Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Electronic health record analysis via deep poisson factor models

Journal Article · · Journal of Machine Learning Research
OSTI ID:1366989
 [1];  [2];  [2];  [2];  [2]
  1. Duke Univ., Durham, NC (United States); Duke University
  2. Duke Univ., Durham, NC (United States)

Electronic Health Record (EHR) phenotyping utilizes patient data captured through normal medical practice, to identify features that may represent computational medical phenotypes. These features may be used to identify at-risk patients and improve prediction of patient morbidity and mortality. We present a novel deep multi-modality architecture for EHR analysis (applicable to joint analysis of multiple forms of EHR data), based on Poisson Factor Analysis (PFA) modules. Each modality, composed of observed counts, is represented as a Poisson distribution, parameterized in terms of hidden binary units. In-formation from different modalities is shared via a deep hierarchy of common hidden units. Activation of these binary units occurs with probability characterized as Bernoulli-Poisson link functions, instead of more traditional logistic link functions. In addition, we demon-strate that PFA modules can be adapted to discriminative modalities. To compute model parameters, we derive efficient Markov Chain Monte Carlo (MCMC) inference that scales efficiently, with significant computational gains when compared to related models based on logistic link functions. To explore the utility of these models, we apply them to a subset of patients from the Duke-Durham patient cohort. We identified a cohort of over 12,000 patients with Type 2 Diabetes Mellitus (T2DM) based on diagnosis codes and laboratory tests out of our patient population of over 240,000. Examining the common hidden units uniting the PFA modules, we identify patient features that represent medical concepts. Experiments indicate that our learned features are better able to predict mortality and morbidity than clinical features identified previously in a large-scale clinical trial.

Research Organization:
Univ. of Michigan, Ann Arbor, MI (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA), Office of Nonproliferation and Verification Research and Development (NA-22)
Grant/Contract Number:
NA0002534
OSTI ID:
1366989
Journal Information:
Journal of Machine Learning Research, Journal Name: Journal of Machine Learning Research Journal Issue: 186 Vol. 17; ISSN 1532-4435
Publisher:
JMLRCopyright Statement
Country of Publication:
United States
Language:
English

Similar Records

Characterizing Sub-Cohorts via Data Normalization and Representation Learning
Conference · Wed Jul 01 00:00:00 EDT 2020 · OSTI ID:1659604

Budget Constrained Machine Learning for Early Prediction of Adverse Outcomes for COVID-19 Patients
Software · Sun Aug 22 20:00:00 EDT 2021 · OSTI ID:code-68001

Predictive models of long COVID
Journal Article · Mon Sep 04 00:00:00 EDT 2023 · EBioMedicine · OSTI ID:2439762