Eliminating Algorithmic Racial Bias in Clinical Decision Support Algorithms: Use Cases from the Veterans Health Administration.

The Veterans Health Administration uses equity- and evidence-based principles to examine, correct, and eliminate use of potentially biased clinical equations and predictive models. We discuss the processes, successes, challenges, and next steps in four examples. We detail elimination of the race modifier for estimated kidney function and discuss steps to achieve more equitable pulmonary function testing measurement. We detail the use of equity lenses in two predictive clinical modeling tools: Stratification Tool for Opioid Risk Mitigation (STORM) and Care Assessment Need (CAN) predictive models. We conclude with consideration of ways to advance racial health equity in clinical decision support algorithms.

The Veteran-Initiated Electronic Care Coordination: A Multisite Initiative to Promote and Evaluate Consumer-Mediated Health Information Exchange.

INTRODUCTION: Information continuity is critical to person-centered care when patients receive care from multiple healthcare systems. Patients can access their electronic health record data through patient portals to facilitate information exchange. This pilot was developed to improve care continuity for rural Veterans by (1) promoting the use of the Department of Veterans Affairs (VA) patient portal to share health information with non-VA providers, and (2) evaluating the impact of health information sharing at a community appointment. MATERIALS AND METHODS: Veterans from nine VA healthcare systems were trained to access and share their VA Continuity of Care Document (CCD) with their non-VA providers. Patients and non-VA providers completed surveys on their experiences. RESULTS: Participants (n = 620) were primarily older, white, and Vietnam era Veterans. After training, 78% reported the CCD would help them be more involved in their healthcare and 86% planned to share it regularly with non-VA providers. Veterans (n = 256) then attended 277 community appointments. Provider responses from these appointments (n = 133) indicated they were confident in the accuracy of the information (97%) and wanted to continue to receive the CCD (96%). Ninety percent of providers reported the CCD improved their ability to have an accurate medication list and helped them make medication treatment decisions. Fifty percent reported they did not order a laboratory test or another procedure because of information available in the CCD. CONCLUSIONS: This pilot demonstrates feasibility and value of patient access to a CCD to facilitate information sharing between VA and non-VA providers. Outreach and targeted education are needed to promote consumer-mediated health information exchange.

Increasing colorectal cancer screening in an overdue population: participation and cost impacts of adding telephone calls to a FIT mailing program.

Many people who live in rural areas face distance barriers to colonoscopy. Our previous study demonstrated the utility of mailing fecal immunochemical tests (FIT) to average risk patients overdue for colorectal cancer (CRC screening). The aims of this study were to determine if introductory and reminder telephone calls would increase the proportion of returned FITs as well as to compare costs. Average risk patients overdue for CRC screening received a high intensity intervention (HII), which included an introductory telephone call to see if they were interested in taking a FIT prior to mailing the test out and reminder phone calls if the FIT was not returned. This HII group was compared to our previous low intensity intervention (LII) where a FIT was mailed to a similar group of veterans with no telephone contact. While a higher proportion of eligible respondents returned FITs in the LII (92 vs. 45 %), there was a much higher proportion of FITs returned out of those mailed in the HII (85 vs. 14 %). The fewer wasted FITs in the HII led to it having lower cost per FIT returned ($27.43 vs. $44.86). Given that either intervention is a feasible approach for patients overdue for CRC screening, health care providers should consider offering FITs using a home-based mailing program along with other evidence-based CRC screening options to average risk patients. Factors such as location, patient population, FIT cost and reimbursement, and personnel costs need to be considered when deciding the most effective way to implement FIT screening.

Evaluation of a home-based colorectal cancer screening intervention in a rural state.

PURPOSE: Distance from health care facilities can be a barrier to colorectal cancer (CRC) screening, especially for colonoscopy. Alternatively, an improved at-home stool-based screening tool, the fecal immunochemical test (FIT), requires only a single sample and has a better sensitivity-specificity balance compared to traditional guaiac fecal occult blood tests. Our objective was to determine if FITs mailed to asymptomatic, average-risk patients overdue for screening resulted in higher screening rates versus mailing educational materials alone or no intervention (ie, usual care). METHODS: Veterans ages 51-64, asymptomatic, at average risk for CRC, overdue for screening and in a veterans administration (VA) catchment area covering a large rural population were randomly assigned to 3 groups: (1) education only (Ed) group: mailed CRC educational materials and a survey of screening history and preferences (N = 499); (2) FIT group: mailed the FIT, plus educational materials and survey (N = 500); and (3) usual care (UC) group: received no mailings (N = 500). FINDINGS: At 6 months postintervention, 21% of the FIT group had received CRC screening by any method compared to 6% of the Ed group (and 6% of the UC group) (P < .0001). Of the 105 respondents from the FIT group, 71 (68%) were eligible to take the FIT. Of those, 64 (90%) completed the FIT and 8 (12%) tested positive. CONCLUSIONS: This low-intensity intervention of mailing FITs to average risk patients overdue for screening resulted in a significantly higher screening rate than educational materials alone or usual care, and may be of particular interest in rural areas.