Identifiable Phenotyping using Constrained Non-Negative Matrix Factorization
Abstract
This work proposes a new algorithm for automated and simultaneous phenotyping of multiple co-occurring medical conditions, also referred as comorbidities, using clinical notes from the electronic health records (EHRs). A basic latent factor estimation technique of non-negative matrix factorization (NMF) is augmented with domain specific constraints to obtain sparse latent factors that are anchored to a fixed set of chronic conditions. The proposed anchoring mechanism ensures a one-to-one identifiable and interpretable mapping between the latent factors and the target comorbidities. Qualitative assessment of the empirical results by clinical experts suggests that the proposed model learns clinically interpretable phenotypes while being predictive of 30 day mortality. The proposed method can be readily adapted to any non-negative EHR data across various healthcare institutions.
Cite
@article{arxiv.1608.00704,
title = {Identifiable Phenotyping using Constrained Non-Negative Matrix Factorization},
author = {Shalmali Joshi and Suriya Gunasekar and David Sontag and Joydeep Ghosh},
journal= {arXiv preprint arXiv:1608.00704},
year = {2016}
}
Comments
Presented at 2016 Machine Learning and Healthcare Conference (MLHC 2016), Los Angeles, CA