know, we're having already opioid crisis in this country. So then they they took that learning. They created a new clinical protocol and a clinical decision support tool that they incorporated into their Oracle, Cerner EMR, and were able to decrease the use of opioids for this condition to almost zero in their emergency departments. They had several in Kansas and Kansas City, Missouri, and just like, you know, a true learning health network, they they took this knowledge and the new clinical protocol and they presented that at headache conferences around the country.
00;18;23;20 - 00;18;39;13
And they know and and they're helping improve care for kids everywhere. So as you can see, the Learning Health Network is really a game changer for these organizations. They're now able to do research in a fraction of what it would be a typical research time.
00;18;40;01 - 00;19;07;20
That's really exciting and inspiring because you listen to every opioid addiction horror story and they all start out with an accident or a headache or a quote unquote, legitimate use for opioids that then turned into something worse later. So that's a particularly incredible impact you're having, but I'm assuming it's not that easy. So what are the biggest challenges to making the dreams you just outlined come true for society?
00;19;07;27 - 00;19;35;27
Yeah, you're absolutely right. We come across many barriers. But the cool thing about this team is we we don't find them discouraging. We're truly motivated to look for solutions in innovative ways, and we find partners that can help us as well. One of the biggest challenges of community based research is the lack of resources and infrastructure today that would allow these providers to offer trials and to conduct trials as a care option for their patients.
00;19;37;03 - 00;20;13;25
You have heard this in many other ways from other people of just how burned out providers and clinicians nurses are today. They're overwhelmed by the numbers. They don't have the time and support to then take on something else like research. So we try to overcome that in a few ways. Obviously, as a software company, we're continuously looking for ways that technology can support these gaps, but we also work with outside partners who can provide the actual resources or boots on the ground and expertise for these community providers to do research.
00;20;14;15 - 00;21;01;03
Another challenge is on the data and technology side, and that is that big data requires significant compute power, know it needs specialized tools, and you need specialized training. So it all can sound easy, but it's not easy. Fortunately, Oracle is the leading provider of cloud infrastructure and services. This continuous pursuit that we have for autonomous databases and low or no code applications, I always struggle with saying that these tools, it really lends itself nicely to the work that we're doing with RWD and I think it's going to allow us to challenge the market with the new generations of these data sets and tools.
00;21;02;00 - 00;21;38;13
And then lastly, I want to touch on on cybersecurity, because that is a constant challenge across healthcare and obviously our entire business is data. So we have to be very aware and cognizant and careful of it and again, I think the unique to Oracle is this ability to leverage other data security experiences that Oracle has. So, you know, Oracle has been protecting the data of the financial and banking sectors for many years, and we're able to leverage that and bring that into Oracle Life Sciences as well.
00;21;38;23 - 00;21;46;21
It's it's a level of security and governance to healthcare data that, you know, is really important to have and it feels good to have it.
00;21;47;08 - 00;22;02;10
Well, none of this happens without tech knowledge is that have come onto the scene. So first, let's talk about how far we've come. What is today's state of electronic health records and data analytics where patient care and health care delivery are concerned?
00;22;03;04 - 00;22;28;24
Yes, this is every doctors favorite subject to the notorious electronic health record in the life that I've that I've led for the last 12 years. You know, my as much as the patient records are still fragmented and EMR is are still considered clunky tools, I do think it's important to recognize the progress that we've made and the effect that it's had for us as a society.
00;22;29;08 - 00;22;54;04
You know, most people's records are digitized today. You know, there are many children that are born across the world that will never have a paper record, will have their entire record available electronically. And that means that their data is available to us and it gives us this ability to understand health care like we've never had before. But of course, our industry is challenged.
00;22;54;15 - 00;23;19;25
We still suffer from a lack of standardization in various areas and that makes data extraction and its use challenging in various ways. The way that I think about it, the simplistic way I think about it, is that old ATM cards, you know, remember how they only function in a specific bank and then years later you could use them within a network as long as you went to that particular symbol in the back of your card.
00;23;20;13 - 00;23;39;19
And then now here we are being able to access our banking information and our money everywhere in the world. And when you are anywhere and you swipe that credit card, the transaction is seamless. I mean, it's seconds there and they're doing a lot with those seconds. You know, they're checking, do you have the right funds? Are you the right person?
00;23;39;20 - 00;24;03;22
Because, you know, could this be fraud and then authorize that? So it's very impressive, their journey. And I'm sure that getting there was not easy nor fast. So similar to that. Our struggles with patient records are similar, but we've made good strides in interoperability. I think that right now we have the right direction and the right tools to get there.
00;24;04;13 - 00;24;33;29
And also, you know, we have the experience from from from these other industries that will accelerate our progress. I think, you know, one of the things that impressed me when we joined Oracle is the number of the number and the variety of industries that this company supports and partners with. And I've seen this constant pursuit of working across the verticals, looking for opportunities to learn and collaborate and understanding that we're better, faster together.
00;24;34;09 - 00;24;57;01
That's really important for us in health care because we do have this reputation of wanting to work alone and being difficult to work with. But, you know, when you look back over time, I don't think that we would be as well positioned as we are today with patient safety, for instance, if we hadn't leveraged, you know, the learnings and the experience of the aeronautics industry.
00;24;57;01 - 00;25;09;19
Right? So flight safety and those concepts were applied to to medical safety, and that's really propelled us ahead. And so I'm looking forward to continue to work across these different industries.
00;25;10;02 - 00;25;34;16
Yeah. You know, when I've asked other guests who are engaged in clinical research and recruiting for clinical research, one of the things they seem least impressed with is how spread out varied, disconnected patient records are. What's the ideal state, and can existing tech get us there, or do we need something more or is it more of a policy and bureaucracy problem?
00;25;34;16 - 00;26;10;03
I think the answer is yes. You know, expanding a little bit more on that fragmentation of of record of patient record health it's still, like I said, struggles with standardization and that's the piping and the backbone that supports good technology. So we're talking about standards for health data elements, meaning having the same names, the same codes, the same ontologies, and also standards for quality in health care data is still not universal, which is, which is a big challenge.
00;26;10;04 - 00;26;46;15
So I have this colleague that works in data quality and runs a company in data quality, and he always says, you know, garbage in means garbage out. So when data is not captured appropriately, it's output is harder to use. Another big challenge is getting to a single longitudinal health record, because we do in this country suffer from a lack of a universal patient ID So interoperability is extremely important, but it's still, you know, having some difficulties getting there to a seamless in a seamless way.
00;26;46;26 - 00;27;07;15
But once again, we have made a lot of progress. You know, I think that we're going to be in the place where, you know, you walk into any facility and you can scan your card or maybe you're going to have a chip on your on your arm there. Mike, I don't know. And those health care workers are going to know who you are and they're going to know how to take care of you.
00;27;07;24 - 00;27;32;22
So I do believe that we are going to get there on the policy side and, well, both research and health delivery are super highly regulated and rightfully so. We want them to be, but they're not always congruent. And there's definitely increased recognition that some of the policies, regulations that we have in place are outdated. We have evolved since then and they need to be reconsidered.
00;27;32;22 - 00;27;59;08
And we're seeing movement across federal sectors, like in I like the NIH and the White House to try to help some of these regulatory burdens. So we absolutely fully believe that your observations are right, and this is a great opportunity for us to help break down those those issues. And to me, that's one of the most exciting ways that we can make an impact.
00;28;00;06 - 00;28;21;18
You know, we've talked to several guests over past episodes about personalized medicine. Obviously, we don't get anywhere near personalized medicine without real world data. What are your thoughts about what the true barriers are to personalized medicine? Can we start looking for it and getting excited about it? Or are we still like a Star Trek distance away from it becoming reality?
00;28;22;09 - 00;28;32;15
Well, I funny that you mention Star Trek because I am a big fan and I still do. I still want to be Dr. McCoy with a tricorder. One of these days.
00;28;32;15 - 00;28;35;11
I think we all have dreams.
00;28;35;11 - 00;29;03;17
I always felt that watching sci fi movies is is a great way to imagine what the future can look like, like Judge Dredd and the Flying cars, you know, other industries already applying intelligence and suggestions. There are way ahead of us and these suggestions are derived everyday from everyday interactions right? You are constantly bombarded by ads that relate to a conversation you had with your spouse near a smart home device or via email or a search that you did.
00;29;04;04 - 00;29;32;26
So all of this is possible. It's very personalized, but health care data needs to be very protected. So I do believe we should be able to get there to more general personalized care, and the data is the foundation for that. There are definitely sectors or treatment areas like oncology, immunology, where these advances are already there in place. And we know more about genomics and other omics and we know how to target treatments for those patients.
00;29;33;07 - 00;29;34;29
So we are we're definitely getting there.
00;29;35;10 - 00;29;46;22
And thinking just about the Learning Health Network What do you see as the biggest opportunities for that organization? What does that look like in five years and what does it need to focus on to get there?
00;29;47;07 - 00;30;08;21
So I'll touch on three very important things for us. And I and I think, you know, that the ranking might be different depending on who you ask on our team, but global expansion is definitely a top priority for us. We want our RWD to power research all over the globe. We want to be a part of that movement and we want to facilitate that movement.
00;30;09;08 - 00;30;33;09
Extension of our data set is going to be very important and also with that extension of our platforms and our partnerships, we feel that there are many possibilities here to augment the current research and discovery processes with different types of data. We know that what makes up an individual and an individual's health, you know, only 20% of that is is health care data.
00;30;33;09 - 00;30;54;13
And what we do in hospitals and in practice, 80% of that is is more related to social determinants of health and our behaviors. So there is other data that we need to bring in as well to help that discovery in that personalized care and then leveraging the rural data to support other important initiatives is very important to us.
00;30;54;13 - 00;31;17;19
So rural data can help us leapfrog the current technical abilities that we have. I truly believe in AI and I know that our customers are dying to have that. So is that, you know, the easiest example I can give you that we need real data, real medical data to train AI and to create large language models that are more suited to health care.
00;31;18;03 - 00;31;24;05
And then, of course, we'll continue on our mission to to bring research into everyday practice.
00;31;24;20 - 00;31;45;24
With technology playing an ever increasing role in health care and how we deliver that health care to society. More of the focus does seem to be on landing on what role companies like Oracle can play. So I suppose my question is just that what's the appropriate role for a company like Oracle? What can it best do to shape the future of health care?
00;31;46;18 - 00;32;22;16
Well, I certainly don't want to simplify it. And, you know, I feel like we can we can do a lot here and and really make a big impact. But I feel in its most simplistic way that companies like ours are pivotal in enablement, in innovation. We have all the tools, advanced health care, we have experience to bring from other sectors and success in my mind is is not just being creative in building things that we think are cool tech, but, you know, really partnering and listening and understanding what clinicians and researchers need in solving for the right problems.
00;32;23;00 - 00;32;26;01
So that's how I see us as the conduit to get there.
00;32;26;17 - 00;32;34;18
Are there any really innovative products you're kind of seeing at Oracle that are especially relevant to the work you're doing and the goals that you're pursuing?
00;32;35;06 - 00;33;15;28
Well, I'm not going to lie. I am super excited about AI and how Oracle is applying AI to remove burden from health care. As a physician that suffered burnout in medical practice, this work is extremely important and it's also happening across life sciences, Oracle life sciences. So this is intelligence not only to decrease the huge amount of duplicative work that exists today, but also to be able to digest the overwhelming amount of data that we have in healthcare and provide more guided, guided decision support to clinicians and researchers and overall to improve safety for our patients.
00;33;16;12 - 00;33;54;15
I think that you had a chat with one of my colleagues who was working on the life sciences safety aspects of our work, and we are leveraging AI there to help read through tons of medical records to pick up those essential elements that are needed for Pharmacovigilance. I also wholeheartedly agree that employers, as often as they are today, should be a thing of the past and that health information needs to live in a different layer, needs to be more flexible, more usable for our patients, for our providers, and certainly for health delivery systems.
00;33;54;24 - 00;34;03;00
So Oracle is currently working on that and that's going to have a tremendous impact. And for our for us on the clinical research side as well.
00;34;03;08 - 00;34;17;15
Well, sounds exciting and we will, as they say, be watching that space very closely. Lu, thanks again for being with us. If someone wants to get in touch with you or learn more about your work or what Learning Health Network does. Is there a way they can do that?
00;34;18;02 - 00;34;44;27
Absolutely. You know, we welcome talking to any provider or organization that has EMR data to contribute. If you can contribute our data or health data in exchange for success, we want to talk to you. And this is regardless of whether you are an Oracle customer or not, today our RWD is EMR agnostic. We have data from at least 18 different health records and it's not exclusive.
00;34;44;29 - 00;34;55;07
So you can join multiple networks, but join ours as well. And you can reach out to us at Learning Health Network underscore at Oracle dot com.
00;34;55;16 - 00;35;27;13
Great Well if you are interested in how Oracle can simplify and accelerate your life sciences research, we invite you to check out Oracle dot com slash life dash sciences. Also be sure to subscribe to the show because there's more great insight and episodes ahead and join us next time on Research in Action.
Research reveals that 95% of patients do not participate in clinical trials. How do we find better ways to connect willing and qualified participants to clinical trials? How do we ensure diversity in participant populations? And how can we make access to clinical trials more patient-friendly? We will get those answers and more in this episode with Brandon Li, Co-Founder at Power. Power is a fast-growing startup building a patient-friendly way to get access to clinical trials and is working to increase the diversity in clinical trials.
--------------------------------------------------------
Episode Transcript:
00;00;00;03 - 00;00;17;02
Are there better ways to connect willing and qualified participants to clinical trials? How do you ensure diversity in participant populations? And why do 97% of patients not participate in clinical trials? We'll get those answers and more on this episode of Research in Action.
00;00;18;07 - 00;00;19;19
The need to.
00;00;21;14 - 00;00;41;18
Build the Hello and welcome to Research and Action, brought to you by Oracle Life Sciences. I'm Mike Stiles, and our guest today is Brandon Lee, co-founder at Power. Power is building a patient friendly way to get access to clinical trials, and they're working on increasing the diversity in clinical trials. Brandon, thanks for taking the time to be with us today.
00;00;41;28 - 00;00;42;27
Yeah, it's my pleasure.
00;00;44;06 - 00;01;03;27
Great. Well, looking forward to it. And we are going to be talking about some amazing stuff as always. But we also always like to get a feel for the person behind that amazing stuff. So what did you want to be when you grew up and how did you get from there to the field of clinical trials and technology and the kind of things you're doing now?
00;01;04;06 - 00;01;13;12
It depends on how far back you want to go, but I think that through most of my childhood, I probably wanted to be a like a professional trading card game player as.
00;01;16;03 - 00;01;17;28
Are you a Pokemon man or.
00;01;18;11 - 00;01;29;24
It was it was all of the above, right? It was like a Pokemon journey. Then there was like a, you know, journey. Then there was a magic. The Gathering journey. I kind of cycled through all of them, but I ended up landing on magic, I think, for most of it.
00;01;30;15 - 00;01;32;25
Well, check those old cards. You could be a millionaire.
00;01;33;01 - 00;01;39;12
I've been. I've been watching the the price of Charizard skyrocket with a lot of energy. You remember having plenty of money?
00;01;39;23 - 00;01;43;08
Well, great. Yeah, but obviously that's not what you wound up doing full on.
00;01;43;23 - 00;02;12;07
No, not at all. Yeah, I think the kind of journey here was. Well, at some point I became a consumer internet. Consumer marketplace person sometime between my my kind of professional trading card game times and and kind of coming out of college, I started thinking a lot more about consumer tech. So I spent a handful of years just doing things that look a lot like classic consumer marketplace work.
00;02;12;07 - 00;02;33;14
Thumbtack, Airbnb, Zillow, all kinds of kinds of products. And at one point I had a close friend of mine diagnosed with a brain tumor who had to go looking for a clinical trial on her own and, you know, that journey was brutal for her. She did everything that patients basically go and do today, which is backchannel the heck out of every doctor that she knows.
00;02;33;14 - 00;02;55;08
And eventually all roads ended up leading to clinicaltrials.gov. So she spent weeks there trying to figure out, okay, is there a trial that could make sense for me? Eventually, she finds one and the contact information is like the front desk of the hospital. So she's cold calling the hospital. The hospital's routing her internally. She's trying to find a way to get an appointment and eventually she gets in front of a study, she gets in.
00;02;55;08 - 00;03;17;26
And that's what they had a positive readout earlier this year, which is probably the happiest journey somebody could have gone through. But it was through that kind of experience that I realized a few things. The first one is that she can't be the only person out there who is sitting in front of clinicaltrials.gov, sitting in this kind of situation trying to answer the question, are there leading medical researchers that can help me?
00;03;18;13 - 00;03;42;10
And the second thing we realized was, while that journey is way too difficult today, right. Everything from even discovering trials in the first place to evaluating your options to figure out what you could be qualified for, what looks really promising through to even contacting the research sites. So we just put put our heads together and realize, well, I think that we can actually bring a lot from this consumer into that space and hopefully, hopefully help a lot more people in need.
00;03;42;22 - 00;03;48;09
So tell me what power was founded to do the problems that it specifically seeks to solve?
00;03;48;29 - 00;04;14;24
It's pretty straightforward, and I like to look at it through a couple of different lenses. So through the lens of the patient, it's exactly this kind of dream that I just described, right? It's helping individuals find and get access to leading medical researchers that could help them from the perspective of the sites. It's how do you connect with as many patients that are potentially interested in your study but not established at your site?
00;04;14;24 - 00;04;31;25
So maybe you don't have a relationship with them yet, but we help you kind of like widen that catchment area as a site and then as a sponsor. It's well, we give superpowers to your sites and we help elevate the kind of the reach of your studies to the patients that are using our platform. And we have hundreds of thousands of them now.
00;04;31;25 - 00;04;37;05
So plenty of folks on, on the website looking, looking around for trials and trial information.
00;04;37;28 - 00;04;55;04
So the people who want to be in clinical trials would find useful connections to those doing the research. And what's the level of the research world? How is it embracing the platform? Is it eagerly seeking to connect with these people who want to do clinical trials?
00;04;55;20 - 00;05;17;25
I think this this kind of touches on an age old problem, right where everybody I'm sure the kind of guest are. The the audience of your podcasts knows these stats, but we didn't coming in certainly turns out that finding patients to participate in trials is one of the biggest problems in life. Science, R&D, right? 86% of trials being delayed because they couldn't find the patients to participate.
00;05;17;25 - 00;05;46;23
So what we found is that we've had north of a thousand like research sites already, like just sign up to start connecting with our patients from the kind of ground ground up. And that's led to a movement that we can then point to some really interesting data and say things like, Wow, actually turns out that the the the research sites that are using power or connecting with patients like ten times more than if they weren't they weren't using patients.
00;05;46;23 - 00;05;49;19
And that data has been really meaningful for us to see.
00;05;49;19 - 00;06;09;20
Well, is it a database of willing participants that the researchers can go look at and find? Because it seems to me most patients, they are totally taking the guidance of their doctor, you know, and so is the doctor playing a role in connecting these people with these research projects?
00;06;09;20 - 00;06;27;25
There's kind of two things here. The first one is, yeah, we've got a registry where patients sign up and they say, Yeah, admitted registry. The registry experience from the the site's perspective is kind of like a LinkedIn for patients, if you can imagine it. It's like, Oh, there's these patient profiles, they've created a profile. I can see them.
00;06;28;04 - 00;06;51;27
They might have answered some prescreening questions at some point. So I'm starting to paint a picture of, you know, medical history and I can invite them to connect if it makes sense. So there's kind of like this LinkedIn for patients. And then on the other side, there's also, you know, new patients signing up every month. And I think that's where a lot of the impact is, because our view is that the patients that are most recently active and interested are the patients that are most likely to actually take action.
00;06;52;24 - 00;06;59;22
So it's all about new flow of patients in our mind, even more so than the the kind of depth of of the database or the registry.
00;07;00;07 - 00;07;11;17
And then what about that Dr. element? Are doctors aware that this tool is available and are they eager or reluctant to get their patients involved in clinical trials?
00;07;12;04 - 00;07;30;23
One of the most interesting things that we've started to see is that doctors are referring their patients to us, right? We're starting to see that in the data where, you know, maybe when we launched, nobody's doing that. And then a year ago, you know, you got a handful of people and that number has actually doubled like year on year of like the number of doctors that are actively referring patients.
00;07;30;23 - 00;07;55;20
And it turns out doctors are okay, referring patients to clinical trial resources. It turns out they do that all day long anyways, but they actually send patients to clinicaltrials.gov. And if you talk to any doctor about it, they they kind of look at you like sheepishly and and almost kind of confess that they do it because they hate it, they hate clinicaltrials.gov, and they know it's not going to help the patients that they're working with.
00;07;55;20 - 00;08;17;26
And it's going to be a really difficult experience. So one of the things we found is that by building a superior product experience for consumers, for individuals on the Internet to learn about clinical trials, doctors are actually more than happy to send patients to to the website to learn about trials. And that's been, you know, one of the kind of happy byproducts of building the kind of best patient experience possible.
00;08;18;12 - 00;08;26;11
So because doctors weren't exactly in love with clinicaltrials.gov, they knew they would be sending their patients kind of down a frustrating rabbit hole.
00;08;26;12 - 00;08;27;05
Correct.
00;08;27;05 - 00;08;53;07
Now, your friend. Well, you're right in saying that, you know, researchers have a hard time finding participants for clinical trials. Your friend on the flip side was eager to participate in a clinical trial. So what makes her different from a lot of patients who are reluctant to participate? Is it because they don't know about the clinical trials or they're too scared to engage in them?
00;08;53;07 - 00;08;54;23
What's what's your view on that?
00;08;55;05 - 00;09;13;29
Yeah, I think it's actually about evaluation. I think evaluation is a key step. If we think about kind of the journey in three phases, there's like discovery, even learning about clinical trials and seeing the trials in the first place. That's difficult. You know, in clinical trials that is rather hard to do properly. Discovery or even your option search.
00;09;14;10 - 00;09;32;29
Then there's the second stage of evaluation. What could be good for me? What am I actually qualified for, and why should I be excited about this relative to status quo? And then there's the kind of participation experience of connecting with the right sites. Right? But I think that, like the second stage of evaluation is really, really the the kind of one of the missing pieces here.
00;09;32;29 - 00;10;00;15
All three are difficult, but evaluations of missing piece, oftentimes when we speak to patients and we speak to patients every week, the key question is, well, how should I be thinking about this trial relative to my current my current care? And is there a reason to believe that this is really exciting or meaningful and I think it's on are kind of like partners in the life science space to properly lay that out for patients.
00;10;00;15 - 00;10;12;10
What is the driving hypothesis that makes you excited enough to put your your capital behind this, this study? And I think patients are looking for that with probably less of a clinical expert explanation of it, though.
00;10;12;21 - 00;10;26;13
Your friend, you mentioned that the outcome was positive, So I'm assuming she got into a clinical trial. She participated. She was not one that got the placebo. She actually got a new drug that helped.
00;10;26;24 - 00;10;27;05
Correct.
00;10;27;16 - 00;10;40;19
Well, let's talk about a lack of diversity and the things that make clinical trials, not that user friendly for everyone. Why is diversity a hard problem to solve and what makes the reward well worth the effort?
00;10;41;01 - 00;11;01;23
You know, we if we look at the stats, it's pretty obvious that clinical trials aren't representative of the population. I think the kind of problem here, let's sit with the problem and talk about kind of like the root cause here. I think the problem here, the problem with it is that it kind of poses a broader public health challenge.
00;11;02;21 - 00;11;25;22
Let's imagine everything goes well and we end up getting new treatments through there. Phase three in front of the FDA approved and we start launching them, but we haven't properly ran these trials with a diverse group of patients. We don't actually know how some how some treatments might affect different different populations and that's why I call it a public health challenge, right?
00;11;25;22 - 00;11;46;14
Because all of a sudden now something becomes standard of care. But we don't know how it affects East Asian, how it affects East Asians and that's and that's the kind of root cause problem. It's it's not a I think, a performative point that diversity, it's really kind of like a downstream potential public health challenge. So that's why it's so important.
00;11;46;14 - 00;12;07;12
And then I think, B, the question of why is it the way it is today is an interesting one. And I think it has to do with the history of clinical research sites that that we choose to partner with. Typically, you know, you partner with a handful of clinical research sites. Those research sites are tasked with recruiting patients from their existing populations.
00;12;08;06 - 00;12;29;05
And then, you know, the kind of set of patients you end up seeing on the set of patients that those sites have established. And it just so happens that the sites that we typically work with in research have a largely white existing patients and that that that ends up skewing the kind of population because you've got a bit of a sampling bias at that point.
00;12;29;25 - 00;12;47;21
Right. So obviously research is not a one size fits all proposition. That's it's amazing that things have been passed that have not been tested on all types of people, all demographics, different patient sets. There's kind of assumption that, well, if it worked with this group, it's going to work with everybody.
00;12;48;05 - 00;13;09;07
Yeah, yeah. I mean, certainly I think the the approach thus far. But you know, I think the the industry is making incredible strides here in raising awareness of this challenge. And then certainly with the recent FDA guidance starting to lean in more to understanding that, oh yeah, there is a potential health care challenge that comes with this that we need to be solving for.
00;13;09;07 - 00;13;12;03
And that's been very inspirational. Watch.
00;13;12;03 - 00;13;32;10
So you did form power to address all this. What does it do in terms of actively recruiting to solve the diverse party problem? In other words, increasing that pool of minority candidates, people that traditionally have not been participating in clinical trials?
00;13;32;24 - 00;13;57;20
You know, we think of ourselves as a a source of unique patients that are interested in trials, Right. So we we help improve access for patients that may not be currently established at the at the research sites. So when we when we think about our role in diversity, what matters to us the most is, is our source of patients more diverse, right, than the other kind of status quo.
00;13;58;03 - 00;14;23;13
And turns out when you look at our data, 40% of the patients who sign up and are actively participating on our platform are nonwhite. And that's right in line with what the US Census and what you would expect in a in a representative sample of of the US population. So I'm we're excited that we're able to hold true to that mission of improving access and that as a result of improving access, actually being a representative source of patients that are interested in research.
00;14;23;29 - 00;14;39;01
Well, you're tackling a tough space because there's so much regulation and the practices are absolutely entrenched. So what's been the rudest surprise you've encountered in your mission so far or the toughest hurdle you had to overcome?
00;14;39;17 - 00;15;11;16
Not not rude surprise, but I think one of the the challenges that, you know, I think everybody can empathize with is that our research sites are incredible busy, busy and often overburdened. So sometimes what is potentially easiest for the patient isn't easiest for the research site. And when you when you think about solving this problem of improving access, if you haven't also solved the problem at the research sites, at the end of the day, you can't close the loop, right?
00;15;11;18 - 00;15;30;03
You can't kind of make the kind of transaction complete, so to speak. Right? So one of the kind of hurdles that we need to we need to overcome and we're constantly kind of like balancing is the line between what is best and easiest for patients and then what is best and easiest for the researchers that they actually need to connect with.
00;15;30;03 - 00;15;39;17
And it has to be, you know, a little bit of give and take and easy for both, Easy enough for both the they that they both can take action because ultimately if if one of them doesn't take action, nothing happens.
00;15;39;27 - 00;16;03;05
Right. So ease of use is definitely a factor. Trust is probably the other factor we kind of touched on this, but we're used to things like control groups and devices to make sure that bias and inaccuracies don't enter the clinical research picture. It seems like if there's underrepresentation and trials, the best results you're going to get are cloudy at best.
00;16;03;16 - 00;16;42;10
Yeah. Yeah. You know, trust is an interesting one, right? One thing that we've experienced with the patients on our platform is that once they've if they if they're coming through our platform, it's because they're almost predisposed to be interested in research. Right. If you think about the kind of factors that have to be true for somebody to be predisposed to be interested in research, one of the factors is that they've they've probably considered it a little bit and are coming in with a higher baseline level of trust, which is not to say that you don't have to continue to build trust.
00;16;42;10 - 00;16;59;15
As a as a researcher, I think everybody has to continue to build trust and it's easy to erode it, especially in a in a clinical setting. But what we're seeing is that the folks are looking around on our website and poking around and reading about different studies there and and then ultimately choosing to connect with it with a researcher.
00;17;00;05 - 00;17;04;02
It's because they've built up a requisite amount of trust already.
00;17;04;21 - 00;17;22;12
Well, let's say I'm someone with an understudied disease and I really want to participate in a clinical trial. How does someone go about that? I mean, obviously going to power and being registered and in the database, but what are the odds that I would get accepted? What factors come into play?
00;17;22;27 - 00;17;51;22
I mean, I think the kind of standard factors come into play at that point, right? So a patient kind of comes through the journey on the website, finds a trial and connects with a with a study, then I think the standard kind of factors come into play around eligibility. How qualified are we and can we prove our qualification as a part of connecting with the research sites in order to get the research site excited to kind of bring you in and kind of work with you?
00;17;51;22 - 00;18;12;12
Right. So some of that is on us as a platform to help help patients maybe put together what we call a dossier or an application packet that helps them get quickly considered and screened for a study. Part of that is the kind of nature of how the protocol is written, and I really think we can influence and that's okay.
00;18;12;12 - 00;18;17;28
And that's kind of par for the course. And just the way that research is structured, not everybody is qualified for every study.
00;18;18;13 - 00;18;30;24
Well, I was looking over the notes and, you know, one figure really jumped out at me. And, you know, correct me if this figure is wrong, 97% of U.S. patients and providers don't participate in trials.
00;18;31;14 - 00;18;55;27
Yeah, it's something like that. I think roughly 3% of of patients as the stat that I've seen, 3 to 5% of patients participate in trials, which is which is amazing when you think about the kind of opportunity to develop improve visibility of research. Research is such an important part of our system and oftentimes should be considered as a part of the the kind of treatment journey like for for an individual.
00;18;56;01 - 00;19;18;04
And I think that's part of actually solving this and increasing that percentage of want to think about that is like the end goal. Part of solving this, I think, is building a relationship with patients through their treatment journey and helping them understand, okay, I'm at this point and I'm on this, you know, potential treatment path and there are some trials that are available on and make sense right now.
00;19;18;13 - 00;19;33;24
But then there are also some trials that could make sense a year from now based on how these kind of treatments progress and based on how I react to them. And I think part of what we want to do as a platform is build that relationship and help be a part of that that journey in that planning for individuals.
00;19;34;17 - 00;20;05;11
Well, 97% is huge. And you said earlier 86% of clinical trials are delayed because they can't recruit enough patients. Is it that people and providers are not participating because trials are so hard to stand up and run? Or, you know, we've talked to other people before, you know, on the podcast and previous interviews and and a big problem is participants in clinical trials kind of don't really know what they're getting into in terms of the level of monitoring that's needed.
00;20;05;11 - 00;20;19;19
And, you know, it becomes very difficult to incorporate the clinical trial into their lifestyles. And are those some of the issues that are just preventing 97% from leaning into research?
00;20;20;12 - 00;20;43;24
You know, I go back to this evaluation question like, are we are we properly are we properly conveying to patients like the reasons to believe if there's a compelling reason to believe that this is a like the best kind of like path forward, I think that that's is kind of like a like put into context of the burden of, of participation.
00;20;43;24 - 00;21;05;28
And I think oftentimes from the patients experience, all they kind of like get exposed to really is the burden of participation without the, you know, the requisite amount of exposure to, you know, why is this the best path forward for me or the best option available right now? I think about it in terms of balancing these two things.
00;21;06;17 - 00;21;38;22
Yeah, there's an increased ask and burden on behalf of the patients and there's also potentially a really compelling reason why this is exciting. And those two things have to be put into a kind of like proverbial pros and cons list that individuals can kind of trade off as they as they think about about research, but not no, I don't think that's the kind of question of burden is excluding 97% of of patients, I think that there are patients that that will be turned off by the burden.
00;21;38;22 - 00;21;41;01
But I don't think it's 97% of people.
00;21;41;20 - 00;22;06;23
And for the general public, you know, getting excited about research, how do you think the amount of time that it takes to do good and qualified research, you know, and get all the way through to FDA approval? It just seems like it takes years and years and years. So it's it's hard to get excited about something that may not yield results for anyone until well into the future.
00;22;07;08 - 00;22;22;27
I think if you put yourself into the shoes of the individual participating, right, it's it's not typically a question of, okay, like what is the impact ten years from now? I think it's a question of, you know, what am I experiencing in the here and now? Does that make sense?
00;22;23;13 - 00;22;39;23
Yeah, absolutely. Is control of the major clinical trials in the hands of too few facilities and researchers, or do you feel it's pretty much properly democratized? You're seeing a lot of clinical research opportunities available.
00;22;40;09 - 00;23;16;16
Yeah, control is an interesting question, right? So certainly clinical trials are concentrated to a group of providers, sites that are familiar and let's say have a track record of doing research. And I think there are like very reasonable rationales for that. I would even argue, you know, probably okay with that, there's a little bit of concentration, right? Because the kind of bigger a trial gets, the more people that are or the more providers that are participating, the more noise and variance kind of gets introduced and gets introduced to the system.
00;23;16;16 - 00;23;38;20
And that's not always a good thing. Our perspective here is that we do need to increase access, but the way to increase access is not necessarily to get to 100% of providers participating in in every study. I think the way to increase access is actually to help individuals and patients learn about studies that are happening in their in their geography, and they get properly connected with those sites.
00;23;38;29 - 00;24;00;02
And to make that that kind of journey easier, rights for patients have more visibility to what's available and then getting connected with the right person in the city. It doesn't really make sense to have, you know, a hundred providers in Cincinnati doing a doing a study right is just about funneling patients to the to the right locations and improving kind of like access and transparency.
00;24;00;02 - 00;24;00;26
Those opportunities.
00;24;01;17 - 00;24;17;01
Well, you do have primarily a technology product. You're connecting people to clinical trials. Technology is going to play a role in that. But it's not like this is tender, right? Me So what what kind of tech and guidelines does power use to make these connections?
00;24;17;01 - 00;24;38;00
We think of the our, you know, our publicly facing platform and that's that's what most people see when they kind of engage with us as like an Airbnb like interface for individuals who are looking for trial. So it's really on the on the patients side, right? It's like a discovery and evaluation product and we do a bunch of things that are interesting there.
00;24;38;05 - 00;24;59;26
But one of the things we do that's interesting is we actually have one of the best structured data sets on eligibility criteria that is out there and then as a result, we can have patients now start to do their search on the basis of, for example, like their genetic biomarkers, and they can do filtering on genetic biomarkers relative or relevant to their their kind of condition that's not available anywhere, anywhere else.
00;24;59;26 - 00;25;31;04
Right. From a patient facing perspective, that's that level of kind of like of detailed search experience actually makes the discovery and evaluation process way easier on from a patient's perspective. Then on the flip side, you know, let's use that as continue the Airbnb analogy research sites get access to. Well, we like to think of as, you know, like a referral management or a recruitment management platform that they can use to see all the patients that are interested in their trial on our website, on our platform.
00;25;32;14 - 00;25;53;09
So it's kind of a workflow management tool that that sites can use to kind of connect those patients that are on our website and expressing interest in their studies. And then somewhere in between we've got a kind of like matching algorithm. So we're I'm sure everybody who's who's kind of come through here and is working on technology is thinking about ways that you can use A.I. rights to improve workflows.
00;25;53;09 - 00;26;25;05
Our view is that A.I. is an interface is not the end game, but as a as a component to kind of like your tech stack is really compelling. So we're looking at ways to use AI to improve match rates, improve kind of screening qualification, and in doing so, reduce some of the burden on the on the patient side for identifying what could be a good trial, but also reducing burden on the site's perspective and having to screen that these patients from from scratch every single time.
00;26;25;27 - 00;26;38;10
So it sounds like the databases, the processing power required for that would be pretty intensive. Is all of that being run smoothly and securely in the cloud? Is that a hybrid approach? Is it on premises? What do you have?
00;26;38;17 - 00;26;46;12
Yeah, it's all in the cloud and it's not a you know, we're not making our own A.I. models, right? So it's it's not nearly as intense as maybe it sounds.
00;26;46;29 - 00;27;03;24
So it sounds like the proposition is just that there are the ability to run filters and eliminate mismatches to get to good results better. And that a superior, I would assume, to what clinicaltrials.gov have offers.
00;27;04;10 - 00;27;23;18
Oh, yeah, certainly right. For if we're going to both sides of the equation, patients can more quickly figure out what trials they should actually be considering. Right. Like if you if your patient search on clinicaltrials.gov, you get thrown 150 different options that you need to track in a spreadsheet and try to whittle down towards five or ten that are a good fit.
00;27;23;18 - 00;27;39;06
So patients can very quickly do that. It takes them a minute on our platform and then on the researchers side, they can double click into the patient's profile, the medical history, all this kind of stuff in order to quickly make an assessment about whether this patient is qualified enough to kind of come in and screen.
00;27;39;29 - 00;28;08;20
So what we've been talking about is bridging the gap and making the connections between patients and clinical research. And Oracle Life Sciences mission is kind of bridge the gap between clinical research and then clinical care. So kind of in the connecting business as well. But if power is successful and we're running diverse clinical trials, what are your thoughts on how those learnings can then be made actionable in the point of care and patient portals area?
00;28;09;08 - 00;28;37;02
I think that, you know, and this is kind of early in and the way that we're thinking about it, but I think that providers have a really important role here and consideration and the consideration process of clinical trials. And one thing that we would love to to see more is for us to have broken down the barriers for providers to understand and what trials are currently running in their specialty and stay on top of the best options.
00;28;37;02 - 00;29;00;12
Right Today, you know, providers in the community have to stay on top of reams of information. It's really quite a difficult journey for them as well to stay on top of the kind of latest research in their in their category. So one thing we would love to see is for those providers to be able to leverage power to, you know, just stay smart on the kind of latest in a medical research.
00;29;00;17 - 00;29;05;14
That way when they do have a patient comes through, they have the information they need at their fingertips as well.
00;29;06;04 - 00;29;26;29
Are doctors reluctant to give patients? I don't want to say false hope because the hope is genuine, but it's almost like they don't want to get their hopes up by saying, hey, this clinical trial is likely to give you a solution where today we don't have a solution for you.
00;29;27;17 - 00;29;50;09
I think providers are are really the experts at navigating that that conversation. And I don't know any providers who I think misrepresent the the opportunities present in clinical trials. But I think really providers are quite thoughtful about how they present research as an option.
00;29;50;09 - 00;30;08;06
Well, we talked about your tech stack. And when you think about your tech stack and you look over all the tools that you have, is there anything on your wish list or is there anything you know, you touched on I a little bit that you see coming in the future that's going to really kick power up a notch?
00;30;08;26 - 00;30;11;27
Yeah. I mean, if somebody could just solve this medical record thing, I'd be nice.
00;30;13;11 - 00;30;29;07
Well, you've brought up an area of mass chaos, but kind of expand on that. You know, what's what's the problem? Is it just like incoherent, inconsistent, not interconnected methods for keeping medical records for Americans and others?
00;30;29;19 - 00;31;07;23
Yeah, all of the above. Right. And, you know, patients might want to get access to their medical records. How do they get those records? You know, the new clinical trial inevitably is going to want the medical records as well. How do how does the trial get access to those medical records, the kind of like general mosaic of different set ups and different communication norms and different like ways to share the records, I think introduces a lot of inconsistency into the space, which makes it difficult for everybody from providers to researchers to patients, and certainly for the life science companies that are pulling their hair out and looking at everything, trying to figure out is there
00;31;07;25 - 00;31;09;09
is there a good way through this mess?
00;31;09;27 - 00;31;12;25
Turns out a little standardization isn't a bad thing.
00;31;13;02 - 00;31;38;28
No, it could be really helpful. I don't know. You know, I think a little bit of the the kind of banking and finance stuff where Clyde has really solved this inter connectivity problem for our intraoperative interoperability problem for financial services institutions to allow fintech at some point. It'd be nice if somebody does that on the medical record side, and there are a lot of really great teams sprinting at this.
00;31;38;28 - 00;31;47;18
So, you know, I'm I'm cheering them on. Waiting for the day when collecting a medical record is as easy as connecting my bank account to a new app.
00;31;48;10 - 00;32;07;28
Well, if you were to assess where we are today in terms of bringing more participation and diversity into clinical trials and where we might be, say, five years from now, can you change mindsets and the culture around clinical trials in that period of time? Where do you see this going in, say, the next five years?
00;32;08;15 - 00;32;36;24
I think it's it's interesting. I think there's a ton of runway ahead of us for impact. Or let's go back to one of the stats that you brought up. 97% do not participate in trials. 3% do getting 1% more of the kind of population to be excited about research. And depending on research, just 1% increases. The overall the overall participate participation rates of the population by 33%.
00;32;36;24 - 00;32;56;25
That's massive, right? So can we go from 3% to 5% in the next five years, almost doubling the kind of participation rate? That's huge impact, a huge impact on on our industry. It's not yet broad population adoption. And I think that's okay. When you're starting from a small base, you kind of have to stack up the the wins and think about them economies relative terms.
00;32;57;14 - 00;33;03;15
Well, we'll look forward to watching the progress in the space and we'll let you know when that medical records thing gets sort of shorter.
00;33;05;01 - 00;33;05;03
So.
00;33;05;04 - 00;33;15;11
You can be on your way. Well, Brandon, thanks again for being with us today. If someone wants to get in touch with you or learn more about what power does, what's the best way to do that?
00;33;15;20 - 00;33;39;28
Yeah, you know, I think that get in touch with me. I probably shouldn't do this, but my email is Brandon up with power dot com. Feel free to send me an email. Always happy to chat and share. Share what we're up to. And then if you want to take a look at our website, it's it's free and public so it's with power dot com pretty easy to go find and take a look at the kind of experience that we're trying to build for for people who are learning about research.
00;33;40;11 - 00;34;12;22
Fantastic. And we appreciate it. If you are interested in how Oracle can simplify and accelerate your life sciences research, we invite you to check out Oracle dot com slash life sciences and also be sure to subscribe to the show because there's more genius ahead and join us next time on Research and Action.
From the publisher's feed