Data for: Assessing medication-related burden and medication adherence among older patients from Central Nepal: A machine learrning approach

Description This repository contains the primary dataset underlying the manuscript titled "Assessing medication-related burden and medication adherence among older patients from Central Nepal: A machine learning approach". The included spreadsheet file, LMQ_ARMS_OlderAdults_Nepal_dataset.xlsx, comprises fully de-identified data collected from 390 ambulatory older patients (aged >= 65 years) attending the dedicated geriatric outpatient department unit at Bharatpur Hospital, a central tertiary public hospital in Nepal. The dataset incorporates multidimensional socio-demographic, clinical, and medication-related features used to predict patient experiences and behaviors. Dataset Contents & Variables Socio-demographic features: Age group, gender, residence, marital status, occupation, educational status, ethnicity, and economic status. Clinical features: Primary diagnosis (Type 2 Diabetes Mellitus, Hypertension, Chronic Obruptive Pulmonary Disease, Ischemic Heart Disease), presence of multi-morbidity, and Charlson Comorbidity Index (CCI) category. Medication-related features: Polypharmacy status, medication formulation (oral only vs. oral + non-oral), medication dosing frequency, requirement of physical/cognitive assistance for medication management, financial payment structure (out-of-pocket vs. insured/free), and duration of medication use. Outcome Metrics: Total and domain-specific scores for the Living with Medicines Questionnaire (LMQ-3) and the Adherence to Refills and Medications Scale (ARMS). Abstract of the Associated Study Background: Nepal is experiencing a rapid demographic shift toward an aging population, with concurrent increase in morbidity and medication-related problems. Despite this, the multidimensional experience of medication-related burden (MRB) and refill adherence remain under-studied, particularly through the lens of socio-demographic, clinical and medication-related predictive features. This study aimed to assess MRB and medication adherence, and utilize machine learning (ML) architectures to identify complex factors influencing both. Methods: A cross-sectional study conducted among 390 ambulatory older patients (aged >= 65 years) at Bharatpur Hospital, Nepal. MRB and medication adherence was assessed using Living with Medications Questionnaire (LMQ-3) and Adherence to Refills and Medication Scale (ARMS). Six ML architectures (Ordinary Least Square, LightGBM, Random Forest, XGBoost, SVM, and Penalized linear regression) were employed to predict ARMS and LMQ scores using various socio-demographic, clinical and medication-related predictive features. Model explainability was provided through SHAP (Shapley Additive exPlanations). All the analysis were performed using R. Results: The median LMQ-3 score was 110.0 (IQR 14.0), reflecting a moderate medication-related burden, while the median ARMS score of 21.0 (IQR 6.0) indicated moderate non-adherence. Random forest was the superior predictive model for both MRB and adherence. SHAP analysis revealed requiring assistance for medication and polypharmacy as the most significant drivers of both increased burden and poor adherence. Interaction analysis revealed that while polypharmacy typically worsens adherence, the risk is partially mitigated when patients receive physical or cognitive assistance. Additional, financial factors and employment status emerged as significant predictors. Conclusion: Older patients in Nepal face a significant medication-related burden and non-adherence, driven largely by regimen complexity and the need for support. The high predictive accuracy of ML models suggests that clinical interventions should prioritize simplified regimens and patient-centered counseling for those with high dependency. These findings provide a data-driven rationale for policy-level medication optimization strategies in Nepal’s evolving healthcare system.