Jean Feng, PhD, and collaborators featured in UCSF News and Nature have developed HACHI, a new model for developing tools that pairs AI’s ability to rapidly analyze medical records with the expertise of clinicians.
Using Wearables Data in the Clinic
Ida Sim, MD, PhD, featured in STAT News, sharing her perspective on the value of wearables data and the challenges of integration in the clinic.
Reducing Breast Cancer Screening Time for High-Risk Women
Researchers Discover New Way to Detect Sudden Cardiac Death Risk
Ziad Obermeyer, MD, CPH PhD student, Alex Schubert, and collaborators featured in Berkeley News for their latest Nature publication, using more than 440,000 EKGs from Sweden to train an artificial intelligence model to analyze the spikes and waveforms produced by the heart’s electrical currents.
Multiview AI Approach Can Improve Diagnostic Accuracy for Cardiac Imaging
Read UCSF Health featuring Geoff Tison, MD, MPH, sharing their demonstration that showed deep learning with ECGs improves detection of major cardiac conditions with full results published in Nature Cardiovascular Research
Marina Sirota, PhD, featured in The Resilient Brain Documentary
Watch The Resilient Brain featuring Marina Sirota, PhD (around minute 52), sharing her Alzheimer’s Disease and drug discovery research.
Healthcare Has a Culture Problem. Can AI Help Fix It?
Listen to The Culture Kit featuring Jon Kolstad, PhD, explaining why healthcare’s broken structure is ultimately a culture problem, and how AI—deployed in the right way—might help fix it.
The OpenEvidence Episode: Dr. Travis Zack on the Future of Clinical Evidence
Listen to NEJM AI Grand Rounds featuring Travis Zack, MD, PhD, discussing that reasoning—not just correctness—defines good care, and that evidence must be contextual, accessible, and usable.
Uncovering Epistatic Interactions in Complex Disease with Machine Learning with Bin Yu
Listen to The Genetics Podcast Episode 238 featuring Bin Yu, PhD, discussing how different statistical approaches, from linear models to random forests, can be used to study complex genetic traits, recent findings on epistasis in cardiomyopathy, and how improving robustness and reproducibility can lead to more reliable scientific conclusions.
Sylvia Cheng and Romain Pirracchio, MD, MPH, PhD, Share Findings at AMIA Informatics Conference in Denver
Sylvia and Romain built a reinforcement learning model using real-world data from UCSF to answer a critical question: how can we design an optimal treatment policy that both signals and treats elevated perioperative blood glucose to reduce life-threatening postoperative outcomes?
