Interpretable Anxiety Detection and Optimization Using BOKHARI Hybrid Model: A Study on the Integration of Explainable AI in Mental Health Care

The anxiety disorders require the need for contemporary and easily comprehensible treatment. The role of artificial intelligence, specifically machine learning algorithms that can accurately predict and identify them, becomes useful. By incorporating the Explainable AI (XAI) approach, this study presents the BOKHARI Hybrid model, which enhances the clinical implementation and role of deep learning frameworks for anxiety detection at an early stage. The BOKHARI Hybrid model includes the base classifier of machine learning, including Support Vector Machines (SVM), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Logistic Regression. The significance of the BOKHARI hybrid model lies in its performance metrics as it attained an F 1 -score of 85.3%, recall of 86.2%, accuracy of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{8 5. 3 \%}$</tex>, and precision of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{8 4. 5 \%}$</tex>. The novelty of this study lies in the incorporation of XAI as it enhances the interpretability in mental health diagnostics, analyzes the patterns, and proposes a better treatment at an early stage. This study also outlines the necessity of further improvement of this model, including multimodal data integration and real-time monitoring for an advanced form of the framework. The BOKHARI model not only strengthens the relationship between technology and mental health treatment by advancing the AI-driven mental health diagnosis but also opens several ways for effective diagnostic tools for better treatment.