Adapting machine learning techniques to censored time-to-event health record data: A general-purpose approach using inverse probability of censoring weighting.

Models for predicting the probability of experiencing various health outcomes or adverse events over a certain time frame (e.g., having a heart attack in the next 5years) based on individual patient characteristics are important tools for managing patient care. Electronic health data (EHD) are appea...

Full description

Bibliographic Details
Published in:Journal of Biomedical Informatics Vol. 61; pp. 119 - 132
Main Authors: Vock, David M., Wolfson, Julian, Bandyopadhyay, Sunayan, Adomavicius, Gediminas, Johnson, Paul E., Vazquez-Benitez, Gabriela, O’Connor, Patrick J., O'Connor, Patrick J
Format: research Journal Article
Published: Academic Press Inc. Jun2016
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=115825547&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 115825547
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        15320464
        OMB
      jtl: Journal of Biomedical Informatics
      issn: 15320464
      maglogo: N
    pubinfo:
      dt: Jun2016
      vid: 61
      pid: 735
      pub: Academic Press Inc.
      place: Burlington, Massachusetts
    artinfo:
      ui:
        115825547
        115825547
        NLM26992568
        115825547
        10.1016/j.jbi.2016.03.009
        NLM26992568
        PMC4893987 [Available on 06/01/17]
        115825547
      ppf: 119
      ppct: 13
      formats:
      tig:
        atl: Adapting machine learning techniques to censored time-to-event health record data: A general-purpose approach using inverse probability of censoring weighting.
      aug:
        au:
          Vock, David M.
          Wolfson, Julian
          Bandyopadhyay, Sunayan
          Adomavicius, Gediminas
          Johnson, Paul E.
          Vazquez-Benitez, Gabriela
          O’Connor, Patrick J.
          O'Connor, Patrick J
        affil: Division of Biostatistics, School of Public Health, University of Minnesota, 420 Delaware Street S.E., MMC 303, Minneapolis, MN 55455, United States
      sug:
        subj:
          Cluster Analysis
          Probability
          Algorithms
          Human
          Funding Source
      ab: Models for predicting the probability of experiencing various health outcomes or adverse events over a certain time frame (e.g., having a heart attack in the next 5years) based on individual patient characteristics are important tools for managing patient care. Electronic health data (EHD) are appealing sources of training data because they provide access to large amounts of rich individual-level data from present-day patient populations. However, because EHD are derived by extracting information from administrative and clinical databases, some fraction of subjects will not be under observation for the entire time frame over which one wants to make predictions; this loss to follow-up is often due to disenrollment from the health system. For subjects without complete follow-up, whether or not they experienced the adverse event is unknown, and in statistical terms the event time is said to be right-censored. Most machine learning approaches to the problem have been relatively ad hoc; for example, common approaches for handling observations in which the event status is unknown include (1) discarding those observations, (2) treating them as non-events, (3) splitting those observations into two observations: one where the event occurs and one where the event does not. In this paper, we present a general-purpose approach to account for right-censored outcomes using inverse probability of censoring weighting (IPCW). We illustrate how IPCW can easily be incorporated into a number of existing machine learning algorithms used to mine big health care data including Bayesian networks, k-nearest neighbors, decision trees, and generalized additive models. We then show that our approach leads to better calibrated predictions than the three ad hoc approaches when applied to predicting the 5-year risk of experiencing a cardiovascular adverse event, using EHD from a large U.S. Midwestern healthcare system.
      pubtype: Academic Journal
      doctype:
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N