Self-matched learning to construct treatment decision rules from electronic health records.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Author(s): Xu T;Xu T; Chen Y; Chen Y; Zeng D; Zeng D; Wang Y; Wang Y; Wang Y
  • Source:
    Statistics in medicine [Stat Med] 2022 Jul 30; Vol. 41 (17), pp. 3434-3447. Date of Electronic Publication: 2022 May 05.
  • Publication Type:
    Journal Article; Research Support, N.I.H., Extramural
  • Language:
    English
  • Additional Information
    • Source:
      Publisher: Wiley Country of Publication: England NLM ID: 8215016 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1097-0258 (Electronic) Linking ISSN: 02776715 NLM ISO Abbreviation: Stat Med Subsets: MEDLINE
    • Publication Information:
      Original Publication: Chichester ; New York : Wiley, c1982-
    • Subject Terms:
      Diabetes Mellitus, Type 2* ; Electronic Health Records*; Computer Simulation ; Humans ; Machine Learning ; Precision Medicine/methods
    • Abstract:
      Electronic health records (EHRs) collected from large-scale health systems provide rich subject-specific information on a broad patient population at a lower cost compared to randomized controlled trials. Thus, EHRs may serve as a complementary resource to provide real-world data to construct individualized treatment rules (ITRs) and achieve precision medicine. However, in the absence of randomization, inferring treatment rules from EHR data may suffer from unmeasured confounding. In this article, we propose a self-matched learning method inspired by the self-controlled case series (SCCS) design to mitigate this challenge. We alleviate unmeasured time-invariant confounding between patients by matching different periods of treatments within the same patient (self-controlled matching) to infer the optimal ITRs. The proposed method constructs a within-subject matched value function for optimizing ITRs and bears similarity to the SCCS design. We examine assumptions that ensure Fisher consistency, and show that our method requires weaker assumptions on unmeasured confounding than alternative methods. Through extensive simulation studies, we demonstrate that self-matched learning has comparable performance to other existing methods when there are no unmeasured confounders, but performs markedly better when unobserved time-invariant confounders are present, which is often the case for EHRs. Sensitivity analyses show that the proposed method is robust under different scenarios. Finally, we apply self-matched learning to estimate the optimal ITRs from type 2 diabetes patient EHRs, which shows our estimated decision rules lead to greater advantages in reducing patients' diabetes-related complications.
      (© 2022 John Wiley & Sons, Ltd.)
    • References:
      Eur J Cancer. 2017 Nov;86:178-185. (PMID: 28992561)
      Clin Diabetes. 2020 Jan;38(1):10-38. (PMID: 31975748)
      J Clin Epidemiol. 2006 May;59(5):437-47. (PMID: 16632131)
      Diabetes Res Clin Pract. 2014 Apr;104(1):1-52. (PMID: 24508150)
      JAMA. 2016 Jul 19;316(3):313-24. (PMID: 27434443)
      Int J Biostat. 2012 Jul 20;8(1):18. (PMID: 22850073)
      J Asthma. 2017 Dec;54(10):1019-1025. (PMID: 28135899)
      Ann Stat. 2011 Apr 1;39(2):1180-1210. (PMID: 21666835)
      Biometrics. 2013 Dec;69(4):893-902. (PMID: 24117144)
      Curr Epidemiol Rep. 2015 Dec;2(4):221-228. (PMID: 26954351)
      J Eval Clin Pract. 2013 Aug;19(4):638-43. (PMID: 22862884)
      Stat Med. 2018 Nov 20;37(26):3776-3788. (PMID: 29873099)
      Evid Based Med. 2016 Dec;21(6):224. (PMID: 27884884)
      J Am Stat Assoc. 2020;115(529):380-392. (PMID: 33041401)
      J Consult Clin Psychol. 2005 Feb;73(1):127-35. (PMID: 15709839)
      Biometrics. 2017 Mar;73(1):145-155. (PMID: 27213913)
      Stat Methods Med Res. 2013 Feb;22(1):70-96. (PMID: 22016461)
      Proc Int Conf Data Sci Adv Anal. 2018 Oct;2018:565-574. (PMID: 30931437)
      Biometrics. 2012 Dec;68(4):1010-8. (PMID: 22550953)
      J Allergy (Cairo). 2013;2013:627384. (PMID: 24204385)
      N Engl J Med. 2015 Nov 26;373(22):2117-28. (PMID: 26378978)
      J Clin Epidemiol. 2017 Jul;87:23-34. (PMID: 28460857)
      Biometrics. 2020 Dec;76(4):1075-1086. (PMID: 32365232)
      J Am Stat Assoc. 2012 Sep 1;107(449):1106-1118. (PMID: 23630406)
      Am J Epidemiol. 1978 Jul;108(1):3-8. (PMID: 685974)
      JAMA. 1988 Sep 23-30;260(12):1743-8. (PMID: 3045356)
    • Grant Information:
      NS073671 United States NS NINDS NIH HHS; P30 CA008748 United States CA NCI NIH HHS; R21 MH117458 United States MH NIMH NIH HHS; R01 MH123487 United States MH NIMH NIH HHS; GM124104 United States GM NIGMS NIH HHS; MH123487 United States MH NIMH NIH HHS; R01 NS073671 United States NS NINDS NIH HHS; R01 GM124104 United States GM NIGMS NIH HHS
    • Contributed Indexing:
      Keywords: individualized treatment rule; machine learning; precision medicine; self-controlled case series
    • Publication Date:
      Date Created: 20220505 Date Completed: 20220715 Latest Revision: 20230731
    • Publication Date:
      20231215
    • Accession Number:
      PMC9283315
    • Accession Number:
      10.1002/sim.9426
    • Accession Number:
      35511090