Personalized Medicine Discovery through Machine Learning

Dr Donglin Zeng

Department of Biostatistics

Gillings School of Public Health

University of North Carolina at Chapel Hill



Personalized Medicine Discovery through Machine Learning

Advances in technology are revolutionizing medical research by collecting abundant data from each individual patient (clinical biomarkers, genomics, electronic health records) for clinical researchers to meet the promise of individualized treatment and health care. The availability of these rich data sources provides new opportunities to deeply tailor treatment for each patient in the presence of the patient heterogeneity, however, it also poses tremendous challenges for analyzing highly complex and noisy data for personalized medicine discovery.


In this talk, I will provide an overview of machine learning methods we have recently developed in this direction. They include learning methods for optimal dynamic treatment regimes, personalized dose finding, benefit-risk analysis, and medical diagnostics. For each method, we establish its theoretical properties including consistency and learning rates. The comparative advantages over existing methods are demonstrated in extensive simulation studies and real applications.



Please make every effort to attend.

975 West Walnut Street | Medical Research and Library Building, IB 130 | Indianapolis, IN 46202 | (317) 944-3966