Skip to main content
Journal cover image

Continuous-time probabilistic models for longitudinal electronic health records.

Publication ,  Journal Article
Kaplan, AD; Tipnis, U; Beckham, JC; Kimbrel, NA; Oslin, DW; McMahon, BH; MVP Suicide Exemplar Workgroup
Published in: J Biomed Inform
June 2022

Analysis of longitudinal Electronic Health Record (EHR) data is an important goal for precision medicine. Difficulty in applying Machine Learning (ML) methods, either predictive or unsupervised, stems in part from the heterogeneity and irregular sampling of EHR data. We present an unsupervised probabilistic model that captures nonlinear relationships between variables over continuous-time. This method works with arbitrary sampling patterns and captures the joint probability distribution between variable measurements and the time intervals between them. Inference algorithms are derived that can be used to evaluate the likelihood of future using under a trained model. As an example, we consider data from the United States Veterans Health Administration (VHA) in the areas of diabetes and depression. Likelihood ratio maps are produced showing the likelihood of risk for moderate-severe vs minimal depression as measured by the Patient Health Questionnaire-9 (PHQ-9).

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

J Biomed Inform

DOI

EISSN

1532-0480

Publication Date

June 2022

Volume

130

Start / End Page

104084

Location

United States

Related Subject Headings

  • Probability
  • Models, Statistical
  • Medical Informatics
  • Machine Learning
  • Humans
  • Electronic Health Records
  • Biomedical Engineering
  • Algorithms
  • 4601 Applied computing
  • 4203 Health services and systems
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Kaplan, A. D., Tipnis, U., Beckham, J. C., Kimbrel, N. A., Oslin, D. W., McMahon, B. H., & MVP Suicide Exemplar Workgroup, . (2022). Continuous-time probabilistic models for longitudinal electronic health records. J Biomed Inform, 130, 104084. https://doi.org/10.1016/j.jbi.2022.104084
Kaplan, Alan D., Uttara Tipnis, Jean C. Beckham, Nathan A. Kimbrel, David W. Oslin, Benjamin H. McMahon, and Benjamin H. MVP Suicide Exemplar Workgroup. “Continuous-time probabilistic models for longitudinal electronic health records.J Biomed Inform 130 (June 2022): 104084. https://doi.org/10.1016/j.jbi.2022.104084.
Kaplan AD, Tipnis U, Beckham JC, Kimbrel NA, Oslin DW, McMahon BH, et al. Continuous-time probabilistic models for longitudinal electronic health records. J Biomed Inform. 2022 Jun;130:104084.
Kaplan, Alan D., et al. “Continuous-time probabilistic models for longitudinal electronic health records.J Biomed Inform, vol. 130, June 2022, p. 104084. Pubmed, doi:10.1016/j.jbi.2022.104084.
Kaplan AD, Tipnis U, Beckham JC, Kimbrel NA, Oslin DW, McMahon BH, MVP Suicide Exemplar Workgroup. Continuous-time probabilistic models for longitudinal electronic health records. J Biomed Inform. 2022 Jun;130:104084.
Journal cover image

Published In

J Biomed Inform

DOI

EISSN

1532-0480

Publication Date

June 2022

Volume

130

Start / End Page

104084

Location

United States

Related Subject Headings

  • Probability
  • Models, Statistical
  • Medical Informatics
  • Machine Learning
  • Humans
  • Electronic Health Records
  • Biomedical Engineering
  • Algorithms
  • 4601 Applied computing
  • 4203 Health services and systems