On National Nurses Day, Practical AI in Healthcare welcomes its first nurse: Sarah Rossetti, RN, PhD, of Columbia University. Her CONCERN early warning system takes an unusual approach to predicting patient deterioration. Instead of modeling a patient's vital signs and labs, it models the nurse's documentation behavior, since the frequency and timing of charting reflect clinical concern long before the numbers move. In a 74-unit randomized trial of more than 60,000 patients, published in Nature Medicine, CONCERN was associated with a 35.6% reduction in instantaneous mortality risk. Rossetti and the hosts unpack the method, the counterintuitive rise in ICU transfers, equity safeguards, and what ambient AI means for the signal.

https://practicalaiinhealthcare.com/episodes/#S1E39

More on Sarah Rossetti's work: https://www.dbmi.columbia.edu/profile/sarah-collins-rossetti/

In their fifth Reflections episode, Steve and Leon look back across six conversations (Matt Truppo at Sanofi, Ted Shortliffe, Barry Chaiken, David Hidalgo-Gato, and Danny van Leeuwen) to ask a sharper question: how specialized does AI have to be to actually work? The throughline is depth. The LLM is a commodity, and so, increasingly, is the generalist agent. What stays scarce is specialization in a workflow, the revival of symbolic methods like knowledge graphs, the literacy that separates an AI's ~95% solo accuracy from the under-35% people get using it themselves, and leaders willing to use themselves as the test rig. After 37 episodes, the technology is no longer the question. The specificity of the work around it is.

Danny van Leeuwen is a nurse of 50 years, a multiple sclerosis patient, host of the Health Hats podcast, and a serial member of national outcomes panels at CMS, AHRQ, PCORI, and the National Academy of Medicine. He has tried more than 100 health apps and uses five. In this episode, he explains how he uses AI to interrogate his own chart, surface symptom patterns, and prepare for clinical encounters, and he shares his Three T's and Two C's framework for evaluating any digital health technology: Time, Trust, Talk, Control, Connection. The conversation covers what patients want from AI, what they do not, and why pain, fear, and cognition still escape the data.

David Hidalgo-Gato is the founder and CEO of Cleo Health. While more than 100 competitors were building generic ambient AI scribes, David's team chose emergency medicine and stayed with one design partner for nine months and roughly 50 product iterations before launching. The result: an average 54-minute time savings per shift, a patient-assignment tool that turned a four-hour process into 15 to 20 minutes, and use across 400+ hospitals nationwide. The conversation covers why ED workflow breaks generic ambient scribes, why generative AI fits patient assignment specifically, and David's argument that workflow understanding is the moat AI cannot commoditize.

https://practicalaiinhealthcare.com/

When physician Barry Chaiken was diagnosed with prostate cancer, his clinical training gave way to fear. It took a friend asking, "What are you doing?" to snap him back into doctor-mode thinking. That experience reshaped how he sees AI in healthcare. In this episode, Chaiken draws on his dual perspective as physician and two-time cancer survivor to argue that consumer health AI is failing patients, not because the models are bad, but because patients don't know how to use them. He shares a practical framework for AI-assisted patient education, makes the case for an aviation-style safety reporting system for healthcare AI, and explains why interoperability is an incentive problem, not a technology problem.

In Part 2 of our conversation with Matt Truppo, Global Head of Research Platforms and Computational R&D at Sanofi, we move from discovery to development, where the real stakes begin. Matt unpacks the promise and limitations of “digital patient twins,” a concept often described as the holy grail of drug development. With nearly 90% of drugs failing in clinical trials, even modest gains in predicting efficacy or patient response could transform the industry. Through real-world examples, including Dupixent and rare disease therapies, Matt shows how quantitative systems pharmacology (QSP) and AI-driven simulations are already shortening timelines, reducing patient burden, and, in some cases, eliminating the need for entire trials.

But the story doesn’t stop at modeling. We explore how AI is reshaping clinical operations, from Sanofi’s “clinical control tower” that integrates trial data across 4,000 users, to generative AI tools that are cutting regulatory document creation time by more than a third. Matt also shares a personal experiment, building a network of AI agents modeled on his own workflow, reclaiming 30% of his time and offering a glimpse into a more “agentic” future of work. The throughline is clear: AI is not replacing human expertise, but amplifying it, helping the industry finally bend the cost and time curve of drug development.

Ted Shortliffe built MYCIN at Stanford in the 1970s, one of the first medical AI systems ever deployed in a clinical setting. Five decades later, he joins Steve and Leon to examine what has persisted in clinical decision support — above all, the demand for explainability — what has changed (computational power finally caught up to the ideas), and what the field may have lost along the way. The conversation includes a direct response to Bob Wachter's claim from S1E24 that AI in healthcare decision support was "too hard a problem to start with," and a case for why structured knowledge representation deserves a second look in the age of LLMs. For anyone tracing the arc of medical AI history, this episode is a rare primary source.

AI in drug discovery has been long on promise and short on delivery. Matt Truppo, Global Head of Research Platforms and Computational R&D at Sanofi, presents a different picture. His team used AI to identify 10+ novel drug targets in 12 months, screen 30 million target combinations in days, and produce AI-designed compounds with 75% synthesizability. But Truppo is equally candid about the gaps: data integration, explainability, and change management remain real barriers. In Part 1 of this two-part conversation, hosts Steve Labkoff and Leon Rozenblit explore what happens when AI moves past pilot projects into core pharmaceutical science.