Format

Send to

Choose Destination
J Biomed Inform. 2016 Dec;64:168-178. doi: 10.1016/j.jbi.2016.10.007. Epub 2016 Oct 12.

Semi-supervised learning of the electronic health record for phenotype stratification.

Author information

1
Graduate Group in Genomics and Computational Biology, Perelman School of Medicine, University of Pennsylvania, United States; Institute for Biomedical Informatics, Perelman School of Medicine, University of Pennsylvania, United States. Electronic address: brettbe@med.upenn.edu.
2
Institute for Biomedical Informatics, Perelman School of Medicine, University of Pennsylvania, United States; Department of Systems Pharmacology and Translational Therapeutics, Perelman School of Medicine, University of Pennsylvania, United States; Institute for Translational Medicine and Therapeutics, University of Pennsylvania, Perelman School of Medicine, University of Pennsylvania, United States. Electronic address: csgreene@upenn.edu.

Abstract

Patient interactions with health care providers result in entries to electronic health records (EHRs). EHRs were built for clinical and billing purposes but contain many data points about an individual. Mining these records provides opportunities to extract electronic phenotypes, which can be paired with genetic data to identify genes underlying common human diseases. This task remains challenging: high quality phenotyping is costly and requires physician review; many fields in the records are sparsely filled; and our definitions of diseases are continuing to improve over time. Here we develop and evaluate a semi-supervised learning method for EHR phenotype extraction using denoising autoencoders for phenotype stratification. By combining denoising autoencoders with random forests we find classification improvements across multiple simulation models and improved survival prediction in ALS clinical trial data. This is particularly evident in cases where only a small number of patients have high quality phenotypes, a common scenario in EHR-based research. Denoising autoencoders perform dimensionality reduction enabling visualization and clustering for the discovery of new subtypes of disease. This method represents a promising approach to clarify disease subtypes and improve genotype-phenotype association studies that leverage EHRs.

KEYWORDS:

Denoising autoencoder; Disease subtyping; Electronic health record; Electronic phenotyping; Patient stratification; Unsupervised

PMID:
27744022
DOI:
10.1016/j.jbi.2016.10.007
[Indexed for MEDLINE]
Free full text

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center