A Bayesian mixture model approach to examining neighbourhood social determinants of health in endometrial cancer care in Massachusetts
研究使用贝叶斯混合模型识别马萨诸塞州社区健康社会决定因素的五个特征类型，并分析它们对子宫内膜癌患者护理的影响，发现不同社区类型患者的护理质量存在差异。
Many studies examine social determinants of health (SDoH) in isolation, overlooking their interconnected nature. We used a multifactorial approach to construct a neighbourhood-level measure that explores how SDoH jointly impact care received for endometrial cancer (EC) patients in Massachusetts (MA). Using 2015-2019 American Community Survey data, we applied a Bayesian multivariate Bernoulli mixture model to identify MA neighbourhoods with similar SDoH characteristics. Five neighbourhood SDoH (NSDoH) profiles were derived and characterized: (1) advantaged non-Hispanic White; (2) disadvantaged racially/ethnically diverse, more renter-occupied housing with limited English proficiency; (3) working class, lower educational attainment; (4) racially/ethnically diverse and greater economic security and educational attainment; and (5) racially/ethnically diverse, more renter-occupied housing with limited English proficiency. We assigned these profiles to EC patients in the Massachusetts Cancer Registry and used them as the main exposure in a Bayesian logistic regression, adjusting for sociodemographic and clinical characteristics. NSDoH profiles were not associated with optimal care; however, patients in all other profiles had lower odds compared to Profile 1. Our findings demonstrate how a flexible model-based clustering approach captures the multidimensional nature of NSDoH in an interpretable way and may support targeted public health interventions based on neighbourhood-specific social factors to improve healthcare delivery.