Background Several states have opted to expand Medicaid under the Patient Protection and Affordable Care Act (ACA), which offers insurance coverage to low‐income individuals up to 138% of the federal poverty level. This expansion of Medicaid to a medically vulnerable population potentially can reduce cancer outcome disparities, especially among patients with screening‐amenable cancers. The objective of the current study was to estimate the effect of Medicaid expansion on the percentage of adults from low‐income communities with screening‐amenable cancers who present with metastatic disease. Methods Using state cancer registry data linked with block group–level income data, a total of 12,760 individuals aged 30 to 64 years who were diagnosed with incident invasive breast (female), cervical, colorectal, or lung cancer from 2011 through 2016 and who were uninsured or had Medicaid insurance at the time of diagnosis were identified. This sample was probability weighted based on income to reflect potential Medicaid eligibility under the ACA's Medicaid expansion. A multivariable logistic model then was fitted to examine the independent association between the exposure (pre‐expansion [years 2011‐2013] vs postexpansion [years 2014‐2016]) and the outcome (metastatic vs nonmetastatic disease at the time of diagnosis). Results After adjusting for potential confounders, individuals who were diagnosed postexpansion were found to have 15% lower odds of having metastatic disease compared with those who were diagnosed pre‐expansion (adjusted odds ratio, 0.85; 95% confidence interval, 0.77‐0.93). As a control, a separate analysis that focused on individuals with private insurance who resided in high‐income communities found nonsignificant postexpansion (vs pre‐expansion) changes in the outcome (adjusted odds ratio, 1.02; 95% confidence interval, 0.96‐1.09). Conclusions Medicaid expansion is associated with a narrowing of a critical cancer outcome disparity in adults from low‐income communities.

Background: Disparities in the stage at diagnosis for breast cancer have been independently associated with various contextual characteristics. Understanding which combinations of these characteristics indicate highest risk, and where they are located, is critical to targeting interventions and improving outcomes for patients with breast cancer. Methods: The study included women diagnosed with invasive breast cancer between 2009 and 2018 from 680 U.S. counties participating in the Surveillance, Epidemiology, and End Results program. We used a machine learning approach called Classification and Regression Tree (CART) to identify county “phenotypes,” combinations of characteristics that predict the percentage of patients with breast cancer presenting with late-stage disease. We then mapped the phenotypes and compared their geographic distributions. These findings were further validated using an alternate machine learning approach called random forest. Results: We discovered seven phenotypes of late-stage breast cancer. Common to most phenotypes associated with high risk of late-stage diagnosis were high uninsured rate, low mammography use, high area deprivation, rurality, and high poverty. Geographically, these phenotypes were most prevalent in southern and western states, while phenotypes associated with lower percentages of late-stage diagnosis were most prevalent in the northeastern states and select metropolitan areas. Conclusions: The use of machine learning methods of CART and random forest together with geographic methods offers a promising avenue for future disparities research. Impact: Local interventions to reduce late-stage breast cancer diagnosis, such as community education and outreach programs, can use machine learning and geographic modeling approaches to tailor strategies for early detection and resource allocation.

ImportanceThe association between cancer mortality and risk factors may vary by geography. However, conventional methodological approaches rarely account for this variation.ObjectiveTo identify geographic variations in the association between risk factors and cancer mortality.Design, Setting, and ParticipantsThis geospatial cross-sectional study used county-level data from the National Center for Health Statistics for individuals who died of cancer from 2008 to 2019. Risk factor data were obtained from County Health Rankings & Roadmaps, Health Resources and Services Administration, and Centers for Disease Control and Prevention. Analyses were conducted from October 2021 to July 2022.Main Outcomes and MeasuresConventional random forest models were applied nationwide and by US region, and the geographical random forest model (accounting for local variation of association) was applied to assess associations between a wide range of risk factors and cancer mortality.ResultsThe study included 7 179 201 individuals (median age, 70-74 years; 3 409 508 women [47.5%]) who died from cancer in 3108 contiguous US counties during 2008 to 2019. The mean (SD) county-level cancer mortality rate was 177.0 (26.4) deaths per 100 000 people. On the basis of the variable importance measure, the random forest models identified multiple risk factors associated with cancer mortality, including smoking, receipt of Supplemental Nutrition Assistance Program (SNAP) benefits, and obesity. The geographical random forest model further identified risk factors that varied at the county level. For example, receipt of SNAP benefits was a high-importance factor in the Appalachian region, North and South Dakota, and Northern California; smoking was of high importance in Kentucky and Tennessee; and female-headed households were high-importance factors in North and South Dakota. Geographic areas with certain high-importance risk factors did not consistently have a corresponding high prevalence of the same risk factors.Conclusions and RelevanceIn this cross-sectional study, the associations between cancer mortality and risk factors varied by geography in a way that did not correspond strictly to risk factor prevalence. The degree to which other place-specific characteristics, observed and unobserved, modify risk factor effects should be further explored, and this work suggests that risk factor importance may be a preferable paradigm for selecting cancer control interventions compared with risk factor prevalence.