Predicting mental health disparities using machine learning for African Americans in Southeastern Virginia.

This study examined mental health disparities among African Americans using AI and machine learning for outcome prediction. Analyzing data from African American adults (18-85) in Southeastern Virginia (2016-2020), we found Mood Affective Disorders were most prevalent (41.66%), followed by Schizophrenia Spectrum and Other Psychotic Disorders. Females predominantly experienced mood disorders, with patient ages typically ranging from late thirties to mid-forties. Medicare coverage was notably high among schizophrenia patients, while emergency admissions and comorbidities significantly impacted total healthcare charges. Machine learning models, including gradient boosting, random forest, neural networks, logistic regression, and Naive Bayes, were validated through 100 repeated 5-fold cross-validations. Gradient boosting demonstrated superior predictive performance among all models. Nomograms were developed to visualize risk factors, with gender, age, comorbidities, and insurance type emerging as key predictors. The study revealed higher mental health disorder prevalence compared to national averages, suggesting a potentially greater mental health burden in this population. Despite the limitations of its retrospective design and regional focus, this research provides valuable insights into mental health disparities among African Americans in Southeastern Virginia, particularly regarding demographic and clinical risk factors.