Tri-Model Synergy: Redefining Depression Detection through the Convergence of ANN, CNN, and SVM

Depression being a universal mental health challenge that affects millions globally, necessitating reliable detection methods in order to aid in timely intervention. Like physical health, mental health is not to be ignored. This study presents a novel hybrid model that combines Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Support Vector Machines (SVM) to analyze and detect depression in individuals. The hybrid model achieved a training accuracy of $\mathbf{9 5 . 6 \%}$ and a test accuracy of $\mathbf{9 1 . 2 \%}$, demonstrating its robustness and reliability. The total training time was recorded at 3.01 seconds, with ANN contributing 1.11 seconds and CNN contributing 1.9 seconds. Furthermore, the model’s performance metrics included an F1-Score of 0.91 and 0.91 for detecting the classes of absence and presence of depression respectively, highlighting its effectiveness in correctly identifying depressive states. This hybrid approach provides a comprehensive analysis by leveraging the strengths of each individual model, paving the way for more reliable and scalable mental health assessment tools.