Coda Change

Ever wondered what life holds after discharge from ICU for the families and partners of patients with a severe brain injury? This interview-style session will focus on the challenges, unexpected good and bad outcomes, positive and negative impacts on relationships, and other issues experienced by patients' loved ones post-ICU. Hearing first-hand from a patient's primary carer will highlight that ICU is only an extremely small component of a patient's long journey to recovery and remind those involved in neurocritical care that whilst short-term physical outcomes dominate in a patient's acute ICU stay, it is the long-term functional and social outcomes that ultimately matter most to patients and their families. It is easy to be distracted by the physical problems, but we must not forget the potential impacts of a severe brain injury on higher cognitive functioning when discussing long-term prognoses with families.

Applying research in the Neuro ICU; Marketing and Branding; follow up after critical illness.

For more head to: codachange.org/podcasts

Cooling the severely brain injured patient in the intensive care unit is far from straight forward. Who should be cooled and when? What do you call a fever, and is this the same as the bedside nurse? When should we start, and when should we not? What would make you stop? This talk will explore the cooling journey of a critically unwell brain injured patient in a neuroscience intensive care unit. It will expose all the potential challenges, questions and pitfalls of cooling at the bedside, and suggest some ways to overcome these.

For more head to: codachange.org/podcasts

Health care providers who phantom or "quick look" ultrasound examine are causing the viral spread of an epidemic, which we can minimize by responsibly utilizing ultrasound inpatient care and by implementing the coaching that artificial intelligence provides.

Current trends in point-of-care ultrasound and how the health care provider community can respond are described:

1. Phantom or‚ Quick look‚ scanning.

2. Faculty credentialing and learning ultrasound.

3. Artificial intelligence technology in ultrasound machinery image acquisition and interpretation.

I discuss the phantom or‚ quick look‚ scan and how correcting this behaviour can only come from yourself. Second I describe my experience with faculty credentialing: being told to learn ultrasound on your own or even being given a faculty credentialing ultrasound education plan generally does not work. I describe the passive and active ways to acquire training. You should not rely upon herd immunity.

Finally, I discuss how errors in human judgement will occur. Ultrasound machinery with artificial intelligence components is increasingly available for image acquisition and pattern recognition so human errors are increasingly minimized.

For more head to: codachange.org/podcasts

The role of ultrasound in paediatric lumbar puncture.

For more head to: codachange.org/podcasts

Action Stage: Stage One - Identify Technology in medicine is advancing at pace, providing unparalleled opportunities to process information and to improve both outcomes and safety for healthcare. But with this good comes many challenges and even dangers. How can we better share information and distribute the opportunities equitably? What are the safety mechanisms and who is providing the oversight?

This episode of CodaZero is the first under the Educate pillar. It is the perfect opportunity to start examining the benefits and risks posed by rapidly changing technology within healthcare. The Educate pillar remains at the 'identify' stage of our staged action-plan development process. At this stage the conversations are just beginning and are designed to highlight possible area for further action. Join us for this fascinating first session, divided into four concise but richly revealing conversations.

Conversation one examines the role of Artificial Intelligence in healthcare. What are the opportunities as we push the boundaries and where are the challenges? Are there inherent biases in the algorithms and could these cause harm? Will healthcare workers be replaced by AI or will it be that healthcare workers using AI will replace those that don't?

In conversation two the tables are turned, and we move from discussing speed as the main goal to focussing in on Indigenous methods of learning. Perhaps slowing down is the answer? What might an Indigenous AI algorithm look like?

Conversation three examines what have we learnt from the pandemic and what learning processes can be evolved.

Finally, conversation four highlights the demise of public interest journalism as a result of media power being concentrated in the hands of a few tech giants. The echo-chamber of our own media feeds is a dangerous proposition. Perhaps the solutions to these early discussions lie in greater connections and breaking free of the echo-chamber by challenging ourselves to listen more to others with differing experiences and opinions.

For more head to: codachange.org/podcasts

Public interest media is vital. However, there is a crisis in public interest journalism and it is not new, but some believe the pandemic may be an extinction event for this discipline. Global media power and wealth have become concentrated into a handful of tech giants. This concentration of power and its' inherent biases not only poses a threat to public interest journalism but also to global health through medical misinformation. This dystopian concept is rapidly becoming reality and perhaps the only way to overcome this is through connection…. Connecting with those that think differently and challenge our beliefs. If we stay in the echo chamber of our polarised media we will not overcome this problem and it will become the end-game. We must get out of the echo chambers of our polarised media. We must get over our affronts and offences in order to listen. We must lean into these voices and realise that we all have something to learn.

For more head to: codachange.org/podcasts

We can have all the evidence in the world in healthcare but at the heart of everything we do and every decision we make there is 'us'.

The Pandemic has seen an incredibly accelerated understanding of Covid19, a virus none of us had heard of before January 2020, but it has seen a change in how Evidenced Based Medicine (EBM) is processed and presented. The 'E' continues to represent 'Evidence' but the 'B' has become 'Belief' and the 'M' is now 'Media'.

Under the pressure of the pandemic we in healthcare have believed there is a need to act on levels of evidence that pre-Covid we would have thought irrational.

So we must adapt our traditional model of EBM to the pace of now and make it faster and more adaptive to become "EBA" or Evidenced Based Agility. We need to have the ability to rapidly filter out the good quality evidence and find ways to translate that into practice. However we must also be agile enough so that if the next month we find the evidence has changed we can admit we were wrong and move on – This has not been a feature of EBM in the past where there has been a lot of inertia.

For more head to: codachange.org/podcasts

We often associate Indigenous cultures with a deep understanding of nature rather than computing or AI. However, deep learning, connected learning and relationships are integral to both AI and indigenous learning. Perhaps indigenous people are the future of AI.

It is essential that we bring groups together to design AI. Indigenous cultures walk in multiple worlds and cross many generations. These perspectives are different but often not represented in universities curriculums. Indigenous learning sees health as holistic. Which human doesn't need to include spiritual, mental, physical, social and emotional dimensions to their healthcare?

It is essential as healthcare providers that we give ourselves a 'software update' and continue a process of life-long learning, particularly about cultural competence. The indigenous practice of coming together in 'collectives' and looking at big data sets yields different outcomes than say a 'western' trained epidemiologist might conclude. Indigenous knowledges work by accumulating over time with continuous quality improvement and reflection.

For more head to: codachange.org/podcasts

Over the last 5 years there has actually been a confluence of a few different historical threats. We've had health data being increasingly digitalised and we've had the proliferation of accessible massive scale computing, both of which have un-locked a technique developed in the early 80's called deep learning, which is really good at pattern recognition over large data sets.

Key trends in the last year include the first randomised clinical trials in the clinical application of AI in health, the potential for AI in clinical discovery particularly using multimodal data (including electronic medical records, imaging data, genomic data) and combining that to find patterns in very large data sets. This is the real beginning of precision medicine.

Finally there are day to day clinical process applications being used to predict resource allocation or disease outbreaks. At the same time there are some systemic challenges facing AI in health, including workflow integration, bias, equity and just access.

How can we mitigate these biases and make them fair. Finally how do we make this sensitive data safe?

Is the answer Federated machine learning where we send the AI algorithms out to local networks and apply them there?

For more head to: codachange.org/podcasts