Articles Vol. 67 No. CĐ11-NCKH 31/07/2026

A MACHINE LEARNING FRAMEWORK FOR PREDICTING TREATMENT ADHERENCE IN PARKINSON’S DISEASE: BALANCING PREDICTIVE ROBUSTNESS AND CLINICAL INTERPRETABILITY

Nguyen Thi Dinh1,2, Nguyen Thi Mai1,2, Nguyen Ngoc Giang3,4
1 Dai Nam University
2 Trường Đại học Đại Nam
3 Phenikaa University
4 Trường Đại học Phenikaa
DOI: 10.52163/yhc.v67iCD11.6029
19 Views
0 Downloads
Abstract

Background: Medication non-adherence among patients with chronic diseases such as Parkinson’s disease (PD) is a major challenge to effective treatment management. Applying Machine Learning (ML) models is a promising approach, but their application in clinical settings is often limited by small sample sizes, imbalanced clinical data, and especially their "black-box" nature.

Objective: This study aims to develop a robust, transparent ML framework to predict treatment adherence in PD patients, providing actionable clinical explanations, especially on a small dataset.

Methods: We analyzed a clinical dataset of 100 patients, which contains demographic, socioeconomic, and clinical features. To evaluate ML models with this small dataset, we utilized a Leave-One-Out Cross Validation (LOOCV) strategy. Additionally, the class imbalance (72% adherent vs. 28% non-adherent) problem was addressed using cost-sensitive learning algorithms. Feature engineering was also applied to resolve multicollinearity. We evaluated performance of Logistic Regression, Random Forest, and Support Vector Machine (SVM) models. Furthermore, Explainable AI (xAI) techniques were used to investigate feature contributions.

Results: The balanced Support Vector Machine (SVM) model achieved the highest overall performance of 85.0% accuracy and a F1-score of 0.746. Feature analysis indicated that medication regimen complexity, age, and disease duration are main indicators in predicting adherence behaviors.

Conclusion: Our proposed framework demonstrates that ML, when coupled with xAI, can reliably forecast treatment adherence even with limited clinical data. This transparent approach provides a foundation for developing robust Clinical Decision Support Systems (CDSS), and helps healthcare professionals to identify high-risk patients early and tailor personalized intervention strategies.

References
[1]
Malek N and Grosset DG. Medication Adherence in Patients with Parkinson’s Disease. CNS Drugs 2015 Jan; 29:47–53. DOI: 10.1007/s40263-014-0220-0 Google Scholar
[2]
Brown MT and Bussell JK. Medication Adherence: WHO Cares? Mayo Clinic Proceedings 2011 Apr; 86:304–14. DOI: 10.4065/mcp.2010.0575 Google Scholar
[3]
McCambridge J, Witton J and Elbourne DR. Systematic review of the Hawthorne effect: new concepts are needed to study research participation effects. Journal of Clinical Epidemiology 2014; 67:267–77. DOI: 10.1016/j.jclinepi.2013.08.015 Google Scholar
[4]
Lo-Ciganic WH, Donohue JM, Thorpe JM, Perera S, Thorpe CT, Marcum ZA and Gellad WF. Using Machine Learning to Examine Medication Adherence Thresholds and Risk of Hospitalization. Medical Care 2015 Aug; 53:720–8. DOI: 10.1097/MLR.0000000000000394 Google Scholar
[5]
Vabalas A, Gowen E, Poliakoff E and Casson AJ. Machine Learning Algorithm Validation with a Limited Sample Size. PLOS ONE 2019 Nov; 14. DOI: 10.1371/journal.pone.0224365 Google Scholar
[6]
Haibo He and Garcia E. Learning from Imbalanced Data. IEEE Transactions on Knowledge and Data Engineering 2009 Sep; 21:1263–84. DOI: 10.1109/TKDE.2008.239 Google Scholar
[7]
Amann J, Blasimme A, Vayena E, Frey D and Madai VI. Explainability for Artificial Intelligence in Healthcare: A Multidisciplinary Perspective. BMC Medical Informatics and Decision Making 2020 Dec; 20:310. DOI: 10.1186/s12911-020-01332-6 Google Scholar
[8]
Bates S, Hastie T and Tibshirani R. Cross-Validation: What Does It Estimate and How Well Does It Do It? Journal of the American Statistical Association 2024 Apr; 119:1434–45. DOI: 10.1080/01621459.2023.2197686 Google Scholar
[9]
Cox DR. The regression analysis of binary sequences. Journal of the Royal Statistical Society: Series B (Methodological) 1958; 20:215–32 Google Scholar
[10]
Cortes C and Vapnik V. Support-vector networks. Machine learning 1995; 20:273–97. DOI: 10.1007/BF00994018 Google Scholar
[11]
Lundberg S and Lee SI. A Unified Approach to Interpreting Model Predictions. 2017. DOI: 10.48550/ARXIV.1705.07874 Google Scholar