Postdoc in the HealthRex Lab at Stanford with Dr. Jonathan H. Chen, building LLMs and evaluation frameworks that hold up in real clinical settings.
Much of my current work explores how LLMs and retrieval-augmented generation can support clinical workflows, enhancing specialty consultations, answering patient messages, and post-training models so the responses are accurate, reliable, and clinically useful.
I'm also a Data Science Lead in the ARISE network, advancing open benchmarks and real-world evaluation of clinical AI systems. Before Stanford, I completed my PhD in Biomedical Sciences at KU Leuven, where I focused on semi-supervised learning for time-to-event prediction in partially labeled clinical data.
I'm always happy to talk about clinical AI, research collaborations, or startup ideas. Drop me a line →
A large-scale benchmark for evaluating the clinical safety of LLMs using real physician-to-physician consultation cases, the foundation of MAST (Medical AI Superintelligence Test).
A retrieval-augmented system that helps primary care providers route specialty consultations and surfaces guideline-aligned recommendations during real clinical workflows.
Combining structured EHR data with LLM-extracted features (chronic pain, liver disease, depression) to predict 6-month retention in buprenorphine-naloxone therapy. Open-sourced an interactive web tool for real-time risk stratification at the bedside.
Methods for time-to-event prediction in ICU patients when most labels are censored, improving outcome prediction without requiring fully observed follow-up.
Open research network advancing safety, reliability, and real-world evaluation of clinical AI through open benchmarks like NOHARM/MAST.
Apprenticeship-style fellowship at Stanford's entrepreneurship engine, exploring how rigorous research translates into ventures that drive consequential, real-world impact.
Lead postdoc on Enhancing Specialty Care with Digital Medical Consultations: A Retrieval-Augmented Language Model Approach. PI: J. H. Chen; Co-PIs: Bernstein, Tibshirani, Goldstein.
Contributing to the world's most-cited annual report on AI progress, produced by Stanford HAI.
Program Committee member for two editions of ECML PKDD, the premier European venue for ML and data-mining research. Reviewing submissions in clinical ML, survival analysis, and applied AI.
When I'm not working on clinical AI, I'm usually traveling, hiking, or behind a camera. See more →
