Use of artificial intelligence for cancer clinical trial enrollment: a systematic review and meta-analysis
Problem
Identifying eligible patients for cancer clinical trials is a bottleneck; AI tools were assessed for their predictive accuracy in trial enrollment.
Why it matters
Faster, accurate trial matching speeds cancer research and patient access to experimental treatments.
What the AI did
A systematic review and meta-analysis of 10 articles (>50,000 patients, 19 datasets) evaluated AI actively used in trial enrollment, pooling accuracy, sensitivity, specificity, PPV and NPV via a hierarchical summary ROC model.
Results
Accuracy, sensitivity, and specificity exceeded 80% in all but 1 included study (10 articles, >50,000 patients, 19 datasets)
Impact
Pooled evidence indicates AI can identify trial-eligible patients with over 80% accuracy across studies.
Record
| Venue | JNCI Journal of the National Cancer Institute |
|---|---|
| Published | 2023 |
| Work type | review |
| Authors | Ronald Chow, Julie Midroni, Jagdeep Kaur, Gabriel Boldt, Geoffrey Liu, Lawson Eng, Fei‐Fei Liu, Benjamin Haibe‐Kains et al. |
| Citations | 64 (OpenAlex, at import time) |
| References | 32 |
| Model or method | not stated in source |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1093/jnci/djad013 |
| Open access | bronze |
| Keywords | artificial intelligence, clinical trials, patient eligibility, meta-analysis, cancer |
Importance rating
significant — thousands to millions affected
Trial enrollment bottleneck slows cancer research and patient access to experimental treatments; pooled evidence across >50,000 patients shows AI screening with >80% accuracy, benefiting an entire research field.