Cross-Organization Aggregate EHR Audit Log Data Imputation

Poster Number: P177
Presentation Time: 05:00 PM - 06:30 PM

Abstract Keywords: Machine Learning, Data Standards, Data Sharing
Primary Track: Applications

Implementing electronic health records (EHRs) has generated valuable vendor audit log data. However, missing data poses challenges for longitudinal and multi-site analysis. Advanced machine learning (ML) techniques may better capture missing patterns and preserve those observations compared to basic imputation methods. The primary objective of this study is to compare the efficacy of specific imputation strategies across diverse EHR usage metric data fields and consider implementation feasibility for organizations.

Speaker(s):
Huan Li, MS
Yale

Author(s):
Huan Li, MS - Yale; Nate Apathy, PhD - University of Maryland; A J Holmgren, PhD - University of California, San Francisco; Edward Melnick, MD - Yale University, School of Medicine; Robert McDougal, Ph.D. - Yale School of Public Health;