Harnessing Opportunities to Screen for Esophageal Adenocarcinoma (HOSEA)
Abstract
Esophageal adenocarcinoma (EAC) is a form of cancer of the esophagus (the swallowing tube connecting the mouth to the stomach). It has become much more common, rising 6-fold over 4 decades. Yet, EAC is still a rare cancer (approximately 3 out of 100,000 people each year), and as such, is one of the 2019 Peer Reviewed Cancer Research Program (PRCRP) Topic Areas. Screening patients at elevated risk for EAC with upper endoscopy has been endorsed by medical professional organizations. But fewer than 20% of patients with EAC underwent screening prior to their diagnosis of the cancer. A number of tools exist for predicting which patients will develop EAC. However, none are commonly used, primarily due to the burden of use. A tool that can be easily used at the point of contact with medical providers is critical, as there are multiple missed opportunities for EAC screening among individuals who develop EAC. The missed opportunity for EAC screening at the time of screening for colorectal cancer is particularly suitable for harnessing: individuals are much more commonly up to date for colorectal cancer screening (for instance, with colonoscopy), and when EAC screening with upper endoscopy is performed simultaneously with colonoscopy it is much less expensive. We envision an automated prediction tool for EAC that harnesses the electronic health record at the point of contact during opportune moments (such as at the time of scheduling colorectal cancer screening) to guide decision making and identify patients who should be offered screening for EAC. We expect that an approach using forms of artificial intelligence (e.g., machine learning) can identify predictive patterns in electronic health records that are even more accurate than the currently available tools for predicting which patients will develop EAC. In addition to developing and validating such a prediction tool using national Veterans Health Administration (VHA) data, we will assess the readiness and acceptability among health-care providers and patients of an approach to screening for EAC that harnesses use of the tool to opportune moments such as at the time of scheduling colonoscopy. Finally, we will pilot the deployment of the developed strategy at one such opportune moment in a single VHA site. If the results are as expected, we plan to scale-up implementation of such a screening strategy nationally with VHA. Implementation of such a strategy would bridge the gap between population-health screening and personalized management in a manner that minimizes its impact on payer budget and resources. This project will also serve as a roadmap for how such precision approaches to screening can be applied to other rare cancers. Veterans disproportionately have many of the important risk factors for EAC, and we have demonstrated that Veterans have a substantial gap in prevention of EAC. We propose to conduct this study using VHA national electronic health data to develop the prediction tool and pilot it for use specifically within VHA.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Mar 10, 2021
- Source ID
- W81XWH2010898
Entities
People
- Joel H Rubenstein
Organizations
- Ann Arbor VA Medical Center
- United States Army