Development of a Depression Recognition System Using Electroencephalogram (EEG) Signals

Depression is a leading mental health disorder worldwide, with significant implications for individuals and society. In the Philippines, the prevalence of depression is alarmingly high, yet traditional diagnostic methods often rely on subjective self-reporting, which can lead to underdiagnosis and misdiagnosis. This study aimed to develop a machine learning-based depression recognition system utilizing electroencephalography (EEG) signals, providing an objective and reliable tool for depression detection. Using the publicly available Multi-modal Open Dataset for Mental-disorder Analysis (MODMA) dataset, which includes clinically validated diagnoses andPHQ-9 scores, EG features were extracted from brain regions known to be implicated in emotional processing, cognitive functions, and sensory integration. Machine learning models, including Support Vector Machine (SVM), Random Forest (RF), and Neural Network (NN), were trained and evaluated to classify depression based on EEG patterns. The study achieved a classification accuracy of 86.3%, with strong performance across sensitivity, specificity, and F1 scores, demonstrating the potential of EEG-based machine learning systems for mental health diagnostics. Among the models tested, Random Forest emerged as the most accurate in distinguishing between depressed and non-depressed states. Furthermore, the integration of the model with Arduino hardware allowed for the development of a real-time depression feedback system using LED indicators, showcasing the practical applicability of the model in real-world settings. This research contributes to the growing field of AI-assisted mental health diagnostics by providing an objective, non-invasive tool that can supplement traditional clinical methods. The findings highlight the potential of combining EEG and machine learning to enhance depression detection, offering a promising pathway for early intervention and improved mental health outcomes. This approach could revolutionize mental health care in the Philippines, addressing the limitations of current diagnostic practices and reducing the stigma surrounding mental health.