AI Health HDS Learning Experience: KESER: Clinical Knowledge Extraction via Sparse Embedding Regression with EHR data

April 13, 2022
4:00 pm to 5:00 pm

Event sponsored by:

AI Health
+DataScience (+DS)
Biostatistics and Bioinformatics
Computer Science
Electrical and Computer Engineering (ECE)


Duke AI Health



Chuan Hong, PhD. Assistant Professor of Biostatistics & Bioinformatics
Traditional data mining of EHR data often requires the use of patient-level data, which hinders the ability to share data across institutions. KESER is a knowledge extraction pipeline via sparse embedding regression, which efficiently summarizes patient-level longitudinal EHR data into hospital-specific embedding data and enables the extraction of clinical knowledge based only on summary-level data. KESER bypasses the need for patient-level data in individual analyses providing a significant advance in enabling multi-center studies using EHR data. Learn more about KESER at This seminar is part of the Health Data Science (HDS) Program learning experiences, which focus on applications of machine learning and use cases in health. Register here: