University of Qom Journal of Data Analytics and Intelligent Decision-making 3115-8161 2 3 2026 07 01 A Hybrid CNN-HMM Framework for EEG-Based Classification of Anxiety, Chronic Stress, and Depression 167 184 4876 10.22091/jdaid.2026.16603.1082 EN Amir Hossein Kahvand Department of Electrical and Computer Engineering, Hamedan University of Technology, Hamedan, Iran 0009-0000-5816-5164 Hamid Reza Shahdoosti Department of Electrical and computer Engineering, Hamedan University of Technology, Hamedan, Iran. Mohammad Ghahremani Department of Electrical and Computer Engineering, Hamedan University of Technology, Hamedan, Iran Journal Article 2026 01 06 One of the biggest challenges in clinical medicine is early and accurate diagnosis of brain disorders, especially functional and psychological disorders like stress, anxiety and depression. While conventional machine learning relies on hand engineered time-consuming features, deep learning models, despite showing superior accuracy, can be limited in clinic application by interpretability issues because of their “black-box” design. In this paper we present a novel hybrid approach for brain disorder detection and classification through the analysis of EEG signals. Our model combines the strength of automatic feature extraction of Convolutional Neural Network (CNN) and time sequence modelling & interpretation of Hidden Markov Model (HMM). A real clinical data from 200 individuals (healthy group, anxiety group, chronic stress group, depression group) is collected and used to train and evaluate our system. This local collected data is for the first time used to validate models. Our results show that the hybrid approach achieved 92.30 percent in 4-class classification, and showed superiority to other standard approaches. The interpretable nature by HMM transition matrices also make it more relevant to aid clinical decision-making. https://jdaid.qom.ac.ir/article_4876_7a326d6cc16f8b5b7de1fff832a61d51.pdf