AI-Integrated Model for Addressing Blind Spots in Mental Health Services: Predicting Insomnia and Depression Comorbidity Using Logistic Regression

Chronic insomnia disorder and major depressive disorder exhibit a high rate of comorbidity. When these conditions co-occur, they are associated with poor treatment prognosis and exacerbated symptoms, highlighting the critical need for early screening. Existing clinical diagnostic approaches are time-consuming and costly, and the lack of rapid screening tools for early identification of complex disorders leaves comorbid patients in a diagnostic blind spot where only a single condition is diagnosed. This study proposes a logistic regression-based classification model to identify potential comorbid patients early by classifying major depressive disorder with comorbid chronic insomnia disorder. The experimental results demonstrate that the logistic regression model achieves approximately 88% classification accuracy, effectively predicting the risk of comorbidity between chronic insomnia disorder and major depressive disorder. These findings suggest the potential of this model as a data-driven decision-making tool for early identification of high-risk groups and the development of personalized treatment plans in mental health clinical settings.