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

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 18, 2025

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

Language: Английский

The Digital Age of Psychiatry in Taiwan: New Opportunities and Challenges

Taiwanese Journal of Psychiatry, Journal Year: 2025, Volume and Issue: 39(1), P. 4 - 6

Published: Jan. 1, 2025

Language: Английский