A Governed Machine Learning Framework for Predicting Healthcare Provider Treatment Adoption and Prescribing Behavior
DOI:
https://doi.org/10.56830/IJSIE202610Keywords:
Governed Machine Learning, Healthcare Provider Treatment Adoption, Prescribing Behavior Prediction, Medicare Part D, Explainable Artificial Intelligence, Semaglutide and Tirzepatide AdoptionAbstract
Machine learning has not yet been studied in relation to treatment adoption among healthcare providers, even though it is relevant for demand forecasting, evidence prediction, and healthcare resource planning. The researchers developed a governed machine-learning framework to estimate observable use of semaglutide and tirzepatide and link it to prescribing activity among Medicare Part D prescribers. This study used a retrospective longitudinal design, drawing on public CMS data from 2021 to 2024 and a stratified sample of 120,000 prescribers. The study compared regularized logistic regression, random forest, and XGBoost across temporal holdout validation, calibration, SHAP explainability, subgroup assessment, and governance controls. In the provisional 2024 holdout analysis, 3,129 of 16,487 eligible providers crossed the observable-adoption threshold of at least 11 claims, yielding an adoption rate of 19.0%. In the provisional classification analysis, XGBoost achieved the highest AUROC (0.858), AUPRC (0.617), Brier score (0.112), calibration slope (0.98), and approximate F1 score (0.60). In the provisional regression analysis, XGBoost achieved a mean absolute error of 38.6 standardized 30-day fills and an R2 of 0.61 for post-adoption prescribing intensity. The framework illustrates how provider-behavior prediction can be coupled with provenance, fairness, explainability, provider monitoring, and human oversight. Furthermore, future studies using prospective Medicaid, multi-insurance, and multiinstitutional EHR data across reimbursement systems and clinical practice would support external validation before operational deployment.
References
Abdullah, M. A., Ahmed, A. S., Shaikh, B. T., Kaleem, M. B., Sumbal, A., & Naeem, Z. (2024). Prescription practices of physicians, quality of care, and patients’ safety: A mixed methods comprehensive study. International Journal of Health Sciences, 18(1), 29–34. https://pmc.ncbi.nlm.nih.gov/articles/PMC10768469/ Ben Moshe Gaash, M., Chodick, G., Romano, R., Greenfeld, S., Gedassi, B., Lerner, U., Azuri, J., & Shapiro Ben David, S. (2026). Physician adoption patterns of AI-driven clinical decision support systems in urinary tract infection management. Scientific Reports. https://doi.org/10.1038/s41598-026-57724-7
Collins, G. S., Moons, K. G. M., Dhiman, P., Riley, R. D., Beam, A. L., Van Calster, B., et al. (2024). TRIPOD+AI statement: Updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ, 385, e078378. https://doi.org/10.1136/bmj-2023-078378
Davoudi, A., Chae, S., Evans, L., Sridharan, S., Song, J., Bowles, K. H., McDonald, M. V., & Topaz, M. (2024). Fairness gaps in machine learning models for hospitalization and emergency department visit risk prediction in home healthcare patients with heart failure. International Journal of Medical Informatics, 191, 105534. https://doi.org/10.1016/j.ijmedinf.2024.105534
Efthimiou, O., Seo, M., Chalkou, K., Debray, T., Egger, M., & Salanti, G. (2024). Developing clinical prediction models: A step-by-step guide. BMJ, 386, e078276. https://doi.org/10.1136/bmj-2023-078276
Enugala, V. K., & Goel, G. (2025). AI-driven sustainable infrastructure and EV supply chain optimization using BIM, LiDAR, and SAP-based automation. In Proceedings of the 2025 Tenth International Conference on Science Technology Engineering and Mathematics (ICONSTEM) (pp. 1–7). IEEE. https://ieeexplore.ieee.org/document/11374619
Fourkiotis, K. P., & Tsadiras, A. (2025). Future internet applications in healthcare: Big datadriven fraud detection with machine learning. Future Internet, 17(10), 460. https://doi.org/10.3390/fi17100460
Ghazalbash, S., Zargoush, M., Guilcher, S. J., & Kuluski, K. (2026). Responsible AI for predicting delayed hospital discharge among older adults: Development and evaluation study for balancing accuracy, equity, and explainability. JMIR Medical Informatics, 14, e83244. https://doi.org/10.2196/83244
Gidali, D., & Ward, B. (2023). The 2021 Physician Pain Management Questionnaire pilot study. National Center for Health Statistics. https://stacks.cdc.gov/view/cdc/131353
Guo, L. L., Fries, J., Steinberg, E., Fleming, S. L., Morse, K., Aftandilian, C., Posada, J., Shah, N., Sung, L., et al. (2024). A multi-center study on the adaptability of a shared foundation model for electronic health records. npj Digital Medicine, 7, 171. https://doi.org/10.1038/s41746-024-01166-w
Johnphill, O., Sadiq, A. S., Kaiwartya, O., & Taheir, M. A. (2026). Cross: A cloud-native approach to automated remediation and self-healing in cyber-physical systems. Cybersecurity, 9(1), 124. https://doi.org/10.1186/s42400-026-00549-8
Kim, H., et al. (2024). Development of a machine learning approach for prediction of red blood cell transfusion in patients undergoing Cesarean section at a single institution. Scientific Reports, 14, 16556. https://doi.org/10.1038/s41598-024-67784-2
Kondrashov, A. A., Loskutova, E. E., & Kurashov, M. M. (2026). The digital profile of a physician as a new approach to improving recommendation systems for prescribing drugs. International Journal of Risk & Safety in Medicine, 37(2), 185–192. https://doi.org/10.1177/09246479251389215
Koneru, N. M. K. (2025). AI-driven optimization of CI/CD pipelines for multi-cloud infrastructure deployment. In Proceedings of the 2025 Tenth International Conference on Science Technology Engineering and Mathematics (ICONSTEM) (pp. 1–6). IEEE. https://ieeexplore.ieee.org/abstract/document/11374441
Kyle, M. A., Kakani, P., Burn, S. L., & Maini, L. (2026). Trends in prescription drug coverage restrictions in Medicare, Medicaid, and commercial insurance plans, 2011– 2019. Health Affairs Scholar, 4(3), qxag059. https://doi.org/10.1093/haschl/qxag059
Lekadir, K., et al. (2025). FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare. BMJ, 388, e081554. https://doi.org/10.1136/bmj-2024-081554
Li, Y., Yuan, M., Yang, Y., Fu, J., Xin, Y., Duan, C. J., & Wang, J. (2026). An ethicsinformed computable audit framework for monitoring misdiagnosis risk in AI-assisted diagnosis. Scientific Reports. https://doi.org/10.1038/s41598-026-46652-1
Liu, X., Lu, C. A., Shih, Y. T., & Jiang, C. (2025). Coverage and prior authorization policies for semaglutide and tirzepatide in Medicare Part D plans. JAMA Network Open, 8(8), e2529842. https://doi.org/10.1001/jamanetworkopen.2025.29842
Lulla, K., & Sayyed, Z. (2025). AI-driven fault-tolerant cloud-native architecture for missioncritical hardware-software integration and scalable enterprise automation. In Proceedings of the 2025 Tenth International Conference on Science Technology Engineering and Mathematics (ICONSTEM) (pp. 1–6). IEEE. https://ieeexplore.ieee.org/document/11374324
Malik, G. (2024). Embedding security into the pipeline: A framework for scalable DevSecOps implementation. International Journal of Data Science and Machine Learning, 4(1), 37–62. https://scholar.google.com/citations?view_op=view_citation&hl=en&user=QeYN5fs AAAAJ&citation_for_view=QeYN5fsAAAAJ:UeHWp8X0CEIC
Malik, G., & Prashasti. (2023). Continuous exposure management using AI and threat intelligence. International Journal of Intelligent Systems and Applications in Engineering, 11(6s). https://scholar.google.com/citations?view_op=view_citation&hl=en&user=QeYN5fs AAAAJ&citation_for_view=QeYN5fsAAAAJ:Se3iqnhoufwC
Moons, K. G. M., Damen, J. A. A., Kaul, T., Hooft, L., Navarro, C. A., Dhiman, P., et al. (2025). PROBAST+AI: An updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods. BMJ, 388, e082505. https://doi.org/10.1136/bmj-2024-082505
Moreno-Sánchez, P. A., Aalto, M., & van Gils, M. (2024). Prediction of patient flow in the emergency department using explainable artificial intelligence. Digital Health, 10. https://doi.org/10.1177/20552076241264194
Nagaraj, V., Gundla, S. R., & Vennamaneni, P. R. (2025). AI-driven secure and cloud-native microservice architectures for high-performance financial and hardware accelerator systems. In Proceedings of the 2025 Tenth International Conference on Science Technology Engineering and Mathematics (ICONSTEM) (pp. 1–7). IEEE. https://ieeexplore.ieee.org/document/11374740
Patel, S. Y., & Basu, S. (2026). Integrating healthcare system context to improve risk prediction and assess racial disparities among dual-eligible Medicare–Medicaid beneficiaries: A retrospective cohort study using national fee-for-service claims. BMJ Open, 16(3), e111343. https://bmjopen.bmj.com/content/16/3/e111343
Prakashkumar, P. K. R. (2025). Analytical study of adapting Oracle AI Agent Studio into Oracle ERP overview. International Journal of Entrepreneurship, Innovation, and Business Strategies, 3(1), 90–103. https://gprjournals.org/journals/index.php/ijeib/article/view/452
Rangu, S., Chadha, K. S., & Samala, S. (2025). AI-powered cloud architecture, agile analytics, and enterprise DevOps-enabled framework for healthcare and insurance ecosystem optimisation. In Proceedings of the 2025 Tenth International Conference on Science Technology Engineering and Mathematics (ICONSTEM) (pp. 1–7). IEEE. https://ieeexplore.ieee.org/document/11374414
Ravindranath, R., Stein, J. D., Hernandez-Boussard, T., Fisher, A. C., Wang, S. Y., Amin, S., et al. (2025). The impact of race, ethnicity, and sex on fairness in artificial intelligence for glaucoma prediction models. Ophthalmology Science, 5(1), 100596. https://doi.org/10.1016/j.xops.2024.100596
Ribers, M. A., & Ullrich, H. (2024). Complementarities between algorithmic and human decision-making: The case of antibiotic prescribing. Quantitative Marketing and Economics, 22, 445–483. https://doi.org/10.1007/s11129-024-09284-1
Rossi, D., Auriemma Citarella, A., De Marco, F., Di Biasi, L., Zheng, H., & Tortora, G. (2026). DREAM: Diabetes risk via explainable AI modeling. Multimedia Tools and Applications, 85(2), 145. https://doi.org/10.1007/s11042-026-21240-7
Saenz, A. D., Centi, A., Ting, D., You, J. G., Landman, A., Mishuris, R. G., et al. (2024). Establishing responsible use of AI guidelines: A comprehensive case study for healthcare institutions. npj Digital Medicine, 7, 348. https://doi.org/10.1038/s41746- 024-01300-8
Sardana, J., Hariharan, R., & Pudi, R. S. (2025). AI-driven secure and resilient healthcare data platforms with intelligent search and personalized communication. In Proceedings of the 2025 Tenth International Conference on Science Technology Engineering and Mathematics (ICONSTEM) (pp. 1–6). IEEE. https://ieeexplore.ieee.org/document/11374370
Sargent, M., Matthews, L. J., Yon, G. V., Storholm, E. D., Ober, A. J., & Green, H. D., Jr. (2024). Assessing the dynamics of PrEP adoption in a national-scale physician network. Social Networks, 78, 226–237. https://doi.org/10.1016/j.socnet.2024.02.001
Scannell, C., Romley, J., Myerson, R., Goldman, D., & Qato, D. M. (2024). Prescription fills for semaglutide products by payment method. JAMA Health Forum, 5(8), e242026. https://doi.org/10.1001/jamahealthforum.2024.2026
Sepuri, S. (2026). Comparative analysis of artificial intelligence test generation methods for compliance validation in regulated enterprise workflows. Journal of Intelligent Decision Making and Information Science, 3(2s), 107–123. https://doi.org/10.59543/jidmis.v3.632
Sun, K. (2026). Machine learning-based prediction model for 30-day emergency department revisits in a medically underserved tertiary hospital: Formative retrospective cohort study. JMIR Formative Research, 10, e87289. https://doi.org/10.2196/87289
Wells, B. J., Nguyen, H. M., McWilliams, A., Pallini, M., Bovi, A., Kuzma, A., et al. (2025). A practical framework for appropriate implementation and review of artificial intelligence (FAIR-AI) in healthcare. npj Digital Medicine, 8(1), 514. https://doi.org/10.1038/s41746-025-01900-y
Wesolowicz, D. M., Becker, W. C., Alegria, M., Chin-Purcell, L., Glass, J. E., Knudsen, H. K., et al. (2025). Integrating implementation outcomes into effectiveness studies: A practical guide for clinical interventionists. Journal of General Internal Medicine, 40(10), 2376–2382. https://doi.org/10.1007/s11606-025-09551-1
Yaseen, A., & Lahiri, S. W. (2023). Health care provider prescribing habits and barriers to use of new type 2 diabetes medications: A single-system survey study. Clinical Diabetes, 41(4), 490–501. https://doi.org/10.2337/cd22-0100
Zhang, Y. W., Blyumin, M. G., Qu, C., Guo, X., & Zhang, M. (2026). Assessing the impact of the Inflation Reduction Act on Medicare prescription drug coverage. American Journal of Health-System Pharmacy, zxag083. https://doi.org/10.1093/ajhp/zxag083
