Prediction of Depression via Supervised Learning Models: Performance Comparison and Analysis

This document Among all the various types of mental and psychosocial illnesses, most commonly occurring type is depression. It can cause serious problems such as suicide. Therefore, early detection important to stop progression this disease that could endanger human lives. Predicting detecting early-stage depression using machine learning (ML) techniques a promising strategy. study’s main purpose assess which ML are highly appropriate accurate regarding diagnoses. Six supervised namely: K-nearest neighbor (KNN), Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), Support vector (SVM) Naive Bayes (NB) were applied on dataset collected from Kaggle compared for their accuracy (ACC) performance in predicting The each model was evaluated 10-fold cross-validation terms ACC, F1-score, Precision (PR), Sensitivity (SEN). Based experimental results analysis, we conclude SVM LR performed better than other methods with an ACC 83,32%. found simple algorithm be used assist clinicians practitioners predict at stage, excellent potential utility considerable degree ACC.