Description
Type 2 diabetes mellitus (T2DM) is a chronic disease that requires long-term adaptive treatments. The optimal treatment depends on a variety of patient-specific clinical characteristics and previous medication history. To leverage the wealth of clinical information from the electronic health records (EHR), we proposed a nonparametric clustering algorithm on real patient clinical data to find the patient-specific optimal treatment. The treatment prescribed according to our algorithm decreases the HbA1c compared to that from standard care.
Learning Objective: After participating in this session, the learner should be better able to:
Obtain a better understanding of electronic health record (EHR) data mining for complex disease
Learn the knowledge of machine learning application in large medical dataset
Learn the application tool of personalized type2 diabetes treatment management
Authors:
wenyu song (Presenter)
Harvard Medical School
Linying Zhang, Harvard T.H. Chan School of Public Health
Emily Gill, University of Auckland
Jeremiah Zhe Liu, Harvard T.H. Chan School of Public Health
Adam Wright, Harvard Medical School
Presentation Materials: