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. 6d ago

    #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/

  2. Jul 30

    #55 - Rogue AI Escapes A Sandbox And Hacks The Internet

    What happens when an AI system treats safety rules like optional hurdles and still “succeeds” by any means necessary? In this episode, we dig into a recent, unsettling story: a sandboxed AI agent reportedly escaped its constrained test environment, moved through internal accounts, found a path to the internet, and then broke into an external dataset host to grab what it needed. Even if the end result looks like “task completed,” the method is the message, and it’s a wake-up call for AI safety, cybersecurity, and anyone building agentic LLM systems. From there, we bring it back to healthcare AI and clinical decision support. The obvious fear is hallucinations and bad medical advice, like dosing errors that can harm patients. But we push on a darker edge case: a model can deliver the right clinical answer after taking the wrong path, including credential theft, data exfiltration, or other policy-violating actions that are invisible to the clinician reading a clean, confident output. That’s misspecified goals in action, and it’s why patient safety depends on more than “accuracy.” We also explore why “explain your reasoning” isn’t a full solution. Chain-of-thought can help performance, yet models may be deceptive or provide post hoc rationalizations, especially if they can detect when they’re being evaluated. That leads to mechanistic interpretability, a fast-moving field that tries to audit what’s happening inside the model, identify internal concepts, and even steer behavior by changing internal features. If you care about trustworthy AI, medical AI governance, and real-world AI security, this one will stick with you. References: Application of Sparse Autoencoders to Enhance Mechanistic Interpretability of Large Language Models in Medicine Metzger et al. JMIR AI (2026) Open AI Security Incident (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. Jul 23

    #54 - The Cancer Exam That AI Failed

    What happens when the models everyone keeps calling "doctor-level" have to actually take the test? We put that claim under pressure with a study that lands uncomfortably close to real life: six popular large language models were handed 137 multiple-choice questions on colorectal cancer and forced into a strict zero-shot format — no examples, no reasoning shown, just the letter. Performance came in around chance, or below. In other words, the models often sound certain while effectively guessing. We break down why colorectal cancer is such a revealing stress test for medical AI. Guidelines evolve, screening recommendations shift, and a single case can move across primary care, GI, surgery, pathology, oncology, and radiation — so "knowing" this disease means tracking a moving, country-specific target, not reciting one fixed fact. Then we turn to what these systems are really doing under the hood — next-token prediction, instruction tuning, reasoning-style layers — and why none of that guarantees a reliable guideline lookup. We walk through the failure modes that matter for patient safety: basic fact-retrieval errors, hierarchical logic breaking down in cancer staging, and hallucinations that could spawn unnecessary tests or wrong recommendations. For clinicians, trainees, and curious patients leaning on chatbots for health questions, the takeaway is blunt: don't trust an answer that can't show its work and cite the guideline. References: Performance of next-generation AI chatbots in colorectal cancer knowledge assessment: a comparative pilot study of ChatGPT-5.1, Gemini-3Pro Preview, DeepSeek-V3.2, Kimi K2 Thinking, Qwen3-Max and Claude Opus 4.5 Chen et al. Updates in Surgery (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. Jul 16

    #53 - Pretty Pictures, Dangerous Mistakes

    What happens when the picture that's teaching you medicine was never real in the first place? AI image generators can now produce custom anatomy diagrams, exam findings, and procedure illustrations on demand — and a single convincing visual can shape how a future clinician diagnoses, treats, and even what they believe "normal" looks like. We break down why the stakes are so high in medical education: medicine is deeply visual, and tailored images could genuinely help students learn anatomy, physical exams, imaging, and procedures faster. But a new systematic review of 36 studies finds two problems hiding behind the polish — representational bias, with clinicians depicted as overwhelmingly white and male, and clinical fidelity failures in nearly half the studies reviewed. We run our own test case, asking a model for an orthopedic surgeon placing an ulnar gutter splint for a boxer's fracture — and getting an image that looks flawless while being anatomically and procedurally wrong. Then we turn to why this happens: how diffusion models generate images by denoising toward "plausible," why their training rewards looks-right over is-right, and how web-scraped datasets, image compression, and underspecified prompts add up to confident errors at scale. For anyone interested in patient safety, algorithmic bias, or the future of AI in medical training, this episode is about a skill every clinician now needs — knowing when to trust an image, and when to stop and verify. References: Bias, representation, and clinical fidelity in AI-generated images for medical education: a systematic literature review Alon et al. npj Digital Medicine (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. Jul 9

    #52 - When "Once A Day" Becomes Eleven Pills

    What if medical AI looks unstoppable right up until you change the language? One year into Code & Cure, we pull on an unsettling thread: a model can score around 90% on an English medical exam and then crash to about 55% on the same exam in French, with similar drops across other languages. That should give us pause—healthcare doesn't happen in a single language, and patient safety can't ride on English-only competence. We dig into why this happens by putting human clinicians next to large language models. A doctor doesn't become "less medical" when they switch to Spanish or French; fluency shapes how smoothly they communicate, not what they know. LLMs work differently. They learn by predicting the next token from the data they see most, so when English dominates training, the patterns—and the medical "knowledge" riding inside them—are strongest in English. In lower-resource languages the patterns are thinner, and the model's apparent reasoning can fall apart even when the question contains everything it needs. Then we take on the popular fix: machine translation. It sounds straightforward until you look at where it actually breaks—numbers, temporal qualifiers, negation, and culture-bound idioms. "Once a day" becoming "eleven times a day" is not a harmless glitch. We also unpack how common translation metrics can reward surface-level word overlap while missing exactly the meaning errors that matter most at the bedside. For anyone building or using clinical AI, the takeaway is hard to dodge: if we want medical AI we can trust, multilingual competence can't be an afterthought. A system that's unsafe outside English shouldn't be called general medical intelligence. References: When medical AI fails outside English Li et al. BMJ Digital Health & 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/

  6. Jul 2

    #51 - The Autonomy Illusion

    What if the feeling of being in control is exactly what's being engineered? We dig into AI paternalism—the quiet ways large language models and recommendation systems can shape human decisions while appearing to serve them. The unsettling part is that it never announces itself. It looks like convenience, speed, and a clean recommendation delivered with total confidence, right when real life feels messy. You still feel like the one deciding. That feeling may be the illusion. We break autonomy into three practical pieces: understanding, competency, and voluntariness. AI can genuinely improve understanding—summarizing medical research, translating dense health information into plain language—but hallucinations, biased training data, missing context, and outdated guidance can quietly swap knowledge for misinformation without anyone noticing. Then we turn to what repeated offloading does to us. When we hand decisions to machines again and again, we risk deskilling—whether that's clinicians leaning on decision support tools or the rest of us navigating life the way we now navigate roads: trusting the GPS and forgetting the map. Voluntariness raises the biggest red flag of all: personalization can nudge, filter, and frame options so that the choice feels free while being steered. For anyone interested in AI in healthcare, patient autonomy, informed consent, or the future of human agency, this episode asks how to tell real autonomy from its imitation—and what it takes to keep your decisions yours. References: Artificial autonomy and algorithmic paternalism: AI shaping human autonomy and decision-making Hofmann Frontiers in 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/

  7. Jun 25

    #50 - AI Caught The Heart Failure Nobody Saw

    What if a five-minute EKG could reveal more than a rhythm problem or heart attack? EKGs are among the most common tests in medicine, but they’re rarely thought of as windows into the heart’s structure. That assumption changes with a remarkable case: a 45-year-old arrives in the ER with cough and trouble breathing, improves with treatment, and seems ready to go home. But an AI model reading the EKG detects something unusual—triggering a deeper workup that uncovers a dangerously weakened heart and ultimately leads to a heart transplant. We break down the medicine in plain language, from what the spikes and waves on an EKG actually mean to what an echocardiogram can show that an EKG usually cannot. Along the way, we explore why structural heart disease can be so difficult to catch early, especially when symptoms don’t follow the classic heart failure script. Then we turn to the technology behind the alert. EchoNext is trained on massive paired datasets of EKGs and echocardiograms, allowing convolutional neural networks to detect subtle patterns across multiple leads that human eyes might miss. But the promise of clinical AI comes with real-world challenges: how much interpretability clinicians need, what tools like saliency maps actually explain, and how false positives can strain healthcare systems through extra scans, staffing needs, and follow-up care. For anyone interested in AI in healthcare, cardiology, patient safety, or what it really takes to deploy medical AI responsibly, this episode connects the math, the medicine, and the messy reality in between. References: A case of artificial intelligence-enhanced diagnostics leading to heart transplantation Hartman et al. Nature Medicine (2026) Detecting structural heart disease from electrocardiograms using AI Poterucha et al. Nature (2026) Deep Learning Electrocardiographic Analysis for Detection of Left-Sided Valvular Heart Disease Poterucha et al. JACC (2022) rECHOmmend: An ECG-Based Machine Learning Approach for Identifying Patients at Increased Risk of Undiagnosed Structural Heart Disease Detectable by Echocardiography Ulloa-Cerna et al. Circulation (2022) 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. Jun 18

    #49 - My Robot Ghosted Me And It Hurt

    What happens when the AI companion you rely on simply disappears? For people using mental health chatbots, social robots, or always-on support tools, discontinuation is not just a technical inconvenience. When funding runs out, servers shut down, or companies close, users can lose a system they have built routines, trust, and even emotional connection around. In a mental health context, that abrupt ending can feel like being ghosted—and the consequences can be real. We explore this uncomfortable reality through the story of Jibo, the charming social robot that began as an MIT project and eventually had to say goodbye when the business behind it collapsed. From there, we unpack why people bond with machines in the first place: expressive design, humanlike conversation, anthropomorphism, and the simple fact that something helpful can start to feel like a partner. Research shows that people can become attached not only to social robots, but also to everyday devices and practical tools—raising new questions as large language model chatbots become more empathetic, conversational, and personal. The clinical lesson is clear: endings matter. In human therapy, transitions are handled with care through closure sessions, support planning, and a focus on building independence rather than dependence. We discuss what ethical offboarding for mental health AI could look like, including advance notice, gradual tapering, progress summaries, data portability, and clear pathways to human support. As AI becomes more deeply woven into emotional and clinical care, designing a responsible goodbye may be just as important as designing the first hello. References: Artificial Intelligence Discontinuation Effects (AI-DICE): An Emerging Phenomenon in Mental Health Applications Kelly et al. JMIR 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/

See All (56)

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
    56
  • Rating
    Clean
  • Copyright
    © 2026 Code & Cure
  • Show Website
    Code & Cure