Skip to main content
Journal cover image

Novel application of approaches to predicting medication adherence using medical claims data.

Publication ,  Journal Article
Zullig, LL; Jazowski, SA; Wang, TY; Hellkamp, A; Wojdyla, D; Thomas, L; Egbuonu-Davis, L; Beal, A; Bosworth, HB
Published in: Health Serv Res
December 2019

OBJECTIVE: To compare predictive analytic approaches to characterize medication nonadherence and determine under which circumstances each method may be best applied. DATA SOURCES/STUDY SETTING: Medicare Parts A, B, and D claims from 2007 to 2013. STUDY DESIGN: We evaluated three statistical techniques to predict statin adherence (proportion of days covered [PDC ≥ 80 percent]) in the year following discharge: standard logistic regression with backward selection of covariates, least absolute shrinkage and selection operator (LASSO), and random forest. We used the C-index to assess model discrimination and decile plots comparing predicted values to observed event rates to evaluate model performance. DATA EXTRACTION: We identified 11 969 beneficiaries with an acute myocardial infarction (MI)-related admission from 2007 to 2012, who filled a statin prescription at, or shortly after, discharge. PRINCIPAL FINDINGS: In all models, prior statin use was the most important predictor of future adherence (OR = 3.65, 95% CI: 3.34-3.98; OR = 3.55). Although the LASSO regression model selected nearly 90 percent of all candidate predictors, all three analytic approaches had moderate discrimination (C-index ranging from 0.664 to 0.673). CONCLUSIONS: Although none of the models emerged as clearly superior, predictive analytics could proactively determine which patients are at risk of nonadherence, thus allowing for timely engagement in adherence-improving interventions.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Health Serv Res

DOI

EISSN

1475-6773

Publication Date

December 2019

Volume

54

Issue

6

Start / End Page

1255 / 1262

Location

United States

Related Subject Headings

  • United States
  • Retrospective Studies
  • Myocardial Infarction
  • Medication Adherence
  • Medicare
  • Male
  • Logistic Models
  • Insurance Claim Review
  • Hydroxymethylglutaryl-CoA Reductase Inhibitors
  • Humans
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zullig, L. L., Jazowski, S. A., Wang, T. Y., Hellkamp, A., Wojdyla, D., Thomas, L., … Bosworth, H. B. (2019). Novel application of approaches to predicting medication adherence using medical claims data. Health Serv Res, 54(6), 1255–1262. https://doi.org/10.1111/1475-6773.13200
Zullig, Leah L., Shelley A. Jazowski, Tracy Y. Wang, Anne Hellkamp, Daniel Wojdyla, Laine Thomas, Lisa Egbuonu-Davis, Anne Beal, and Hayden B. Bosworth. “Novel application of approaches to predicting medication adherence using medical claims data.Health Serv Res 54, no. 6 (December 2019): 1255–62. https://doi.org/10.1111/1475-6773.13200.
Zullig LL, Jazowski SA, Wang TY, Hellkamp A, Wojdyla D, Thomas L, et al. Novel application of approaches to predicting medication adherence using medical claims data. Health Serv Res. 2019 Dec;54(6):1255–62.
Zullig, Leah L., et al. “Novel application of approaches to predicting medication adherence using medical claims data.Health Serv Res, vol. 54, no. 6, Dec. 2019, pp. 1255–62. Pubmed, doi:10.1111/1475-6773.13200.
Zullig LL, Jazowski SA, Wang TY, Hellkamp A, Wojdyla D, Thomas L, Egbuonu-Davis L, Beal A, Bosworth HB. Novel application of approaches to predicting medication adherence using medical claims data. Health Serv Res. 2019 Dec;54(6):1255–1262.
Journal cover image

Published In

Health Serv Res

DOI

EISSN

1475-6773

Publication Date

December 2019

Volume

54

Issue

6

Start / End Page

1255 / 1262

Location

United States

Related Subject Headings

  • United States
  • Retrospective Studies
  • Myocardial Infarction
  • Medication Adherence
  • Medicare
  • Male
  • Logistic Models
  • Insurance Claim Review
  • Hydroxymethylglutaryl-CoA Reductase Inhibitors
  • Humans