Biography

I am an Assistant Professor of Computer Science and Engineering (CSE) at the University of Michigan. I currently head the MLD3 research group. My primary research interests lie at the intersection of machine learning and healthcare. The overarching goal of my research agenda is to develop the computational methods needed to help organize, process, and transform data into actionable knowledge.

I received my PhD in 2014 from MIT. At MIT, I worked with Prof. John Guttag in the Computer Science and Artificial Intelligence Lab (CSAIL). My PhD research focused on developing accurate patient risk-stratification approaches that leverage spatiotemporal patient data, with the ultimate goal of discovering information that can be used to reduce the incidence of healthcare-associated infections.

What drew you to MiCHAMP?

The people! MiCHAMP members span a wide variety of academic backgrounds and have diverse but complementary expertise. At weekly meetings, I have benefitted from the different perspectives around the table. It’s been fun to engage with MiCHAMP clinicians and other computational experts who share a common research goal: use data to make a real impact in patient care.

What specific expertise do you bring to MiCHAMP?

I am an Assistant Professor of Computer Science and Engineering. My expertise lies at the intersection of machine learning and healthcare. In particular, I’m focused on machine learning methods for time-series analysis. Time-series data appear frequently in healthcare in many different forms, including structured longitudinal electronic health record data, waveform data, and even imaging data.

What are your research interests and how do they tie into MiCHAMP?

I am particularly interested in time-series analysis, transfer/multitask learning, and building intelligible models. To date, we have focused for the most part on developing tools for patient risk stratification for adverse outcomes and modeling disease progression. We have projects that touch on a number of different application areas within healthcare including both acute (e.g., healthcare-associated infections) and chronic diseases (e.g., diabetes). The overarching goal of my research agenda is to develop the computational methods needed to organize, process, and transform data into actionable knowledge.