Affordable Access

deepdyve-link
Publisher Website

Transitive Sequencing Medical Records for Mining Predictive and Interpretable Temporal Representations

Authors
  • Estiri, Hossein1, 2, 3
  • Strasser, Zachary H.1, 2, 3, 4
  • Klann, Jeffery G.1, 2, 3
  • McCoy, Thomas H. Jr.3, 5
  • Wagholikar, Kavishwar B.1, 2, 3
  • Vasey, Sebastien6
  • Castro, Victor M.2
  • Murphy, MaryKate E.2
  • Murphy, Shawn N.1, 2, 3, 4, 7
  • 1 Laboratory of Computer Science, Massachusetts General Hospital, Boston, MA 02144, USA
  • 2 Research Information Science and Computing, Mass General Brigham, Somerville, MA 02145, USA
  • 3 Harvard Medical School, Boston, MA 02115, USA
  • 4 Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, USA
  • 5 Center for Quantitative Health, Massachusetts General Hospital, Boston, MA 02114, USA
  • 6 Department of Mathematics, Harvard University, Cambridge, MA 02138, USA
  • 7 Department of Neurology, Massachusetts General Hospital, Boston, MA 02114, USA
Type
Published Article
Journal
Patterns
Publisher
Elsevier BV
Publication Date
Jun 18, 2020
Volume
1
Issue
4
Pages
100051–100051
Identifiers
DOI: 10.1016/j.patter.2020.100051
PMID: 32835307
PMCID: PMC7301790
Source
PubMed Central
Keywords
License
Unknown

Abstract

Electronic medical records (EHRs) contain valuable temporal information about progression of diseases and treatment trajectories. However, time is not precisely captured in clinical data. In a study of congestive heart failure, Estiri and colleagues propose an approach for extracting temporal sequential patterns from EHR data that improve phenotype prediction and classification and are also interpretable.

Report this publication

Statistics

Seen <100 times