Code & Cure

Vasanth Sarathy & Laura Hagopian

Decoding health in the age of AI Hosted by an AI researcher and a medical doctor, this podcast unpacks how artificial intelligence and emerging technologies are transforming how we understand, measure, and care for our bodies and minds. Each episode unpacks a real-world topic to ask not just what’s new, but what’s true—and what’s at stake as healthcare becomes increasingly data-driven. If you're curious about how health tech really works—and what it means for your body, your choices, and your future—this podcast is for you. We’re here to explore ideas—not to diagnose or treat. This podcast doesn’t provide medical advice.

  1. 8h ago

    #63 - When AI Writes Back To Patient Messages

    AI can draft a patient portal reply in seconds, but the hard part starts when a clinician has to decide whether that draft is safe, accurate, and appropriate for a real human being. We unpack new research on AI-generated portal messages and what providers actually change, from the small administrative tweaks that pile up to the high-stakes clinical edits that demand careful judgment.  We talk through how these systems work in practice: categorizing incoming portal messages, using category-specific prompts, and pulling context from the electronic health record to generate a personalized response. Then we zoom in on the most revealing signal of all: the edits. Scheduling and rescheduling changes show up constantly, often because drafts default to recommending an office visit. Meanwhile, the edits that take the most time are the ones tied to clinical interpretation, like radiology and lab results, diagnosis clarification, referral decisions, and guidance on when to seek urgent care or the emergency department.  From there, we get into the human factors that make or break AI in healthcare: “human in the loop” versus “human on the loop,” automation bias, and why response time doesn’t necessarily measure trust. We also ask what gets lost when AI takes over the writing, including subtle patient signals and the relationship-building that happens when clinicians think through a response themselves. Finally, we pull back to the bigger truth: portal overload is a systemic problem shaped by reimbursement, staffing, access to primary care, and unrealistic time constraints, and technology alone can’t fix that foundation.  If you care about digital health, clinician burnout, AI governance, and the future of patient communication, subscribe, share this with a colleague, and leave a review so more people can find the show. What part of patient messaging should AI never touch? Reference: Physician Edits to AI-Drafted Patient Messages and Their Impact on Clinical Workload Poursoltan et al. NEJM AI (2026) Credits: Theme music: Nowhere Land, Kevin MacLeod (incompetech.com)  Licensed under Creative Commons: By Attribution 4.0  https://creativecommons.org/licenses/by/4.0/

  2. Sep 17

    #62 - What Is Drift? (And Why We Need To Keep A Close Eye)

    Your clinical AI model passed validation. Everyone celebrates. Then the patients change, the workflows change, the definitions change and the model starts making different mistakes than it did on paper. That gap is drift, and it might be the most unglamorous, most important part of AI safety in healthcare. We break drift down in a practical way: covariate drift (the inputs shift), outcome drift (what you’re predicting shifts), and concept drift (the relationship between inputs and outcomes shifts). Along the way, we dig into concrete clinical examples, like a speech-based Alzheimer’s screening tool struggling when real-world accents and dialects don’t match the training set, and a mammography software update that changes images enough to trigger more abnormal flags, more recalls, more anxiety, and real operational strain. We also talk about why COVID is a perfect stress test for outcome drift and why guideline changes can instantly move the goalposts for concept drift. Most importantly, we map this back to what teams can do: build a monitoring plan before deployment, define triggers, decide what “severe” means, and make sure there’s a clear intervention pathway including the ability to pause or shut off a tool when metrics no longer make sense. We connect this to real product realities, updates that backfire, and the kind of lifecycle thinking regulators like the FDA increasingly expect from AI medical devices. Subscribe, share this with your clinical or engineering team, and leave a review. What’s one metric you’d monitor first to catch drift early? References: Drift isn’t a bug, it’s the work: post-deployment surveillance for clinical artificial intelligence Emir A Syailendra BMJ Journal (2026) Identifying and understanding significant change due to drift when assessing AI models in healthcare: a narrative review Rotalinti et al. BMJ Digital Health and AI (2026) Credits: Theme music: Nowhere Land, Kevin MacLeod (incompetech.com)  Licensed under Creative Commons: By Attribution 4.0  https://creativecommons.org/licenses/by/4.0/

  3. Sep 10

    #61 - Congrats, You Added A Human in the Loop. Now What?

    “Put a human in the loop” sounds like common sense. But when we actually look at how medical AI shows up in busy clinical workflows, that slogan can become a liability. We unpack why oversight often turns into a checkbox, how responsibility quietly shifts onto the clinician, and why that does not equal healthcare AI safety. We dig into automation bias with a concrete example from clinical decision support: when recommendations are correct, errors drop, but when recommendations are wrong, people still accept them and errors rise. That dynamic shows up everywhere from e-prescribing to EKG interpretation, especially when the user experience is built to be fast and frictionless. We also talk about a subtler risk that can be even harder to catch: omissions. An ambient AI note can read beautifully while missing essential red flag questions, and noticing what is absent demands time and cognitive energy clinicians often do not have. From there, we lay out a practical framework for meaningful oversight that goes beyond one person “glancing” at outputs. We cover epistemic capacity (knowing what the model can and cannot do), cognitive space (designing workflows that support real review), decisional authority (protecting clinicians when they disagree with AI), and intervention effectiveness (being able to pause, deactivate, and regression test tools when models change). If you care about clinical governance, explainable AI, and safer deployment of medical AI in the real world, this gives you a clearer blueprint than slogans ever will. Reference: Meaningful oversight of medical AI beyond human in the loop van de Sande et al. Nature (2026) Credits: Theme music: Nowhere Land, Kevin MacLeod (incompetech.com)  Licensed under Creative Commons: By Attribution 4.0  https://creativecommons.org/licenses/by/4.0/

  4. Sep 3

    #60 - We Can Teach Medical AI To Look Like Experts

    If you’ve ever wondered why an AI model can sound confident while still being wrong, radiology is the perfect lens. We’re looking at a new approach to medical imaging AI that tries to close the gap between raw pattern matching and real clinical thinking: training models using radiologists’ eye gaze while they interpret chest X-rays. We talk through how clinicians read a chest X-ray systematically, why that “checklist” behavior matters, and how it changes depending on the question being asked (shortness of breath, line placement, suspected pneumonia). Then we connect that to explainable AI: if we can record where experts look, the order they scan, and where they pause, we can fine-tune a vision transformer or vision language model to produce reports in a way that’s easier to audit and trust. Along the way, we revisit the notorious “cat diagnosed as COVID” story to show how out-of-distribution failures happen when a model learns correlations without domain grounding. We also keep it real about limitations. A gaze-informed model may be better, but it’s still a neural network, and it still might not be “reasoning” the way a human does. Laura brings the clinical workflow reality check: comparing to prior films, using two-view chest X-rays, and integrating symptoms, exam, and anatomy in a way that a single image cannot fully capture. Reference: Seeing through experts' eyes: a foundational vision-language model trained on radiologists' gaze and reasoning Lee et al. Nature NPJ Artificial Intelligence (2026) Credits: Theme music: Nowhere Land, Kevin MacLeod (incompetech.com)  Licensed under Creative Commons: By Attribution 4.0  https://creativecommons.org/licenses/by/4.0/

  5. Aug 27

    #59 - When a Humanoid Robot Removes A Gallbladder

    What happens when the “robot surgeon” stops being a fixed set of arms and starts walking into the operating room like a person? We explore a fresh research result where a teleoperated humanoid robot performs laparoscopic gallbladder surgery in pigs, and we get specific about what worked, what didn’t, and why the details matter more than the headlines. We start by defining what “humanoid” actually buys you in surgical robotics. The promise is less about a face and more about human-like dexterity and mobility: a robot that can reposition itself, approach from different angles, and potentially use standard human tools in a normal OR without the heavy, purpose-built infrastructure that platforms like the Da Vinci system require. That leads to a crucial reality check: this is not autonomous AI doing surgery. A human surgeon is still on the controls, and a bedside assistant is still in the room handling the constant small needs of a real case. From there, we dive into the most revealing technical constraint in laparoscopic surgery: the remote center of motion, the fixed pivot point at the skin that instruments must rotate around to avoid tearing tissue. Classic systems enforce it with hardware; a humanoid has to enforce it in software. We talk through what their evaluation shows, including straight-line versus circular motion accuracy, speed tradeoffs, and why a measured 156 ms latency can be a big deal for operator feel and safety. Finally, we unpack the pig surgeries and the unglamorous blockers that decide whether this scales: range-of-motion limits that force repositioning pauses, recalibration, overheating, and the sterilization problem when autoclaving can destroy sensitive electronics.  References: In vivo feasibility study of humanoid robots in surgery Liang et al. Nature (2026) Credits: Theme music: Nowhere Land, Kevin MacLeod (incompetech.com)  Licensed under Creative Commons: By Attribution 4.0  https://creativecommons.org/licenses/by/4.0/

  6. Aug 20

    #58 - Can AI find sperm that the human eye misses?

    A pregnancy from two viable sperm recovered by AI sounds impossible until you walk through the workflow step by step. We start with the reality that male factor infertility can drive a huge share of infertility cases, and we talk about why “no sperm found” is not just a lab result but a years-long clinical and emotional grind. When the only path forward involves invasive sampling and hours of microscope time, even the best teams are fighting biology, fatigue, and the limits of manual search. Then we unpack the STAR system, a sperm tracking and recovery approach that pairs computer vision with physical automation. We explain how modern object detection, including YOLO-style models, can scan microscopy imagery at massive scale, spotting sperm amid blood cells and tissue where a human could easily miss them. But the real leap is that it does not stop at detection. Microfluidic chips with hair-thin channels, gating mechanisms, and robotic handling help isolate and recover sperm quickly so they can be used in IVF workflows like intracytoplasmic sperm injection (ICSI). Finally, we dig into the part that makes this feel real: the numbers and the clinical outcome. Millions of images scanned, a few sperm recovered, embryos created, and a positive pregnancy after a 19-year infertility history. We also wrestle with a key AI in medicine question: when a task is close to “sperm or no sperm” and the system is both fast and highly accurate, how much should we demand interpretability versus validation and results? References: First clinical pregnancy following AI-based microfluidic sperm detection and recovery in non-obstructive azoospermia Suryawanshi et al. The Lancet (2025) STAR (Sperm Tracking and Recovery) System Credits: Theme music: Nowhere Land, Kevin MacLeod (incompetech.com)  Licensed under Creative Commons: By Attribution 4.0  https://creativecommons.org/licenses/by/4.0/

  7. Aug 13

    #57 - If We Can Invent New Viruses Should We

    AI can now “autocomplete” DNA, and researchers are using that ability to design real, working viruses in the lab. We dig into a Science paper that trains genome language models to generate brand-new bacteriophage genomes, then validates them by building the phages and testing whether they actually infect E. coli. If you’ve been curious about AI in genomics, synthetic biology, or what comes after today’s large language models, this is a concrete example of design, not just prediction.  We walk through the key ideas without assuming you’re a biologist: what a bacteriophage is, why  ΦX174 is a useful starting point, and how models like Evo 1 and Evo 2 learn the “grammar” of genomes from massive pretraining. Then we get specific about the engineering: supervised fine-tuning to a narrow phage family, prompting with a short nucleotide prefix, and the practical filters that keep generated sequences from turning into biological nonsense. We also talk about host targeting, novelty constraints, and why diversity matters when you’re trying to outmaneuver bacterial defenses.  The clinical angle is impossible to ignore. Antibiotic resistance keeps rising, and phage therapy could become a more precise way to kill dangerous bacteria, especially when standard drugs fail. But we end where everyone’s mind goes sooner or later: if we can generate novel viruses quickly, what prevents misuse, accidents, or designs we don’t fully understand yet? Subscribe for more clear-eyed conversations about AI and medicine, and if this raised your blood pressure or your hope, share the episode and leave a review with your take on where the guardrails should be. References: Generative design of bacteriophages with genome language models King et al. Science (2026) Credits: Theme music: Nowhere Land, Kevin MacLeod (incompetech.com)  Licensed under Creative Commons: By Attribution 4.0  https://creativecommons.org/licenses/by/4.0/

  8. Aug 6

    #56 - How Deep Learning Finds Hidden Clues In A Standard EKG

    Sudden cardiac death is the nightmare scenario: someone feels fine, then a lethal arrhythmia hits without warning. The problem is not a lack of tests, it is that our best screening tools still miss too many people. We talk through how clinicians use left ventricular ejection fraction to estimate risk and decide who might need an implantable cardioverter defibrillator, then confront the uncomfortable truth that EF creates false positives and false negatives when the underlying causes are more diverse than one number can capture. From there, we shift to the ECG as an underused goldmine. We break down how modern deep learning models for ECG interpretation can learn subtle waveform patterns across large datasets, including registries that link ECGs to death certificates to identify sudden cardiac death outcomes. Because the event is rare, we discuss a multitask, multi-head approach that learns related targets at the same time to make the most of available labels, then tests whether the signal generalizes beyond the original training population. The most exciting moment is where AI stops being an automation tool and becomes a discovery instrument. We unpack “generative morphing,” where a variational autoencoder generates realistic heartbeats and a predictor nudges them step by step toward higher risk, creating a movie that shows exactly what changes. That approach recovers known ECG risk features and proposes a new biomarker: a slurred terminal downstroke of the QRS complex in lead aVL, with a hypothesis that it reflects disorganized conduction that could set the stage for sudden arrhythmia even when EF is normal. References: An ECG biomarker for sudden cardiac death discovered with deep learning Obermeyer et al. Nature (2026) Credits: Theme music: Nowhere Land, Kevin MacLeod (incompetech.com)  Licensed under Creative Commons: By Attribution 4.0  https://creativecommons.org/licenses/by/4.0/

See All (63)

5
out of 5
6 Ratings

About

Decoding health in the age of AI Hosted by an AI researcher and a medical doctor, this podcast unpacks how artificial intelligence and emerging technologies are transforming how we understand, measure, and care for our bodies and minds. Each episode unpacks a real-world topic to ask not just what’s new, but what’s true—and what’s at stake as healthcare becomes increasingly data-driven. If you're curious about how health tech really works—and what it means for your body, your choices, and your future—this podcast is for you. We’re here to explore ideas—not to diagnose or treat. This podcast doesn’t provide medical advice.

Information

  • Creator
    Vasanth Sarathy & Laura Hagopian
  • Years Active
    2025 - 2026
  • Episodes
    63
  • Rating
    Clean
  • Copyright
    © 2026 Code & Cure
  • Show Website
    Code & Cure