Key result
AI-driven patient matching identifies eligible clinical trial candidates from ~45,000 screened breast cancer patients.
Why the study?
Enrollment gaps persist in breast cancer clinical trials due to high patient volume, unstructured clinical notes, and limited research staffing, which challenge traditional manual screening.
Does an AI-driven Clinical Trial Patient Matching system improve the identification and enrollment of eligible patients, including underrepresented groups, in breast cancer trials?
Population
45,380 unique breast cancer patients across 13 oncology sites in a health network
Comparison
AI- and NLP-powered clinical trial patient matching system pre-screening
Design
Prospective observational implementation study
Authors
Loading...
AI pre-screening may aid identification of breast cancer trial candidates including underrepresented groups; leaves open effects on consent and enrollment.
Observational (n=45,380)
Yes
Does an AI-driven Clinical Trial Patient Matching system improve the identification and enrollment of eligible patients, including underrepresented groups, in breast cancer trials?
An AI-driven trial-matching system successfully identified eligible breast cancer patients, including historically underrepresented groups, though downstream barriers to consent and enrollment remained.
Liu et al. (2026) conducted an observational in High-risk hormone receptor-positive (HR+), HER2-negative early breast cancer (n=45,380). Clinical Trial Patient Matching (CTPM) system was evaluated on Identification of eligible patients and enrollment. An AI-driven Clinical Trial Patient Matching system pre-screened 45,380 breast cancer patients, identifying 263 eligible for EMBER-4 (13.8% enrolled) and 140 for DARE (22.1% enrolled).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: