Skip to content Skip to navigation

Research & Ideas

Search this site

​Finale Doshi-Velez: Marrying data science and health care

​​At the second annual Women in Data Science conference at Stanford, a computer scientist explains how machine-learning techniques can optimize HIV treatments.

health and computer icons

Insights on the overlap between health care, data science and artificial intelligence | Shutterstock/Bloomicon

In a presentation at the second annual Women in Data Science conference, Harvard assistant professor of computer science Finale Doshi-Velez shared insights on the overlap between health care, data science and artificial intelligence.

“In the United States we spend more on health care and get worse outcomes than comparable countries,” she said. “There’s definitely work to be done here. The good news is that there are lots of cool questions that data science can address.”

For instance, Doshi-Velez researches ways to address one of the key challenges in treating HIV patients: The virus can become resistant to different drug cocktails over time. Doctors, therefore, must design treatments with both the present and the future in mind. Her lab’s key insight, she said, is to marry two data-centric techniques: modeling which patients are similar, and predicting the progression of the disease. Despite clinicians’ uncertainty that you can approach treatment on such a time scale, Doshi-Velez said they “were able to show there is enough predictability in this disease progression that you can think about the future and you can optimize for it.”

Get Updates from Stanford Engineering