About

MOGU Lab is a Machine Learning (ML) laboratory at Wellesley College, focused on enabling effective and responsible uses of expressive (deep) ML models in safety-critical domains like precision healthcare. Our research specifically focuses on developing methods to help us better understand, predict, and prevent suicide and related behaviors.

Although based at Wellesley College, we work closely with clinical collaborators in the Boston area, including at Mass General Hospital, and Harvard’s Medical School and Department of Psychology, to develop new ML methodology that addresses the unique challenges found in their data.

We see clinicians’ insights and lived experiences as invaluable. As such, our work does not look to replace clinicians, but instead, to develop effective clinician-AI collaboration by finding new ways to meaningfully incorporate their expertise into ML systems.

Our work focuses both on the nitty-gritty details of the machine learning methodology, as well as on the broader sociotechnical system in which our methods will live. As such, we are equally as interested in ensuring our methods have the necessary statistical properties as we are in the necessary human-facing properties for good performance on their intended task and positive impact in their intended context.