Machine Learning-Based Prediction of Diabetes Medication Use: A Pharmacoepidemiological Analysis of the Indonesia Family Life Survey
DOI:
https://doi.org/10.37287/ijghr.v8i6.2740Keywords:
diabetes medication, LASSO, machine learning, pharmacoepidemiology, SMOTENCAbstract
Diabetes pharmacotherapy frequently coexists with treatment for cardiovascular and metabolic comorbidities, highlighting the potential role of data-driven methods in pharmaceutical care. This study aimed to develop and compare machine learning models for predicting diabetes medication use using the fifth wave of the Indonesia Family Life Survey (IFLS5), conducted in Indonesia in 2014–2015. A secondary analysis included 48,139 participants with valid outcome information, of whom 353 (0.73%) reported diabetes medication use. Predictors included age, sex, pregnancy status, weight, height, hemoglobin, systolic and diastolic blood pressure, pulse, and medication use for anemia, hypertension, and hypercholesterolemia. Class imbalance was addressed using Synthetic Minority Over-sampling Technique for Nominal and Continuous features (SMOTENC) exclusively within training folds. LASSO-based feature selection was also performed within stratified 10-fold cross-validation. Random Forest, linear Support Vector Machine (SVM), Logistic Regression, and Gaussian Naive Bayes were compared. Logistic Regression achieved 80.13% accuracy, 76.20% sensitivity, 80.16% specificity, and an AUC of 0.870. Linear SVM showed comparable discrimination (AUC=0.870). Random Forest achieved high accuracy (97.86%) but low sensitivity (18.13%), whereas Naive Bayes achieved high sensitivity (98.30%) but low specificity (26.77%). LASSO consistently identified pregnancy status, cholesterol medication use, hypertension medication use, and weight among the strongest predictors. Logistic Regression provided the most balanced classification performance and may support further pharmacoepidemiological investigation of diabetes medication-use patterns.
References
9. Pharmacologic Approaches to Glycemic Treatment: Standards of Care in Diabetes—2024. (2024). Diabetes Care, 47, S158–S178. https://doi.org/10.2337/dc24-S009
Al Assaf, S., Zelko, R., & Hanko, B. (2022). The Effect of Interventions Led by Community Pharmacists in Primary Care for Adults with Type 2 Diabetes Mellitus on Therapeutic Adherence and HbA1c Levels: A Systematic Review. In International Journal of Environmental Research and Public Health (Vol. 19, Number 10). MDPI. https://doi.org/10.3390/ijerph19106188
Alex, S. A., Jhanjhi, N. Z., Humayun, M., Ibrahim, A. O., & Abulfaraj, A. W. (2022). Deep LSTM Model for Diabetes Prediction with Class Balancing by SMOTE. Electronics (Switzerland), 11(17). https://doi.org/10.3390/electronics11172737
Alfian, R., Fathin Fawwazi, M. H. A., Adikusuma, W., & Abero Phiri, Y. V. (2026). Pharmacists’ Experiences and Needs in Pharmaceutical Care to Support Diabetes Medication Adherence in Indonesian Primary Care. Journal of Public Health and Pharmacy, 6(2), 241–251. https://doi.org/10.56338/jphp.v6i2.8568
Alwhaibi, M. (2022). Potentially Inappropriate Medications Use among Older Adults with Comorbid Diabetes and Hypertension in an Ambulatory Care Setting. Journal of Diabetes Research, 2022. https://doi.org/10.1155/2022/1591511
Aman, & Chhillar, R. S. (2023). Optimized stacking ensemble for early-stage diabetes mellitus prediction. International Journal of Electrical and Computer Engineering, 13(6), 7048–7055. https://doi.org/10.11591/ijece.v13i6.pp7048-7055
Cabot, J. H., & Ross, E. G. (2023). Evaluating prediction model performance. Surgery (United States), 174(3), 723–726. https://doi.org/10.1016/j.surg.2023.05.023
Collins, G. S., Dhiman, P., Ma, J., Schlussel, M. M., Archer, L., Van Calster, B., Harrell, F. E., Martin, G. P., Moons, K. G. M., van Smeden, M., Sperrin, M., Bullock, G. S., & Riley, R. D. (2024). Evaluation of clinical prediction models (part 1): from development to external validation. BMJ. https://doi.org/10.1136/bmj-2023-074819
Coutureau, C., Slimano, F., Mongaret, C., & Kanagaratnam, L. (2022). Impact of Pharmacists-Led Interventions in Primary Care for Adults with Type 2 Diabetes on HbA1c Levels: A Systematic Review and Meta-Analysis. In International Journal of Environmental Research and Public Health (Vol. 19, Number 6). MDPI. https://doi.org/10.3390/ijerph19063156
Elreedy, D., Atiya, A. F., & Kamalov, F. (2024a). A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning. Machine Learning, 113(7), 4903–4923. https://doi.org/10.1007/s10994-022-06296-4
Elreedy, D., Atiya, A. F., & Kamalov, F. (2024b). A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning. Machine Learning, 113(7), 4903–4923. https://doi.org/10.1007/s10994-022-06296-4
Elseddawy, A. I., Karim, F. K., Hussein, A. M., & Khafaga, D. S. (2022). Predictive Analysis of Diabetes-Risk with Class Imbalance. Computational Intelligence and Neuroscience, 2022. https://doi.org/10.1155/2022/3078025
Kwon, Y., Han, K., Suh, Y. J., & Jung, I. (2023). Stability selection for LASSO with weights based on AUC. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-32517-4
Ou, Q., Jin, W., Lin, L., Lin, D., Chen, K., & Quan, H. (2023). LASSO-based machine learning algorithm to predict the incidence of diabetes in different stages. Aging Male, 26(1). https://doi.org/10.1080/13685538.2023.2205510
Piccialli, V., & Sciandrone, M. (2022). Nonlinear optimization and support vector machines. Annals of Operations Research, 314(1), 15–47. https://doi.org/10.1007/s10479-022-04655-x
Rastogi, R., & Bansal, M. (2023). Diabetes prediction model using data mining techniques. Measurement: Sensors, 25. https://doi.org/10.1016/j.measen.2022.100605
Sardu, C., Zimbudzi, E., Moradpour, F., & Alfian, S. D. (n.d.). Sociodemographic and behavioural risk factors associated with low awareness of diabetes mellitus medication in Indonesia: Findings from the Indonesian Family Life Survey (IFLS-5).
Ullah, Z., Saleem, F., Jamjoom, M., Fakieh, B., Kateb, F., Ali, A. M., & Shah, B. (2022). Detecting High-Risk Factors and Early Diagnosis of Diabetes Using Machine Learning Methods. Computational Intelligence and Neuroscience, 2022. https://doi.org/10.1155/2022/2557795
Vanacore, A., Pellegrino, M. S., & Ciardiello, A. (2024). Fair evaluation of classifier predictive performance based on binary confusion matrix. Computational Statistics, 39(1), 363–383. https://doi.org/10.1007/s00180-022-01301-9
Wang, P., Adisa, R., Davar Siadat, S., Yang, Y., Tong Xingwei Wu, R., Copyright, fpubh, Li, M., Lu, X., Yang, H., Yuan, R., Tong, R., & Wu, X. (n.d.). Development and assessment of novel machine learning models to predict medication non-adherence risks in type e diabetics.
Welvaars, K., Oosterhoff, J. H. F., van den Bekerom, M. P. J., Doornberg, J. N., van Haarst, E. P., van der Zee, J. A., van Andel, G. A., Lagerveld, B. W., Hovius, M. C., Kauer, P. C., Boevé, L. M. S., van der Kuit, A., Mallee, W., & Poolman, R. (2023). Implications of resampling data to address the class imbalance problem (IRCIP): an evaluation of impact on performance between classification algorithms in medical data. JAMIA Open, 6(2). https://doi.org/10.1093/jamiaopen/ooad033.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Indonesian Journal of Global Health Research
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
