Mediators of racial and ethnic inequities in clinical trial participation among patients with cancer, 2011-2023

Abstract

Background: Although racially and ethnically minoritized populations are less likely to participate in cancer trials, it is unknown whether social determinants of health (SDOH) explain these inequities. Here we identify SDOH factors that contribute to racial and ethnic inequities in clinical trial participation among patients with 22 common cancers.

Methods: This retrospective cohort study used electronic health record data (2011-2023) linked to neighborhood (US Census tract) data from multiple sources. Patients were followed from diagnosis to clinical study drug receipt (proxy for trial participation), death, or last recorded activity. Associations were assessed using Cox proportional hazards models adjusted for clinical factors (year of diagnosis, age, sex, performance status, disease stage, cancer type). To elucidate which area-level SDOH underlie racial and ethnic inequities, mediation analysis was performed using nonlinear multiple additive regression tree models.

Results: This study included 250 105 patients (64.7% non-Latinx White, 8.9% non-Latinx Black, 5.2% Latinx). Black and Latinx patients were more likely to live in economically or socially marginalized areas (eg, disproportionately minoritized [measure of segregation], limited English proficiency, low vehicle ownership) than White patients. Black (3.7%; hazard ratio = 0.55, 95% confidence interval [CI] = 0.52 to 0.60) and Latinx patients (4.4%; hazard ratio = 0.63, 95% CI = 0.58 to 0.69) were less likely to participate in trials than White patients (6.3%). Fewer patients in economically or socially marginalized neighborhoods participated in trials. Mediators explained 62.2% (95% CI = 49.5% to 74.8%) of participation inequities between Black and White patients; area-level SDOH-including segregation (29.9%, 95% CI = 21.2% to 38.6%) and vehicle ownership (11.6%, 95% CI = 7.0% to 16.1%)-were the most important mediators. Similarly, Latinx-White participation inequities were mediated (65.1%, 95% CI = 49.8% to 80.3%) by area-level SDOH, such as segregation (39.8%, 95% CI = 28.3% to 51.3%), limited English proficiency (11.6%, 95% CI = 2.8% to 20.4%), and vehicle ownership (9.6%, 95% CI = 5.8% to 13.5%).

Conclusions: To improve racial and ethnic diversity in cancer trials, efforts to address barriers related to adverse neighborhood SDOH factors are necessary.

Figure 1.

Kaplan-Meier estimates of clinical trial participation, by race and ethnicity. Patients were followed up from index diagnosis until clinical trial participation, last confirmed activity, or end of the study period (December 2023). The index date was defined as initial, advanced, or metastatic diagnosis (depending on the specific cancer diagnosis) (see Supplementary Table 2, available online). Clinical trial participation was defined as documented clinical study drug receipt during cancer treatment (line of therapy). Race and ethnicity were categorized as non-Latinx White (referred to as “White”), non-Latinx Black (“Black”), Latinx, or other or unknown (“including groups with insufficient data for reliable reporting, such as Asian, Pacific Islander, and Indigenous persons). Although race/ethnicity values in electronic health records likely reflect self-reported assignments by patients, it is unknown whether these values are self-reported, staff reported, or clinician reported.

Figure 2.

Trends in clinical trial participation among patients with cancer, by race and ethnicity. Clinical trial participation within 365 days, accounting for differences in follow-up. Patients were followed up from index diagnosis until trial participation, last confirmed activity, or the end of the study period (December 2023). Index diagnosis was defined as initial, advanced, or metastatic diagnosis, depending on cancer type (see Supplementary Table 2, available online). Clinical trial participation was defined as documented clinical study drug receipt during cancer treatment (line of therapy). Race and ethnicity were categorized as non-Latinx White (referred to as “White”), non-Latinx Black (“Black”), Latinx, or other or unknown (including groups with insufficient data for reliable reporting, such as Asian, Pacific Islander, and Indigenous persons). Although race and ethnicity values in electronic health records likely reflect self-reported assignments by patients, it is unknown whether these values are self-reported, staff reported, or clinician reported.