A Comparative Analysis of Depression in Malaysia and Argentina Using Machine Learning Approach

Abstract

This study conducts a comparative analysis of depression in Malaysia and Argentina using machine learning approach. By analysing datasets from the National Health and Morbidity Survey (Malaysia) and the Open Science Framework (Argentina), the study identifies key factors contributing to depression and evaluates the performance of various machine learning models, including Classification and Regression Tree (CART), Random Forest (RF), k-Nearest Neighbour (k-NN), Naïve Bayes (NB), and Support Vector Machine (SVM). The findings reveal socio-economic and demographic variables significantly influencing depression in both countries. CART and RF reveals as the most effective algorithms in predicting depression, with high accuracy and F1-scores, while SMOTE oversampling improved model performance by addressing class imbalance. The results highlight the importance of culturally sensitive predictive models for mental health and provide valuable insights for targeted interventions and policies in Malaysia and Argentina.