Estimated Risk for Overactive Bladder in Native American Women: Unsupervised Machine Learning Approach.

This article focuses on estimating the risk of overactive bladder (OAB) in Native American women using an unsupervised machine learning (UML) approach. OAB, characterized by urinary urgency and frequency, is linked to significant physical, psychological, and financial burdens, yet its prevalence and risk factors in Native American women remain understudied despite this population's higher rates of obesity, diabetes mellitus (DM), smoking, and other known OAB risk factors. Using data from the 2020 CDC Behavioral Risk Factor Surveillance System (BRFSS), the study applied k-means clustering to identify risk factor patterns in age-matched White and Native American women, finding that BMI and duration of DM were key variables associated with increased OAB risk in both groups. Although the UML model fit slightly better for White women, results suggest similar risk profiles, highlighting the need for targeted screening and further research on OAB and its mental health consequences in Native American women, especially considering disparities in healthcare access and socioeconomic factors.