Random Forest Model for Mental Disorder Prediction

Mental health is super important for our overall well-being-how we think, feel, and interact with others. Accurate diagnosis of mental disorders like bipolar disorder or depression is crucial, as they significantly impact our daily lives. That's where machine learning comes in. Random Forest is gaining attention for its potential to improve diagnostic accuracy. It's good at handling complex data. This study employed Random Forest model to predict various mental disorders, which includes Bipolar Mania, Bipolar Depression, Major Depression, and Normal. Random forest model performed well in identifying Bipolar Type-2 and Depression class. Some features like Mood Swing, Optimism, and Sexual Activity played a big role in predicting mental disorders. The RF model performed better than K-Nearest Neighbors, Support Vector Machine, Logistic Regression, and Naive Bayes, achieving a precision of 0.9365, recall of 0.8958, and an F1-score of 0.9076. Balanced data, fine-tuned hyperparameters, and careful feature preprocessing were key to success. The proposed model gives reliable and understandable predictions when it comes to classifying mental disorders. These findings could really help push forward AI tools for diagnosing mental health issues.