Exploring Explainable AI for Enhanced Depression Prediction in Mental Health

Depression is a prevalent mental health condition affecting millions of individuals worldwide. This paper presents a comprehensive analysis using machine learning to predict depression, a prevalent mental health issue affecting millions worldwide. The dataset employed for this study includes a range of mental health conditions such as schizophrenia, bipolar disorder, eating disorders, anxiety disorders, drug use disorders, and alcohol use disorders, investigating their correlations with depression. We explore these relationships and develop predictive models to forecast the likelihood of depression. The study evaluates the performance of various machine learning algorithms, with the Random Forest algorithm demonstrating the highest accuracy rate of 99.30%. Furthermore, we delve into model interpretability by applying techniques like LIME and SHAP to explain the predictions. Our findings contribute significantly to the understanding and prediction of depression, offering valuable insights that could assist healthcare professionals in the early detection and proactive management of this condition.