Quantifying Cancer Clinical Trial Eligibility Using Artificial Intelligence-Based Matching
- 1Department of Radiation Oncology, Stanford University School of Medicine
Abstract
PURPOSETo develop and validate an artificial intelligence-enabled platform that combines efficient screening with explicit eligibility logic by converting unstructured cancer trial criteria into reusable structured queries, and illustrates potential eligibility using synthetic patients.
METHODSWe downloaded actively recruiting US interventional treatment trials for advanced/metastatic breast cancer, colon cancer, and non-small cell lung cancer from ClinicalTrials.gov. Medical oncologists created 24 synthetic patient vignettes. A large language model converted trial eligibility criteria into Structured Query Language (SQL) code and patient information into structured records, enabling rule-based matching without further LLM inference. Cancer details and treatment history were considered, but not laboratory results or comorbidities. Validation included physician editing of generated eligibility code for 30 trials and independent assessments by two physicians, followed by consensus adjudication, for eligibility across ten trials. We descriptively summarized potential eligibility by trial characteristics and when varying age, ECOG performance status, sex, and ZIP code.
RESULTSOf 833 candidate trials, 746 met inclusion criteria. Performing matching for all 746 trials took a median of 0.459 seconds per patient, excluding patient-data preparation. Against physician consensus, automated matching agreed on 230/240 patient-trial pairs (95.8%; sensitivity 83.3%, specificity 100%). Across synthetic patients, potentially eligible trials ranged from 10 to 258 without geographic restrictions. Counts decreased with worse performance status and geographic restriction and were relatively stable across ages 30-90. Later-phase, randomized, and molecularly selective trials generally matched fewer vignettes.
CONCLUSIONLLM-generated SQL enables rapid, explicit rule-based screening for potential trial eligibility. Evaluation in synthetic vignettes supports feasibility, while missed matches underscore the need for further validation.
Related
- Low-Dose CT in the Age of Artificial Intelligence: Techniques, Evidence, and Clinical Impact
- Artificial Intelligence in Otolaryngology—From Demonstrating Capability to Delivering Trustworthy Clinical Impact
- Toward Precision Colorectal Cancer Screening: Integrating Clinical Risk Stratification, Molecular Biomarkers, and Artificial Intelligence
- Artificial Intelligence in Oncologic Imaging: Deep Learning, Radiomics, and Clinical Integration for Precision Cancer Diagnosis
- Clinical Translation of Artificial Intelligence in Oncology: Real-World Validation, Workflow Integration, and Precision Medicine Applications
BibTeX
@misc{goel2026quantifying,
title = {{Quantifying Cancer Clinical Trial Eligibility Using Artificial Intelligence-Based Matching}},
author = {K. P. Goel and N. J. Myall and J. Dickerson and J. L. Caswell-Jin and T. Johnson and J. E. Worth and M. F. Gensheimer},
howpublished = {medRxiv},
year = {2026},
month = jun,
doi = {10.64898/2026.06.03.26354859},
url = {https://www.medrxiv.org/content/10.64898/2026.06.03.26354859v2},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Quantifying Cancer Clinical Trial Eligibility Using Artificial Intelligence-Based Matching
AU - K. P. Goel
AU - N. J. Myall
AU - J. Dickerson
AU - J. L. Caswell-Jin
AU - T. Johnson
AU - J. E. Worth
AU - M. F. Gensheimer
PY - 2026
DA - 2026/06/03
PB - medRxiv
DO - 10.64898/2026.06.03.26354859
UR - https://www.medrxiv.org/content/10.64898/2026.06.03.26354859v2
AB - PURPOSETo develop and validate an artificial intelligence-enabled platform that combines efficient screening with explicit eligibility logic by converting unstructured cancer trial criteria into reusable structured queries, and illustrates potential eligibility using synthetic patients. METHODSWe downloaded actively recruiting US interventional treatment trials for advanced/metastatic breast cancer, colon cancer, and non-small cell lung cancer from ClinicalTrials.gov. Medical oncologists created 24 synthetic patient vignettes. A large language model converted trial eligibility criteria into Structured Query Language (SQL) code and patient information into structured records, enabling rule-based matching without further LLM inference. Cancer details and treatment history were considered, but not laboratory results or comorbidities. Validation included physician editing of generated eligibility code for 30 trials and independent assessments by two physicians, followed by consensus adjudication, for eligibility across ten trials. We descriptively summarized potential eligibility by trial characteristics and when varying age, ECOG performance status, sex, and ZIP code. RESULTSOf 833 candidate trials, 746 met inclusion criteria. Performing matching for all 746 trials took a median of 0.459 seconds per patient, excluding patient-data preparation. Against physician consensus, automated matching agreed on 230/240 patient-trial pairs (95.8%; sensitivity 83.3%, specificity 100%). Across synthetic patients, potentially eligible trials ranged from 10 to 258 without geographic restrictions. Counts decreased with worse performance status and geographic restriction and were relatively stable across ages 30-90. Later-phase, randomized, and molecularly selective trials generally matched fewer vignettes. CONCLUSIONLLM-generated SQL enables rapid, explicit rule-based screening for potential trial eligibility. Evaluation in synthetic vignettes supports feasibility, while missed matches underscore the need for further validation.
ER -