Practical AI in Healthcare

What if early signs of psychosis could be detected from how patients speak—not what they say, but how they organize their thoughts?Amar Mandavia (VA Boston, Boston University) and Enrique "Kike" Gutiérrez (Polytechnic University of Madrid) join hosts Steve Labkoff and Leon Rozenblit to discuss CHiRP, an AI tool that identifies formal thought disorder from routine clinical conversations. They explain why the gold-standard manual test takes 5+ hours, how their system reduces that to minutes, and the hard ethical questions around labeling patients as "at risk."Key topics: prodromal psychosis detection, NLP in mental health, clinical workflow integration, MIT linQ Catalyst, and the payer challenges that make prevention hard to fund.

In this episode of Practical AI in Healthcare, we sit down with Dr. Jeff Chuang, a computational biologist at The Jackson Laboratory, to explore how AI is reshaping cancer diagnostics, starting with pediatric sarcoma. Jeff shares his journey from physics and protein folding to computational pathology, where machine learning is being applied to standard H&E pathology slides to deliver faster, cheaper, and more accurate diagnoses.The conversation dives into how AI models trained on relatively small but carefully curated image datasets can outperform traditional diagnostic approaches, especially in rare cancers where expertise is scarce. We also explore the challenges of data sharing, IRB approvals, and real-world deployment, along with a glimpse into the future of spatial genomics and ultra-high-resolution tissue analysis. This episode is a powerful example of how practical AI can directly improve patient care today.

In this episode of Practical AI in Healthcare, we sit down with Dr. Alvin Liu, retinal surgeon and Professor of Artificial Intelligence and Ophthalmology at Johns Hopkins University, to explore one of the earliest and most successful real-world deployments of medical AI.Dr. Liu walks us through the evolution of autonomous AI for diabetic retinopathy screening, from FDA approval to large-scale clinical implementation across health systems. We unpack what it really takes to move AI from validation to impact, including workflow integration, sensitivity and specificity tradeoffs, reimbursement challenges, and post-market monitoring. The conversation also looks ahead to emerging AI applications using retinal imaging to predict cardiovascular disease, dementia, and kidney disease at the population level.This episode is a masterclass in how AI can meaningfully improve access, equity, and outcomes in healthcare when deployed thoughtfully and responsibly.

In this episode, Steven Labkoff and Leon Rozenblit explore the legal, regulatory, and risk-management challenges introduced by AI with two top experts in the field: Kathy Roe, Principal at Health Law Consultancy, and Kenny White, Director of the Managed Care Industry Group at Alliant Insurance Services. Together, they unpack how AI intersects with medical malpractice, product liability, HIPAA privacy, de-identification, intellectual property, contractual risk, and insurance coverage. Kathy and Kenny explain why AI is not yet the standard of care — but why clinicians and health systems must develop AI literacy now as the legal landscape evolves.A must-listen episode for healthcare leaders navigating the risks and realities of AI adoption.

We just released one of the most intellectually energizing conversations we’ve had on Practical AI in Healthcare. Our guest this week is Dr. Adam Rodman, physician, informatician, historian of medicine, and one of the most original thinkers at the intersection of AI and clinical reasoning.Adam brings a rare perspective to the field: before becoming an AI researcher, he spent years studying how humans make medical decisions — how clinicians reason, where cognition breaks down, and how technology reshapes the way we conceptualize disease. His reflections on the evolution from QMR and INTERNIST-1 to today’s large language models are a must-hear.In this episode, we explore:• Why LLMs challenge 50 years of clinical decision support assumptions• New collaboration models for doctors, patients, and AI — not just “human in the loop,” but truly redesigned workflows• What’s holding back clinical AI adoption (spoiler: it’s not accuracy)• The regulatory gap—and why the FDA’s old device mindset won’t work for generative models• How urgent-care AI companies are early signals of a broader shiftAdam also discusses what the next 3–5 years may actually look like — and why change will be slow…until the moment it becomes very fast.Listen here and join the conversation on the future of practical, safe, and human-centered AI in healthcare.Apple Podcasts: https://podcasts.apple.com/us/podcast/practical-ai-in-healthcare/id1837172964Spotify: https://open.spotify.com/show/63NBSNTdKsLHO7jmNxiZHv?si=277e9a14c24f41d9Amazon Podcasts: https://music.amazon.com/podcasts/8ed0ba60-15f4-419b-85f1-c4b85af81b41/practical-ai-in-healthcare#HealthcareAI, #ClinicalAI #MedicalInformatics #ClinicalDecisionSupport #AIinMedicine #DigitalHealth #HealthTech #FutureOfHealthcare #GenerativeAI #AIGovernance #DiagnosticExcellence #PatientCareInnovation #HealthcareTransformation #AIThoughtLeadership #PracticalAI

In the conclusion of our two-part conversation with Dr. Yin Ho, author of Rushing Headlong: Health IT’s Legacy and the Road to Responsible AI, we explore how healthcare can avoid repeating its digital past. Dr. Ho and hosts Dr. Steven Labkoff and Dr. Leon Rozenblit dive into small language models, decision support vs. decision control, the pitfalls of ambient scribing, and why “rage-building” the next generation of EHRs might be the most responsible act of all.

Dr. Yuri Quintana, Director of the Division of Clinical Informatics at Beth Israel Deaconess Medical Center, joins us this week to discuss the DCI Network’s mission: turning AI in healthcare from theory into practice.The conversation traces DCI’s evolution as a multi-stakeholder “action tank” focused on collaboration, transparency, and patient safety. Quintana recounts the success of the Signal Through the Noise conference and the insights that emerged—chief among them that “mundane AI” (like triage, scheduling, and documentation tools) is quietly creating real value.The episode also explores topics like AI literacy, governance, transparency (“AI nutrition (model) labels”), and post-market surveillance for clinical AI—ending with a call to action: keeping healthcare innovation grounded in what truly matters to patients.