Missing Data Imputation in the Electronic Health Record Using Deeply Learned Autoencoders

Brett K. Beaulieu-Jones¹, Jason H. Moore², The Pooled Resource Open-Access ALS Clinical Trials Consortium

¹Genomics and Computational Biology Graduate Group, Computational Genetics Lab, Institute for Biomedical Informatics, Perelman School of Medicine, University of Pennsylvania
²Computational Genetics Lab, Institute for Biomedical Informatics, University of Pennsylvania
Email: brettbe@med.upenn.edu, jhmoore@exchange.upenn.edu

Pacific Symposium on Biocomputing 22:207-218(2017)

© 2017 World Scientific
Open Access chapter published by World Scientific Publishing Company and distributed under the terms of the Creative Commons Attribution (CC BY) 4.0 License.

Abstract

Electronic health records (EHRs) have become a vital source of patient outcome data but the widespread prevalence of missing data presents a major challenge. Different causes of missing data in the EHR data may introduce unintentional bias. Here, we compare the effectiveness of popular multiple imputation strategies with a deeply learned autoencoder using the Pooled Resource Open-Access ALS Clinical Trials Database (PRO-ACT). To evaluate performance, we examined imputation accuracy for known values simulated to be either missing completely at random or missing not at random. We also compared ALS disease progression prediction across different imputation models. Autoencoders showed strong performance for imputation accuracy and contributed to the strongest disease progression predictor. Finally, we show that despite clinical heterogeneity, ALS disease progression appears homogenous with time from onset being the most important predictor.