Depressive Disorder Diagnostic Assessment Framework: A Review

Major Depressive Disorder (MDD) is one of the psychiatric condition that is undetected due to the limitations of subjective diagnostic methods. This study proposes a deep learning approach that combines the Convolutional Neural Net- works (CNNs) with a Multi- Layer Perceptron (MLP) to increase the diagnostic accuracy. The system is trained on the datasets containing demographic, psychological, and clinical attributes obtained from the NHANES depression dataset. The process includes the data preprocessing, feature selection, dimensionality reduction, and classification. Evaluation results shows that the MLP outperforms traditional machine learning models, such as Support Vector Machines, Logistic Regression, K-Nearest Neighbors, and XGBoost, achieving an accuracy of 91.2% with an F1- score of 0.9091. The proposed framework that presents the reliable and scalable method for improving the efficiency of the early MDD diagnosis. The final feature set is fed into an MLP classifier. The proposed method’s performance is benchmarked against conventional models, including Support Vector Machines (SVM), K-Nearest Neighbors (KNN), XGBoost, and Logistic Regression. Evaluation metrics—accuracy, precision, recall, and F1-score— demonstrate the robustness and reliability of the CNN- MLP model, highlighting its potential as a scalable solution for precise and data-driven mental health evaluation.