The rising predictive power of LGBT identity in mental health: An analysis of variable importance.

Purpose: To assess the changing predictive importance of lesbian, gay, bisexual, and transgender (LGBT) status on mental health outcomes between 2014 and 2023.

Methods: We utilized data from the Behavioral Risk Factor Surveillance System (BRFSS) and employed two ensemble methods-random forests and gradient boosting-as well as traditional logistic regression, to analyze the predictive power of various factors, including LGBT status, on frequent mental distress. Frequent mental distress was defined as experiencing poor mental health for 14 or more days during the previous 30 days.

Results: Our analysis revealed a significant and consistent increase in the predictive importance of LGBT status on frequent mental distress across all three modeling approaches. Specifically, LGBT status consistently rose from the 8th or 13th most important predictor in 2014 to the 3rd or 5th most important in 2023, depending on the model. This trend demonstrates that SOGI has become one of the most influential factors for predicting mental health challenges in recent years.

Conclusions: These findings highlight the growing importance of sexual orientation and gender identity (SOGI) as a risk factor for mental health challenges.