N/A
Completed N=355
Assessing the Performance of Artificial Intelligence (AI)-Augmented Electronic Health Record (EHR) Data Abstraction for Clinical Trial Patient Screening
Source: ClinicalTrials.gov NCT06561217 ↗Enrolled (actual)
355
Serious AEs
—
Results posted
Jul 2025
Primary outcomePrimary: Abstracted Chart-level Accuracy — 76.10; 71.48; 59.92 % of elements correctly abstracted — p=<0.001
Summary
Identifying eligible patients is a key process in the clinical trial enterprise. Currently, this process relies on time-intensive manual chart review, creating a rate-limiting step for trial participation. The integration of AI technology into the trial screening process has potential to improve participation rates. This study aims to assess the performance (accuracy, efficiency) of AI-augmented patient identification and inform optimal integration into clinical research screening processes.
Outcome Measures
| Outcome | Result | p-value |
|---|---|---|
| PRIMARY Abstracted Chart-level Accuracy |
76.10; 71.48; 59.92 | <0.001 sig |
| SECONDARY Efficiency of Chart-level Abstraction (in Minutes) |
32.12; 31.75 | 0.513 |
Eligibility Criteria
Inclusion Criteria
- Diagnosis of colorectal or non-small cell lung cancer.
- A minimum of 5 patient documents in the Mendel database.
- Most recent document was within 5 years from the time of data extraction.
Exclusion Criteria
- None.
Data sourced from ClinicalTrials.gov (NCT06561217). Outcome figures and adverse-event rates are extracted automatically from the registry's posted results and are provided for clinician reference, not as a substitute for the primary publication. Informational only — not medical advice.