Home

Welcome to the Wang lab!

Our group develops statistical and machine learning methods for precision health. We focus on learning scientifically meaningful patient representations, using them to guide individualized and sequential treatment decisions, and providing valid inference for learned strategies. Our work includes generative, multimodal, and latent-state models of brain and behavioral dynamics and disease progression, integrated with reinforcement learning and causal inference for individualized treatment rules (ITRs) and dynamic treatment regimes (DTRs). Applications include clinical trials, electronic health records, biomarkers, and digital phenotypes in mental health and neurodegenerative disorders.

Research Interests

  • Learning optimal ITRs and DTRs with causal inference, reinforcement learning
  • Trustworthy inference for learned decision rules
  • Generative, multimodal, and latent-state models for brain, behavioral, and digital health data
  • Integrative learning from clinical trials, electronic health records and digital phenotypes
  • Applications in mental health and neurodegenerative disorders

Academic Appointments

Education

Selected Honors

  • Mitchell B. Balter Award, Journal of Clinical Psychopharmacology, 2026
  • President’s Citation Award, International Chinese Statistical Association, 2026
  • First Place Winning Team for the Parkinson’s Disease Digital Biomarker DREAM Sub-Challenge (Sponsored by the Michael J. Fox Foundation), 2017
  • Elected Fellow, American Statistical Association (ASA), 2016
  • Tow Faculty Leadership Scholars Award, Mailman School of Public Health, Columbia University, 2015-2018

Selected Professional Service and Leadership