Regina Barzilay, Professor of AI and Health; AI Faculty Lead, MIT Jameel Clinic

Regina Barzilay is a professor of electrical engineering and computer science at MIT and the AI faculty lead at the MIT Jameel Clinic. She spent her early career teaching computers to read news and dead languages, then turned to cancer after her own breast cancer diagnosis in 2014, and built Mirai, which reads a mammogram and estimates a woman's risk of breast cancer up to five years out.

Emigrating to Israel

She was born in 1970 in Chișinău, the capital of Moldova, and emigrated to Israel with her parents at 20. She earned a bachelor's degree in 1993 and a master's degree in 1998 from Ben-Gurion University of the Negev, then moved to New York City for a PhD in computer science at Columbia University, which she finished in 2003 under Kathleen McKeown.

Teaching Computers to Summarize and Decipher

For her dissertation she led Newsblaster, which took stories from different outlets about the same event and rewrote the shared facts as one summary. After a postdoctoral year at Cornell she joined MIT in 2003. With a student she mapped Ugaritic, a Bronze Age Semitic language written in cuneiform, onto Hebrew by lining up related words and word forms, a way to read a language almost no one had annotated.

Facing Breast Cancer

A routine mammogram found breast cancer in 2014. "Am I going to survive? What's going to happen to my son?" she remembered asking. Treated at Massachusetts General Hospital, she found almost no data or machine learning in her own care. "I really strongly felt it has to be changed," she said in 2017.

Building Mirai

With then-student Adam Yala and radiologists at Mass General Brigham she led Mirai, a deep-learning model that turns a mammogram into a risk score up to five years ahead, so a clinic can send a high-risk patient for extra screening and spare a low-risk patient extra tests. The MIT Jameel Clinic, where she became AI faculty lead in 2018, counts more than 2.7 million mammograms from 115 hospitals in 29 countries checked against Mirai.

Her lab also turned to drugs. In 2020 she and James J. Collins were on the team that published a deep-learning screen for new antibiotics, which identified halicin, a compound that killed drug-resistant bacteria in laboratory tests.

Winning the MacArthur and Squirrel AI Awards

The MacArthur Foundation gave her a fellowship in 2017 for machine-learning methods that work with few labeled examples. In 2020 she was the first recipient of the AAAI Squirrel AI Award for Artificial Intelligence for the Benefit of Humanity, a $1 million prize, and in 2023 she was elected to the National Academy of Engineering and the National Academy of Medicine.

Links

← All people · Featured in Voices of Healthcare: 30 People Changing Health Tech (2026)