A new study led by Selin Everett, with senior authors Jonathan Chen & Eric Horvitz, explores how rethinking human-AI collaboration can improve clinical decision-making. Published in Nature Digital Medicine, the multicenter randomized controlled trial found that when physicians and AI reason independently and then combine their perspectives, diagnostic accuracy significantly improves.

Jonathan Chen, MD, PhD, clinician, AI researcher, and Associate Professor at Stanford, whose work focuses on combining human and artificial intelligence to improve clinical decision-making. Dr. Chen reflects on the rapid rise of AI in medicine, and the moment he realized everything had changed. He also walks through surprising findings from his research, including studies showing that AI alone can sometimes outperform doctors using AI tools.

From uncertainty to impact, Purvesh Khatri’s career path was anything but straight. In this episode, he shares how curiosity and a willingness to pivot led to a breakthrough blood test that helps doctors make faster, life-saving decisions for sepsis.

In conference rooms and clinics across the country, leaders are asking the same question: How do we move from excitement about artificial intelligence to systems that actually work — safely, responsibly, and at scale? At the Stanford Division of Computational Medicine, a new program aims to answer that question.

The latest issue of Stanford Medicine Magazine explores how discoveries move from the lab to lasting impact in patient care. We’re proud to share that several members of our DoM community are featured in this issue, including Alan Pao, Purvesh Khatri, Victoria Parikh, Crystal Mackall, Seung Kim, and more.

A new study in npj Health Systems authored by Kameron Black, Stephen Ma, Hanna Kiani, Aditya Bhasin, Jonathan Chen, Nigam Shah, & colleagues, examines how non-clinician staff are using generative AI tools in real-world healthcare settings.

The Stanford-Harvard AI Research and Science Evaluation (ARISE) network produced a comprehensive guide to help clinicians and decision-makers who are inundated with AI offerings. The report is presented as an easy-to-digest slide deck synthesizing the most impactful clinical AI research over the past year. Click to read the full report.

As biological AI and general-purpose reasoning systems advance, the community faces balancing scientific progress with misuse risks. A new study by Tina Hernandez-Boussard, Russ Altman, & colleagues recommends narrow access controls on select high-risk pathogen data, while maintaining open access for most scientific data.

Euan Ashley and Nigam Shah Honored at PMWC 2026
Euan Ashley and Nigam Shah have been named 2026 Luminary Award honorees by the Precision Medicine World Conference (PMWC). Euan is being honored for his work integrating precision medicine into clinical care, while Nigam is being recognized in the AI in Clinical Decision Support & Real-World Evidence track for advancing data-driven approaches that translate innovation into patient impact. Congrats to both on this well-deserved recognition!
Click the Image to read more.

A large, Stanford-led team, senior-authored by Nigam Shah, introduces MedHELM — an open, task-based framework for evaluating medical LLMs on realistic clinical work, not just exam-style benchmarks.
Click the image to read the full paper!

AI isn’t about replacing clinicians — it’s about augmenting judgment in an increasingly complex healthcare system. In this episode, Jonathan Chen explores how AI can support clinical reasoning, education, and patient care, while also surfacing deeper issues around incentives, trust, and equity.
(Click image for podcast)