Eli Sherman, a PhD candidate in the Department of Computer Science, has been chosen as a 2020 Google PhD Fellow in the machine learning category. He is one of 54 doctoral students from around the globe to receive this fellowship, which awards winners with two years of tuition and fees paid.
Sherman’s research in machine learning and health care prompted him to apply for the competitive fellowship. He is particularly interested in how machine learning can help improve clinical decision-making and the allocation of health care resources.
“Imagine you need an important medical procedure and your hospital only has the capacity to perform that procedure for one patient per day. If there happen to be several people ‘in line’ for the procedure, how should clinicians at the hospital decide which patient goes first?” Sherman asks. “Certainly, there are clear cases where a patient in a severe state of illness should be moved to the front of the line. But there are also gray areas, where determining severity and need is less obvious. These are the types of questions I study.”
Eli Sherman
Advised by Ilya Shpitser, a John C. Malone Assistant Professor of Computer Science, Sherman utilizes statistics and causal inference—a machine learning-adjacent field—in his research. Casual inference focuses on developing methods to identify and quantify causal relationships between variables in data collected from the world around us.
“I work on methods for analyzing causal relationships in populations where there is dependence between the subjects we’re studying, such as infectious disease spread, pollution, or public policy,” Sherman says.
Google created its PhD Fellowship program in 2009 to recognize and support outstanding graduate students who seek to influence the future of technology by pursuing exceptional research in computer science and related fields. Now in its 12th year, these fellowships have helped support approximately 500 graduate students globally in North America, Europe, Africa, Australia, East Asia, and India.
“I view this fellowship as permitting me a great deal of freedom to pursue the development of methods for better allocating resources and, more importantly, work towards deploying them in clinical practice,” says Sherman. “The strongest motivation for doing research is not the intellectual challenge of the work, but the idea that the research could have a tangible, positive impact on peoples’ lives.”