Adam Blum: AI-Powered Clinical Trial Matching
When Adam Blum was diagnosed with follicular lymphoma, he tried over a dozen commercial trial matchers. None returned actual matches. So the serial AI entrepreneur built CancerBot, a free precision matching service that assesses 100% of eligibility criteria — not the five surface-level attributes most matchers use. On this episode, Blum explains the Prompt Workbench (where biomedical experts refine extraction prompts to above 90% accuracy), how conjunctive normal form makes complex eligibility logic tractable, and why "best trial" means something different for every patient. A masterclass in AI scaffolding for healthcare.
Charlie Harp, CEO | Clinical Architecture
Healthcare Data Quality & the PIQI Framework
For 37 years, Charlie Harp heard the same thing from healthcare organizations: "Our data quality is fine." They were right — for billing and scheduling. But AI changed the equation. Harp, founder of Clinical Architecture, built the PIQI framework to measure patient data quality across four dimensions: availability, accuracy, conformance, and plausibility. His PIQXL Gateway scores data on a 1-100 scale before it enters your systems — not after. Early deployments reveal uncomfortable truths: lab data averages 70% quality against USCDI standards, and one facility coded every blood test to a single LOINC code. The framework is now going through HL7 balloting as an open national standard.
Discharge Planning Translation Services
with Giovanni Donatelli
Every day, patients leave US hospitals with discharge instructions they can't read. Giovanni Donatelli, CEO of The Language Group, built FETCH — a patented AI system embedded in Epic that translates discharge documents in 15 minutes with human review. He did it because he was the 8-year-old interpreting for his immigrant parents at doctor's appointments. Hosts Steve Labkoff and Leon Rozenblit explore the discharge instruction gap, the tragic cases that make it personal, FETCH's three-layer translation pipeline, the case for keeping humans in the loop, and why healthcare executives think they've already solved a problem that doesn't yet have a solution.
Reflections 3:
What Happens When Principles Meet Reality
Steve and Leon have reviewed blocks of guest episodes twice before on Practical AI in Healthcare. Both times the themes snapped into place. This time they didn't -- and the disagreement between them became the episode. Across five recent conversations, they found stories that kept spilling past the edges of their framework: AI that works but can't get paid, laws that already apply but nobody realizes it, and a scientific record under threat from AI-generated paper mills. The hosts' attempt to make sense of it all reveals where their thesis holds, where it breaks, and what needs to change.
Bob Wachter, MD | A Giant Leap: AI in Healthcare
Bob Wachter wrote the book on the EHR disaster. Now he's written one about AI.
The UCSF Chair of Medicine joins hosts Steve Labkoff and Leon Rozenblit to discuss A Giant Leap, his argument that AI doesn't need to be perfect—it needs to beat a healthcare system already failing at scale. They cover Watson's $3B collapse, why ambient scribes became AI's first clinical success story, the human-in-the-loop problem that nobody has solved, and the dangerous gap between how experts and novices use AI tools.
Key topics: productivity paradox, complementary innovations, clinical decision support design, AI literacy, and the "compare me to the alternative" thesis.
Amar Mandavia, PhD & Enrique "Kike" Gutiérrez, PhD
CHiRP: AI-Enabled Early Detection of Psychosis Risk
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.
Aaron Kamauu, MD, MS, MPH
RWE Design in the Age of Data
Real-world evidence was supposed to accelerate drug development. Instead, we've created definitional chaos—over 100 data vendors, inconsistent definitions, and studies that can't be compared.
Dr. Aaron Kamauu, CEO of Navidence and co-host of Real World Wednesday, explains why one missing diagnosis code can exclude 30% of your cohort, how GLP-1 eligibility criteria vary wildly between NHS and US guidelines, and what it means to document "the seven definitions you chose NOT to use."
A conversation about the unsexy infrastructure that makes evidence trustworthy.
Jeff Chuang, PhD
AI in Preclinical Cancer Research
When pathologists disagree on pediatric sarcoma diagnoses 25% of the time, the stakes are more than academic—these kids need different treatments depending on the cancer type. Jeff Chuang, Deputy Director of the JAX Cancer Center, built an AI classifier that achieves 96-98% accuracy. But the real story isn't the model. It's what it took to assemble training data from five institutions in just four months, navigating IRB processes that usually take years. We talk data diplomacy, foundation models that wash out batch effects, and why "the AI isn't the hard part." Plus: what it means to go from "2 colors" in traditional histology to "5,000 colors" with spatial transcriptomics.
Josh Geleris, MD (Co-founder & CPO, SmarterDx)
SmarterDx: Clinical AI for Revenue Integrity
Josh Geleris, MD, co-founder and Chief Product Officer of SmarterDx, joins us to discuss how clinical AI is transforming revenue cycle management. He explains the challenge of compressing 30,000 data points per patient into 20 diagnosis codes, and how his company evolved from SQL queries to post-trained LLMs to capture value hospitals were leaving on the table. We explore their data flywheel approach, why fine-tuned models outperform frontier systems on domain tasks, and how three layers of human oversight maintain compliance. Josh also shares his vision for moving beyond the payer-provider "arms race" toward more cooperative systems.
Alvin Liu, MD, Johns Hopkins
Oculomics and Diabetes Retina Screening
In this episode, we sit down with Dr. Alvin Liu, retinal surgeon and AI leader at Johns Hopkins, to explore one of the earliest real-world successes in medical AI: autonomous screening for diabetic retinopathy.
Dr. Liu walks us through what happened after FDA approval — the workflow integration challenges, the surprising equity gains for historically disadvantaged populations, and the economic realities that most AI deployments ignore.
We also look ahead to oculomics: using AI to extract cardiovascular, dementia, and kidney disease signals from retinal images, opening new pathways for community-based screening at scale.
This is what moving from AI hype to clinical reality actually looks like.
Tiffany Leung, MD, JMIR Scientific Editorial Director
In this episode of Practical AI in Healthcare, we sit down with Dr. Tiffany Leung, Scientific Editorial Director at JMIR Publications, to explore how artificial intelligence is reshaping scientific publishing from the inside out. As open access journals face unprecedented volumes of submissions, AI is simultaneously enabling faster discovery and creating new challenges around research integrity, peer review, and trust in the scientific record.
Tiffany shares how journals are adapting to generative AI tools, from policy development and disclosure norms to editorial decision support systems that help identify potential risks without stifling innovation. The conversation moves beyond hype to examine how AI can act as a co scientist, streamline editorial workflows, and potentially redefine peer review itself. This episode offers a rare look at how AI is influencing not just what gets published, but how knowledge is validated and shared globally.
Kathy Roe & Kenny White:
The Legal Realities of AI in Healthcare
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.
Reflections II - Episodes 9-15
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.
Adam Rodman, MD
Rethinking Clinical Reasoning in the Age of AI
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.
Orr Inbar, CEO Quant Health
AI Simulations of Clinical Trials
In this episode of Practical AI in Healthcare, Steven Labkoff and Leon Rozenblit speak with Orr Inbar, CEO of QuantHealth, one of the leading companies pioneering AI-driven clinical trial simulation. Orr explains how QuantHealth integrates mechanistic biology, real-world data from hundreds of millions of patients, and advanced AI foundation models to simulate clinical trials with unusually high accuracy.
The discussion explores why protocol design remains one of the most consequential — and error-prone — steps in drug development, and how simulation is helping pharma teams optimize eligibility criteria, endpoints, dosing strategies, safety considerations, and commercial positioning well before running a costly study.
Together, we examine where simulation fits today, how companies are using it to rescue struggling trials, and what the next 3–10 years may look like as AI-first trial design becomes standard across R&D.
A must-listen for anyone working in clinical development, R&D leadership, or life-science AI.
Part 2: Dr. Yin Ho's discussion of her new book,
Rushing Headlong: Health IT’s Legacy and the Road to Responsible AI
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.
Part 1: Dr. S. Yin Ho discusses her new book
The newest episode of Practical AI in Healthcare features Dr. Yin Ho—physician, entrepreneur, and author of Rushing Headlong: Health IT's Legacy and the Road to Responsible AI.
In Part 1 of our two-part conversation, Dr. Ho joins Dr. Steven Labkoff and Dr. Leon Rozenblit to unpack 25 years of digital health transformation—from the dawn of electronic medical records to the market and policy forces that shaped today’s health IT landscape.
Together, we explore how well-intentioned decisions created a fragmented system that prioritizes billing over care—and why understanding that history is essential to building a responsible AI future.
Dr. Yuri Quintana from the DCI Network
reviews our latest Meeting
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.
AI in Healthcare: A Patient's Perspective
with ePatient Dave
In this episode of Practical AI in Healthcare, Dr. Steven Labkoff and Dr. Leon Rozenblit speak with ePatient Dave DeBronkart, a globally recognized advocate for patient empowerment.
Dave shares his journey from a life-threatening kidney cancer diagnosis in 2007 to becoming one of the earliest champions of open data, patient access to medical records, and of late, patient use of AI tools to help empower them along their medical journey. He recounts how the ability to access information, share data, and join online patient communities helped save his life—and how those lessons now translate into how patients use generative AI. Dave highlights stories where AI enabled patients to identify rare diagnoses, manage health conditions, and even prepare for clinical visits.
The discussion examines how AI literacy and trust can empower patients, the ethical boundaries of sharing health data, and the evolution of patient–clinician partnerships in the era of AI.
Martin Leach, PhD, MBA
CDO of Black Canyon Consulting
This week’s episode of Practical AI in Healthcare dives into AI, truth, and the future of data in the government with Dr. Martin Leach, Chief Data Officer at Black Canyon Consulting.
Dr. Martin Leach, PhD, is a data, science, and technology leader with a career spanning some of the most innovative organizations in life sciences and academia. A self-described “data geek,” Martin began his career as a molecular neuropharmacologist before shifting from the bench to data-driven discovery. Over the past two decades, he has held senior roles at Merck, Biogen, Alexion, and AstraZeneca, and was the inaugural Chief Information Officer at the Broad Institute of MIT and Harvard.
Today, Martin serves as Chief Data Officer at Black Canyon Consulting, where he works these organizations on projects that unite bioinformatics, AI, and data federation — from building semantic knowledge graphs to creating “gold-standard” datasets for model validation. His work bridges the worlds of science, computation, and policy, shaping how government and industry can responsibly harness AI to advance biomedical research and healthcare delivery.
From building gold-standard datasets to exploring quantum AI, Martin shares how these projects are shaping the next generation of healthcare data science.
Reflections on Our First 7 Episodes
In this week's episode, Leon and Steve unpack and digest the various pearls provided by our first 7 podcasts. From frameworks to consider concerning AI in the business and healthcare setting to AI Literacy, we highlight the various lessons learned as we move into our third month of the Podcast.
Brendan Arbuckle, CIO, The Jackson Laboratory
This episode of Practical AI in Healthcare features Brendan Arbuckle, CIO of The Jackson Laboratory (JAX). Brendan shares how a world-leading genetics institute is deploying AI to advance research, streamline operations, and raise AI literacy across its organization. From ethical sandboxes to research breakthroughs and “everyday AI” that saves clinicians time, he offers a refreshingly grounded take on what responsible AI looks like in practice.
Listen now to learn how JAX balances innovation with rigor and why Brendan believes AI is “bigger than IT—it’s a new language of discovery.”
John Glaser: Lessons from a Healthcare IT
Pioneer on the Future of AI
Season 1, Episode 6 welcomes John Glaser—executive in residence at Harvard Medical School, former SVP at Cerner, past CEO of Siemens Health Services, and a pioneer in healthcare IT. Join hosts Dr. Steve Labkoff and Dr. Leon Rozenblit as they explore Glaser’s unique perspective on the trajectory of AI in healthcare, drawing lessons from over 40 years of industry transformation. Find out:
-
Why every breakthrough, from the mainframe to mobile, set the stage for today’s AI revolution.
-
How practical deployments—like specialized AI for prior authorizations—deliver true value, while hype often fills the void left by a lack of hands-on experience.
-
The importance of focusing on real-world ROI, efficiency, and smart clinical capacity management, with less emphasis on “sexy” use cases and more on what genuinely reshapes healthcare for the better.
-
Essential insights on domain specificity: why expert models outperform generic AI in high-stakes environments, and how learning from implementation drives success.
-
Why building successful AI adoption means mitigating risks, fostering literacy—not just technical training—and evolving governance to match pace with technology.
Glaser’s message is clear: “This is a remarkable time. This is remarkable technology. Extraordinarily powerful. ... But the way you deal with this kind of stuff is one step at a time.” Join the conversation and stay practical about what’s next in healthcare AI.
Yair Saperstein, MD - CEO of AVO
Yair Saperstein, MD, MPH, is CEO and Co-Founder of Avo, the AI engine used by healthcare organizations to improve care and operational outcomes in a way clinicians love. He is a hospitalist at Mount Sinai Hospital. Dr. Saperstein graduated from Albert Einstein College of Medicine with distinction in research in global health and from SUNY Downstate with a Master's in Public Health in hospital policy and management.
Avo is the OS for healthcare AI applications, providing a single point of entry for health systems to deploy any AI-powered workflow. Their initial suite of applications focuses on clinical decision support, chart review, scribing, and patient discharges.
Yair will discuss the challenges faced by clinicians and how Avo is changing some of the most perplexing issues in the day-to-day practice of medicine.
Author, Professor, & Healthcare Executive
Scott Snyder
Scott Snyder is many things: a part-time professor at the Wharton School of Business at the University of Pennsylvania, an author on AI, and the Chief Digital Officer of Eversana. In this episode we will explore Scott's various pursuits, his new book, and his view on where AI an Healthcare are intersecting.
Dr. Dereck Paul and Glass Health
One of the most underserved communities in the world of AI is that of clinicians. But Dr. Dereck Paul of Glass Health is trying to change that. Being a clinician himself, he's bringing a new approach to something that's the bane of a clinician's existence - creating and documenting interactions with patients. Listen in to this young entrepreneur as he unpacks his vision for clinical medicine and how Glass Health is trying to change things for clinicians for the better.
John Apathy and XponenL's Perspectives on AI
This week we hear from someone in the thick of the AI game, John Apathy from XponenL.AI. John's the Chief Solution's Officer for this recently acquired AI firm that focuses in on the pharmaceutical R&D space. John explains his perspectives as well as some of the work being done by his firm for some of their largest customers.
Leon Rozenblit of the QED Institute
In this pilot episode, co-hosts Dr. Steven Labkoff and Dr. Leon Rozinblit introduce the vision behind the podcast and lay the groundwork for future conversations. They discuss why now is the right moment for this kind of show, what defines a “practical” AI solution in healthcare, and how listeners—regardless of their role in the industry—can use these insights to inform their own work.
Connect With Us
Stay up to date with the most compelling stories available today.