ABSTRACT
BACKGROUND: Self-rated health is a strong predictor of mortality and morbidity. Machine learning techniques may provide insights into which of the multifaceted contributors to self-rated health are key drivers in diverse groups. OBJECTIVE: We used machine learning algorithms to predict self-rated health in diverse groups in the Behavioral Risk Factor Surveillance System (BRFSS), to understand how machine learning algorithms might be used explicitly to examine drivers of self-rated health in diverse populations. DESIGN: We applied three common machine learning algorithms to predict self-rated health in the 2017 BRFSS survey, stratified by age, race/ethnicity, and sex. We replicated our process in the 2016 BRFSS survey. PARTICIPANTS: We analyzed data from 449,492 adult participants of the 2017 BRFSS survey. MAIN MEASURES: We examined area under the curve (AUC) statistics to examine model fit within each group. We used traditional logistic regression to predict self-rated health associated with features identified by machine learning models. KEY RESULTS: Each algorithm, regularized logistic regression (AUC: 0.81), random forest (AUC: 0.80), and support vector machine (AUC: 0.81), provided good model fit in the BRFSS. Predictors of self-rated health were similar by sex and race/ethnicity but differed by age. Socioeconomic features were prominent predictors of self-rated health in mid-life age groups. Income [OR: 1.70 (95% CI: 1.62-1.80)], education [OR: 2.02 (95% CI: 1.89, 2.16)], physical activity [OR: 1.52 (95% CI: 1.46-1.58)], depression [OR: 0.66 (95% CI: 0.63-0.68)], difficulty concentrating [OR: 0.62 (95% CI: 0.58-0.66)], and hypertension [OR: 0.59 (95% CI: 0.57-0.61)] all predicted the odds of excellent or very good self-rated health. CONCLUSIONS: Our analysis of BRFSS data show social determinants of health are prominent predictors of self-rated health in mid-life. Our work may demonstrate promising practices for using machine learning to advance health equity.
Subject(s)
Health Equity , Adult , Algorithms , Behavioral Risk Factor Surveillance System , Humans , Logistic Models , Machine LearningABSTRACT
INTRODUCTION: Financial hardship is associated with coronary heart disease risk factors, and may disproportionately affect some African American groups. This study examines whether stress because of financial hardship is associated with incident coronary heart disease in African Americans. METHODS: The Jackson Heart Study is a longitudinal cohort study of cardiovascular disease risks in African Americans in the Jackson, Mississippi metropolitan statistical area. Participant enrollment began in 2000. Analyses were performed in 2017 and included adjudicated endpoints through December 2012. Financial stress was assessed from the Jackson Heart Study Weekly Stress Inventory and categorized into four levels: (1) did not experience financial stress, (2) no stress, (3) mild stress, and (4) moderate to high stress. Incident coronary heart disease was defined as the first event of definite or probable myocardial infarction, definite fatal myocardial infarction, definite fatal coronary heart disease, or cardiac procedure. There were 2,256 individuals in this analysis. RESULTS: Participants with moderate to high (versus no) financial stress were more likely to have incident coronary heart disease events after controlling for demographics, SES, access to care, and traditional clinical risk factors (hazard ratio=2.42, 95% CI=1.13, 5.17). The association between financial stress and coronary heart disease was no longer statistically significant in a model adjusting for three specific risk factors: depression, smoking status, and diabetes (hazard ratio=1.99, 95% CI=0.91, 4.39). CONCLUSIONS: Financial stress may be an unrecognized risk factor for coronary heart disease for African Americans. Additional research should examine these associations in intervention studies that address perceived stress, in addition to other coronary heart disease risk factors, in patients experiencing financial stress.
