AI-assisted workflow enables rapid, high-fidelity breast cancer clinical trial eligibility prescreening

TL;DR

This paper presents MSK-MATCH, an AI system that automates breast cancer trial eligibility screening with high accuracy, significantly reducing manual review time and cost, thereby facilitating faster patient enrollment in clinical trials.

Contribution

The study introduces MSK-MATCH, a novel AI workflow combining large language models and knowledge bases for accurate, explainable, and efficient trial eligibility prescreening.

Findings

Achieved 98.6% accuracy in eligibility classification.

Reduced manual screening time from 20 minutes to 43 seconds.

Automated 61.9% of eligibility assessments.

Abstract

Clinical trials play an important role in cancer care and research, yet participation rates remain low. We developed MSK-MATCH (Memorial Sloan Kettering Multi-Agent Trial Coordination Hub), an AI system for automated eligibility screening from clinical text. MSK-MATCH integrates a large language model with a curated oncology trial knowledge base and retrieval-augmented architecture providing explanations for all AI predictions grounded in source text. In a retrospective dataset of 88,518 clinical documents from 731 patients across six breast cancer trials, MSK-MATCH automatically resolved 61.9% of cases and triaged 38.1% for human review. This AI-assisted workflow achieved 98.6% accuracy, 98.4% sensitivity, and 98.7% specificity for patient-level eligibility classification, matching or exceeding performance of the human-only and AI-only comparisons. For the triaged cases requiring manual review, prepopulating eligibility screens with AI-generated explanations reduced screening time from 20 minutes to 43 seconds at an average cost of $0.96 per patient-trial pair.