Cristian Taborda

PURPOSE: To assess the generalizability of cancer clinical trials by comparing trial enrollment with baseline cancer populations across three National Cancer Institute (NCI)–designated cancer centers and to identify institutional barriers and best practices. METHODS: We conducted a retrospective analysis (2020-2024) of three NCI-designated Comprehensive Cancer Centers using Epic electronic health records and Clinical Trial Management Systems. Baseline cancer populations were compared with enrolled patients across solid tumors and hematologic malignancies by age, race/ethnicity, language, geography, and insurance status. We additionally evaluated the impact of an automated clinical trial prescreening tool implemented at Yale Cancer Center on enrollment demographics. RESULTS: Among 311,186 patients with solid tumor and 62,988 with hematology malignancies, non–English-speaking and Medicaid-insured populations were consistently underrepresented. Vanderbilt-Ingram Cancer Center enrolled the largest cohorts (12,053 solid tumor; 2,214 hematology) and demonstrated strong rural representation (23.2% enrolled v 17.8% baseline in solid tumors) but limited enrollment of non-English speakers (0.7% v 2.3% baseline in hematology). Mays Cancer Center at UT Health San Antonio achieved the highest racial/ethnic (68.5% v 57.5% baseline) and Medicaid-insured representation (28.3% v 10.4% baseline) in hematology despite smaller volumes. Yale Cancer Center maintained strong enrollment of older adults but underrepresented young adults; implementation of automated prescreening increased young adult consent (1.2%-5.2%) and minority participation (18.2%-23.8%) in solid tumors. CONCLUSION: Persistent enrollment disparities—particularly among non–English-speaking and Medicaid populations—were observed across institutions, alongside distinct institutional strengths. Technology-enabled interventions and cross-institutional knowledge sharing targeting language, socioeconomic, and geographic barriers are critical to improving equitable trial participation in precision oncology.

PURPOSE: Cancer clinical trial enrollment remains critically low at 5%-7% of adult patients despite exponential growth in available trials. Manual patient-trial matching represents a fundamental bottleneck, whereas current artificial intelligence (AI) and machine learning patient-trial matching systems lack data standardization and compatibility across health systems. We developed and validated a semiautomated clinical trial patient matching (CTPM) tool to improve recruitment efficiency and scalability. METHODS: We created a hybrid rules–based and natural language processing (NLP)–based pipeline that automatically screens patients using structured and unstructured electronic health record data standardized to the Observational Medical Outcomes Partnership (OMOP) common data model. CTPM performance was first evaluated on one metastatic colorectal cancer (CRC) trial by comparing CTPM accuracy and efficiency to manual chart review. Following the single-trial validation, we then implemented the system across 29 clinical trials spanning multiple cancer specialties and phases. RESULTS: For the single CRC trial, CTPM achieved 94% retrospective and 88% prospective accuracy, matching gold standard clinical chart review with 100% sensitivity. Implementation reduced chart review workload 10-fold and screening time by 41% (3.1 to 1.8 minutes per chart) for those patients who did undergo review. Since September 2022, the system has screened 98,348 patients across 29 trials, identifying 825 eligible candidates and facilitating 117 patient enrollments with 9%-37% consent rates. CONCLUSION: This AI and NLP tool demonstrates improved efficiency in clinical trial recruitment by enabling research teams to focus on qualified candidates rather than exhaustive chart reviews. The OMOP-based framework supports scalability across health systems, with potential to address enrollment challenges that limit patient access to clinical trials.