Review of cohort diversity in the development and validation of cancer risk assessment models.

Abstract

e18570 Background: Multiple validated models have been proposed to quantify an individual's lifetime risk of breast and colon cancer. However, an evaluation of the race and ethnicity of the cohorts studied in the development and validation of each of these models has not been reviewed. Predicting cancer risks accurately in Black, Indigenous and People of Color (BIPOC) can be crucial in helping to reduce cancer mortality rates and improving access to preventative care for these individuals. Methods: A literature search was conducted to identify published development and validation studies for the following cancer risk assessment models: Breast Cancer Surveillance Consortium (BCSC) Risk Calculator, Tyrer-Cuzick, Gail, Claus, CanRisk/BOADICEA, BRCAPRO and MMRPRO. Articles included were identified through review of a number of electronic databases and websites for the cancer risk prediction models. Authors were contacted for data not readily available through literature search. Results: A total of 15 development studies and 19 validation studies of the cancer risk prediction models were reviewed for the seven models listed above. Out of the 19 validation studies, seven were internal and twelve were external validation studies. 80% (12/15) of development studies and 68% (13/19) of validation studies did not include information on racial and ethnic composition of the cohorts. After obtaining additional information from authors, 53% (8/15) of the development studies were conducted solely in non-Hispanic White (NHW) cohort. The development cohorts ranged from 50%-100% NHW, 0%-7% non-Hispanic Black (NHB), 0%-8% Hispanic/Latinx, 0%-3% Asian and 0%-1% Indigenous participants. 58% (7/12) of external validation studies included ethnically and racially diverse populations compared to 14% (1/7) of internal validation studies. The BCBS, Gail, BRCAPRO and MMRPRO models were the only models with external validation studies conducted in ethnically or racially diverse populations. Overall, the model that had the most diverse cohort for its development and internal validation studies was the BCBS with 70% NHW, 6.7% NHB, 7.5% Hispanic/Latinx, 2.7% Asian, 0.8% Indigenous and 11.5% mixed/other ethnicities. Conclusions: The majority of the models reviewed did not have ethnically or racially diverse populations in their development and validation cohorts. Awareness of the under-representation of ethnically and racially diverse populations in these models is an important precaution for extrapolating data when using these models in medical decision making for BIPOC individuals. Although several barriers exist for participation of BIPOC individuals in clinical studies, these findings highlight the critical, yet unmet need for the development and use of appropriate cancer risk models in racially and ethnically diverse populations as a means to reduce health-related disparities.