Identifying chronic disease patients using predictive algorithms in pharmacy administrative claims: an application in rheumatoid arthritis.

To evaluate the predictive performance of logistic and linear regression versus machine learning (ML) algorithms to identify patients with rheumatoid arthritis (RA) treated with target immunomodulators (TIMs) using only pharmacy administrative claims. Adults aged 18–64 years with ≥1 TIM claim in the...

Full description

Bibliographic Details
Published in:Journal of Medical Economics Vol. 24; no. 1; pp. 1272 - 1280
Main Authors: Maksabedian Hernandez, Ervant J., Tingzon, Isabelle, Ampil, Lorenzo, Tiu, Jessica
Format: Journal Article
Published: Taylor & Francis Ltd Jan-Dec 2021
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=154545246&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 154545246
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        13696998
        3K1U
      jtl: Journal of Medical Economics
      issn: 13696998
      maglogo: N
    pubinfo:
      dt: Jan-Dec 2021
      vid: 24
      iid: 1
      pid: 377
      pub: Taylor & Francis Ltd
      place: Philadelphia, Pennsylvania
    artinfo:
      ui:
        154545246
        153258154
        10.1080/13696998.2021.1999132
        154545246
      ppf: 1272
      ppct: 8
      formats:
      tig:
        atl: Identifying chronic disease patients using predictive algorithms in pharmacy administrative claims: an application in rheumatoid arthritis.
      aug:
        au:
          Maksabedian Hernandez, Ervant J.
          Tingzon, Isabelle
          Ampil, Lorenzo
          Tiu, Jessica
        affil: Global Health Economics, Amgen Inc, Thousand Oaks, CA, USA
      sug:
      ab: To evaluate the predictive performance of logistic and linear regression versus machine learning (ML) algorithms to identify patients with rheumatoid arthritis (RA) treated with target immunomodulators (TIMs) using only pharmacy administrative claims. Adults aged 18–64 years with ≥1 TIM claim in the IBM MarketScan commercial database were included in this retrospective analysis. The predictive ability of logistic regression to identify RA patients was compared with supervised ML classification algorithms including random forest (RF), decision trees, linear support vector machines (SVMs), neural networks, naïve Bayes classifier, linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and K-nearest neighbors (k-NN). Model performance was evaluated using F1 score, accuracy, precision, sensitivity, area under the receiver operating characteristic curve (AUROC), and Matthews correlation coefficient (MCC). Analyses were conducted in all-patient and etanercept-only samples. In the all-patients sample, ML approaches did not outperform logistic regression. RF showed small improvements versus logistic regression that were not considered remarkable, respectively: F1 score (84.55% vs 83.96%), accuracy (84.05% vs 83.79%), sensitivity (84.53% vs 82.20%), AUROC (84.04% vs 83.85%), and MCC (68.07% vs 67.66%). Findings were similar in the etanercept samples. Logistic regression and ML approaches successfully identified patients with RA in a large pharmacy administrative claims database. The ML algorithms were no better than logistic regression at prediction. RF, SVMs, LDA, and ridge classifier showed comparable performance, while neural networks, decision trees, naïve Bayes classifier, and QDA underperformed compared with logistic regression in identifying patients with RA.
      pubtype: Academic Journal
      doctype: Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N