Predicting self-administered biologic nonadherence in Medicare fee-for-service beneficiaries with inflammatory bowel disease using machine learning models

Authors

• Christian Rhudy, University of Kentucky HealthCareFollow
• Courtney Perry, University of Kentucky
• Cody Bumgardner, University of KentuckyFollow
• Michael J. Wesley, University of KentuckyFollow
• David W. Fardo, University of KentuckyFollow
• Terrence Barrett, University of KentuckyFollow
• Jeffery Talbert, University of KentuckyFollow

Abstract

BACKGROUND: Nonadherence to self-administered biologic therapies increases risk for disease flares and adverse outcomes in inflammatory bowel disease (IBD). OBJECTIVE: To use machine learning and Medicare fee-for-service claims to create models predictive of medication nonadherence. METHODS: This study included Medicare fee-for-service beneficiaries with at least 2 IBD claims separated by 30 days between 2017 and 2021 and analyzed claims data from 2021. Beneficiaries with missing data or fewer than 3 self-administered biologic dispenses (adalimumab, certolizumab, golimumab, ustekinumab) on different dates in 2021 were excluded. Beneficiary-level nonadherence was defined as a proportion of days covered less than 0.8, and dispenselevel nonadherence as dispenses occurring more than 5 days after previous supply elapsed. Sixteen machine learning models were trained, and model performance was evaluated based on area under the receiver operating characteristic curve (AUC) scores, accuracy, F1 score, positive and negative predictive value (P/NPV), sensitivity, and specificity. RESULTS: A total of 10, 160 beneficiaries met inclusion and exclusion criteria. Subsequently, 64, 197 dispense transactions were observed, with 8, 547 (13.3%) considered nonadherent. Prior nonadherence was strongly associated with current dispense nonadherence (odds ratio, 2.65; 95% CI, 2.53-2.78). The random forest dispense-level model had fair predictive performance (AUC 0.739, accuracy 85.4%, sensitivity 17.7%, specificity 95.8%, PPV 39%, NPV 88.3%, F1 score 0.243). The bagging dispense-level model performed comparably with higher sensitivity (AUC 0.714, accuracy 74.9%, sensitivity 51%, specificity 78.6%, PPV 26.8%, NPV 91.3%, F1 score 0.351). CONCLUSIONS: Machine learning models trained on Medicare feefor- service claims data had fair predictive performance identifying nonadherent dispenses. The bagging model, which minimizes false negatives, may be most appropriate for future clinical decision support tools.

Document Type

Article

Publication Date

1-1-2026

Notes/Citation Information

Publisher Copyright: Copyright © 2026, Academy of Managed Care Pharmacy. All rights reserved.

Digital Object Identifier (DOI)

10.18553/jmcp.2026.32.1.27

Archival?

Archival

Repository Citation

Rhudy, Christian; Perry, Courtney; Bumgardner, Cody; Wesley, Michael J.; Fardo, David W.; Barrett, Terrence; and Talbert, Jeffery, "Predicting self-administered biologic nonadherence in Medicare fee-for-service beneficiaries with inflammatory bowel disease using machine learning models" (2026). Psychiatry Faculty Publications. 64.
https://uknowledge.uky.edu/psychiatry_facpub/64