Although substantial progress has been made in reducing overall cancer mortality, substantial geographic disparities in cancer mortality persist.^1,2 Traditional cancer prevention and control efforts have been targeted toward communities with a high prevalence of known cancer risk factors, presuming that a high prevalence of these factors directly translates to a higher risk of cancer.^3,4 In reality, these factors likely have a contextual, place-dependent relationship with health outcomes.⁵ Thus, understanding the geographic association between cancer mortality and risk factors is key to targeting and optimizing resources directed at cancer disparities elimination.

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.

The proportion of patients diagnosed with colorectal cancer (CRC) at age < 50 (early-onset CRC, or EOCRC) has steadily increased over the past three decades relative to the proportion of patients diagnosed at age ≥ 50 (late-onset CRC, or LOCRC), despite the reduction in CRC incidence overall. An important gap in the literature is whether EOCRC shares the same community-level risk factors as LOCRC. Thus, we sought to (1) identify disparities in the incidence rates of EOCRC and LOCRC using geospatial analysis and (2) compare the importance of community-level risk factors (racial/ethnic, health status, behavioral, clinical care, physical environmental, and socioeconomic status risk factors) in the prediction of EOCRC and LOCRC incidence rates using a random forest machine learning approach. The incidence data came from the Surveillance, Epidemiology, and End Results program (years 2000–2019). The geospatial analysis revealed large geographic variations in EOCRC and LOCRC incidence rates. For example, some regions had relatively low LOCRC and high EOCRC rates (e.g., Georgia and eastern Texas) while others had relatively high LOCRC and low EOCRC rates (e.g., Iowa and New Jersey). The random forest analysis revealed that the importance of community-level risk factors most predictive of EOCRC versus LOCRC incidence rates differed meaningfully. For example, diabetes prevalence was the most important risk factor in predicting EOCRC incidence rate, but it was a less important risk factor of LOCRC incidence rate; physical inactivity was the most important risk factor in predicting LOCRC incidence rate, but it was the fourth most important predictor for EOCRC incidence rate. Thus, our community-level analysis demonstrates the geographic variation in EOCRC burden and the distinctive set of risk factors most predictive of EOCRC.

Designing a system to solve school bus routing problems (SBRP), especially in a large school district, is very complex and expensive. One of the challenges resides in designing routes for the school buses when they have mixed loads, where each bus transports students for one or more schools at the same time to save the total number of buses required. This article aims to explore whether the algorithm originally developed for pickup and delivery problem with time windows (PDPTW) can be employed for solving mixed load SBRP. We present a PDPTW-based algorithm to address the mixed load SBRP focusing on minimizing the number of buses required. Our algorithm combines a record-to-record travel framework with three neighborhood operators, single paired insertion, swapping pairs between routes, and within route insertion, to improve solution iteratively. Results from implementing this algorithm show that our PDPTW-based algorithm is feasible for mixed load SBRP. Moreover, we found that guided strategy is better than random for permuting nodes that would be selected to relocate positions in a route or among routes. In addition, the results also show that the spatiotemporal connectivity index used in our algorithm can reduce the computation time needed for searching for solutions without affecting the quality of the solutions.