Analyzing Geospatial and Socioeconomic Disparities in Breast Cancer Screening Among Populations in the United States: Machine Learning Approach

• DOI: 10.2196/59882
• Publication Date: 2025-01-17T09:12:44Z
• Authors: Soheil Hashtarkhani; Yiwang Zhou; Fekede Asefa Kumsa; Shelley White-Means; David L Schwartz; Arash Shaban-Nejad
• Keywords: Breast Cancer Screening

Breast cancer screening plays a pivotal role in early detection and subsequent effective management of the disease, impacting patient outcomes survival rates. This study aims to assess breast rates nationwide United States investigate impact social determinants health on these Data mammography at census tract level for 2018 2020 were collected from Behavioral Risk Factor Surveillance System. We developed large dataset health, comprising 13 variables 72337 tracts. Spatial analysis employing Getis-Ord Gi statistics was used identify clusters high low To evaluate influence determinants, we implemented random forest model, with aim comparing its performance linear regression support vector machine models. The models evaluated using R2 root mean squared error metrics. Shapley Additive Explanations values subsequently significance direction their influence. Geospatial revealed elevated eastern northern States, while central midwestern regions exhibited lower model demonstrated superior performance, an R2=64.53 2.06 compared indicated that percentage Black population, number facilities within 10-mile radius, population least bachelor's degree most influential variables, all positively associated