In our second Reflections episode, Steve Labkoff and Leon Rozenblit synthesize the most meaningful insights from guests across Episodes 9–15. Drawing on conversations with Orr Inbar, Martin Leach, Ing Ho, Yuri Quintana, and patient advocate E-Patient Dave, this episode highlights the themes shaping practical AI adoption in today’s healthcare landscape.

Key topics include the inflection point AI has created across clinical care, research, and patient engagement; the need for stronger data stewardship to support trustworthy automation; and the emerging promise of AI-driven clinical trial optimization and simulation. We also explore how patients are engaging with AI tools independently, raising new questions about literacy, safety, and empowerment.

Additional themes include the cultural alignment required for tools like ambient listening and chart summarization to succeed and what it will take for AI to avoid the missteps of past health-IT transitions.

The episode closes with a preview of upcoming guests discussing AI in law, payer innovation, psychiatric diagnostics, and the future of scientific publishing.

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 shift

Adam 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/id1837172964

Spotify: https://open.spotify.com/show/63NBSNTdKsLHO7jmNxiZHv?si=277e9a14c24f41d9

Amazon 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

Practical AI in Healthcare just released one of our most eye-opening conversations yet, featuring Orr Inbar, CEO & Co-Founder of QuantHealth.

QuantHealth is pushing the boundaries of what’s possible in clinical development with AI-driven clinical trial simulation. Orr walked us through how modern deep learning, massive biological knowledge graphs, and patient-level real-world data can now simulate clinical trials with 80–90% accuracy — across dozens of indications, modalities, and trial phases.

In our conversation, we cover:

• How QuantHealth models patient-drug interactions at massive scale
• Why trial design is still the most critical (and fixable) failure point in drug development
• How simulation is becoming the new starting point for protocols
• What AI-first trial design could mean for speed, cost, and reducing avoidable trial failures
• Where the field is headed in the next 5–10 years — including the provocative question of how far simulation can replace human trials

Orr also discusses the acceleration of biological data, the maturity of real-world data, and transformer-based AI — the perfect storm that made this moment possible.

This is one of the best deep dives yet into the practical future of drug development.