Predicting depression in Italy using random forest through the E2Tree methodology

Abstract Machine Learning techniques are celebrated for their predictive accuracy, uncovering subtle patterns beyond human perception. Among these, Random Forest is a widely adopted ensemble method, valued for its robust performance and ease of use, especially in scenarios where the cost of errors is significant. However, the inherent opacity of such models raises concerns about their interpretability and trustworthiness. In this study, we apply the Random Forest algorithm to analyze data from the Italian National Institute of Statistics (Istituto Nazionale di Statistica, Istat), specifically the European Health Interview Survey (EHIS), to identify risk factors associated with depression in Italy. To enhance transparency and interpretability, we subsequently employ the Explainable Ensemble Trees methodology to explore and understand the decision-making processes of the Random Forest model. The goal is to demonstrate how E2Tree can provide actionable insights for targeted interventions, supporting public health efforts in addressing mental health challenges.