Frances Dean

Joint with Ziad Obermeyer

Scholar LinkedIn Website

Franny Dean is a PhD student in Computational Precision Health at the UCSF and UC Berkeley. Her research focuses on predicting cardiovascular effects of cancer treatments with AI surrogates. Previously, she worked in global health, modeling cancer trends at the University of Washington’s Institute for Health Metrics and Evaluation and at St. Jude Children’s Research Hospital. She was originally admitted to the Berkeley PhD program in Mathematics and holds an MA in Mathematics from UC Berkeley and a BA in Mathematics from Williams College.

Publications

Causal Effect Estimation with Learned Instrument Representations

Frances Dean*, Jenna Fields*, R. Bhalerao, Marie-Laure Charpignon, Ahmed Alaa (*Co-first authors)

arXiv preprint · 2026

Paper

Artificial Intelligence Surrogate Models to Predict Long-Term Cardiovascular Effects of Immune Checkpoint Inhibitor Therapies Using Electrocardiograms

Frances Dean, J. Barrios, G. Tison, J.J. Moslehi, Ahmed Alaa

Journal of Clinical Oncology · 2026 · Abstract

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

Med-Real2Sim: Non-Invasive Medical Digital Twins using Physics-Informed Self-Supervised Learning

Keying Kuang, Frances Dean, Jack B. Jedlicki, David Ouyang, Anthony Philippakis†, David Sontag†, Ahmed Alaa† (†Co-senior authors)

NeurIPS · 2024

Paper