Alaa Lab

Developing and Evaluating AI
to Transform Healthcare

We are a joint UC Berkeley and UCSF multidisciplinary research lab building and evaluating AI for healthcare. We develop methods to bring AI into clinical practice, and benchmarks to measure its real-world impact.

Our Publications Meet the Team
UC Berkeley UCSF Computational Precision Health Berkeley AI Research

Navigate our research here!

research.sh
— press any key —
$ select focus research area▌

Featured Publications

All publications →
ER-Reason: A Benchmark Dataset for LLM Clinical Reasoning in the Emergency Room
Nikita Mehandru, Niloufar Golchini, Namrata Garg, Kathy LeSaint, Christopher Nash, Anu Ramachandran, Travis Zack, Liam McCoy, Adam Rodman, David Bamman, Melanie Molina, Ahmed Alaa
arXiv preprint · 2026
Paper Code Data
CheXthought: A Global Multimodal Dataset of Clinical Chain-of-thought Reasoning and Visual Attention for Chest X-ray Interpretation
Sonali Sharma, Jin Long, George Shih, Sarah Eid, Christian Bluethgen, Francine L Jacobson, Emily B Tsai, Ahmed M Alaa, Curtis P Langlotz, Global Radiology Consortium
arXiv preprint · 2026
Paper Data
Position: Medical Large Language Model Benchmarks Should Prioritize Construct Validity
Ahmed Alaa, Thomas Hartvigsen, Niloufar Golchini, Shiladitya Dutta, Frances Dean, Inioluwa Deborah Raji, Travis Zack
ICML 2025 · Oral Presentation
Paper
Evaluating Large Language Models as Agents in the Clinic
Nikita Mehandru, Brenda Miao, Eduardo Rodriguez, Madhumita Sushil, Atul Butte, Ahmed Alaa
NPJ Digital Medicine · 2024
Paper
How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models
Ahmed Alaa, Boris van Breugel, Evgeny Saveliev, Mihaela van der Schaar
ICML 2022
Paper Code