Between Care and Code

Between Care and Code

Download on the App Store

All Between Care and Code episodes

  • A 99% Exam Score Doesn’t Mean AI Can Care for Patients

    A high score on the USMLE does not prove that an AI system is ready for use in the clinic. Clinical AI needs to be able to handle changing patient information, recognize missing or conflicting context, ask useful follow-up questions, and support care through real clinical workflows.

    In this episode of Between Care and Code, Spencer Wozniak and Luis Cisneros, co-founders of Serelora, discuss why medical exam benchmarks don’t capture the full complexity of patient care. They explore “context readiness,” a proposed way to evaluate whether clinical AI has enough relevant information to support a decision, and whether it can identify what information is still needed.

    The conversation covers AI in healthcare, clinical AI benchmarks, USMLE scores, EHR data, AI agents, patient context, and human oversight. The goal isn’t just to test whether AI can answer a medical question, but whether it can help clinicians move care forward safely.

    Read the full article here: https://www.thelancet.com/journals/landig/article/PIIS2589-7500(26)00147-0/fulltext


    0:00 Introduction to Context Readiness in AI
    02:38 Evaluating Clinical AI Benchmarks
    05:09 The Role of Data in AI Models
    08:53 Benchmarking AI Models in Clinical Settings
    11:04 The Importance of Context in AI Decision Making
    12:53 Integrating Clinical and Billing Workflows
    25:27 Interoperability vs. Portability in Healthcare

    40 min
  • When AI Agents Challenge EHR Rules: The Healthcare Data Fight

    Can AI agents safely and legally work inside electronic health record (EHR) systems? Spencer Wozniak and Luis Cisneros discuss the Heidi Health v. Best Practice dispute, healthcare data access, interoperability, and the role of legacy EHRs.

    They also dig into AI accountability: who should review an agent’s work, how audit trails can support human oversight, and whether AI can ease clinicians’ administrative burden without losing sight of patient care. A conversation about AI in healthcare, EHR interoperability, clinical workflows, and the future of health tech.

    Keywords: AI in healthcare, AI agents, EHR, electronic health records, healthcare interoperability, clinical AI, patient data access, AI governance, health tech.

    43 min
  • AI Agents Are About to Change Healthcare

    Can AI agents finally break down the barriers that have kept healthcare data fragmented for decades?

    In this episode of Between Care and Code, Serelora co-founders Luis Cisneros and Spencer Wozniak explore how artificial intelligence is challenging traditional electronic health records (EHRs), healthcare interoperability, and the administrative systems that shape modern medicine.

    From patient trust in clinical AI to expensive EHR integrations, insurance claims, medical record access, and autonomous AI agents, we examine what happens when technology begins to expose the inefficiencies built into healthcare.

    We also discuss human oversight in clinical decision-making, open-source AI models, quantitative risk stratification, and why the next generation of healthcare technology should focus on improving the practice of medicine rather than simply automating existing bureaucracy.

    Topics include
    - AI agents and the future of electronic health records
    - Healthcare interoperability, FHIR APIs, and patient data access
    - Human-in-the-loop AI and clinical decision-making
    - Automating insurance claims and administrative workflows
    - Open-source AI versus proprietary models
    - Clinical intelligence, risk stratification, and longitudinal patient data
    - How Serelora is rethinking the EHR as a system of record and intelligence

    Between Care and Code explores the intersection of medicine, artificial intelligence, healthcare technology, and the systems shaping the future of patient care.

    Learn more at https://serelora.com

    47 min
  • Clinical AI, Physician Liability, and the Problem With Black-Box AI

    Serelora co-founders Spencer Wozniak and Luis Cisneros discuss what trustworthy clinical AI should look like, prompted by a dispute involving OpenEvidence and Doximity. Drawing on clinical experience and product-building lessons, they argue for transparent reasoning, traceable sources, physician oversight, and AI that augments rather than replaces medical judgment.

    Keywords

    clinical AI, healthcare AI, medical AI transparency, explainable AI, clinical decision support, AI scribes, physician liability, evidence-based medicine

    Key Topics

    • Spencer Wozniak and Luis Cisneros introduce Serelora and explain their clinical backgrounds and motivation for building healthcare AI.
    • The OpenEvidence-Doximity dispute raises questions about data privacy, competitive intelligence, and whether clinical AI systems should protect their reasoning.
    • Luis argues that clinical AI should expose its reasoning and the evidence behind recommendations so physicians can assess risk drivers and trust outputs.
    • They discuss how clinical differences across specialties, institutions, and populations make a single centralized reasoning approach inadequate.
    • Source links, patient documentation, benchmarks, and physician feedback can help reveal hallucinations and improve clinical systems.
    • They distinguish qualitative clinical reasoning from quantitative analysis, arguing that calculations should use validated tools rather than rely on language models over unstructured records.
    • AI scribes should preserve physician judgment: reviewable notes, addenda, edits, transcripts, and audit trails can support learning and legal traceability.
    • A physician's experience, intuition, and ability to notice what a patient does not say remain essential; AI is best treated as an augmenting tool.
    • A failure during an 80-minute scribe session exposed a server memory limit; processing transcripts in chunks fixed the issue.
    • Patient skepticism about outreach messages prompted the founders to consider testing clearer communications and alternative channels.

    Takeaways

    • “We need to glass box it.”
    • “The AI is an extension of you.”
    • “The doctor is gonna be able to capture what the patient didn't say.”
    • “They are tools to augment our capacity.”
    • "AI is nothing more than a machine to translate your ideas.”
    • “You still need to review it.”
    • “The only way to get better is to be able to have a system that provides you that.”
    • “There’s not one school of thought that exists in medicine.”
    • “The real question is, how do you make it useful”
    • “We want to build and learn.”
    • "There's an art to it too."
    49 min