Assessing the Performance of Artificial Intelligence (AI)-Augmented Electronic Health Record (EHR) Data Abstraction for Clinical Trial Patient Screening

NCT06561217 | Completed Results

• 1 other identifier: 854016
• Study Type: observational
• Target: 355
• Locations: 1 country
• Sites: 2

Brief 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.

Conditions

Cancer

Outcome Measures

Primary Outcomes (1)

• Abstracted Chart-level Accuracy

  The primary outcome measured was mean chart-level accuracy, defined as the percentage of elements identified by clinical research coordinators among all elements in the gold-standard set, measured for each chart, and averaged across all charts. Research coordinator-abstracted responses were identified as being accurate when they exactly matched with the gold-standard set. The gold-standard set was determined by 2-3 clinicians blinded to experimental arms.

  1 year

Secondary Outcomes (1)

• Efficiency of Chart-level Abstraction (in Minutes)

  1 year

Study Arms (3)

AI-alone

Other: Chart review

Human-alone

Other: Chart review

Human + AI

Other: Chart review

Interventions

Chart review OTHER

Chart review

AI-alone; Human + AI; Human-alone

Eligibility Criteria

• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

De-identified patient charts from community oncology practices, with a diagnosis of non-small cell lung cancer (NSCLC) or colorectal cancer (CRC).

You may qualify if:

• 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.

You may not qualify if:

• None.

Sponsors & Collaborators

• University of Pennsylvania: lead
• Mendel AI: collaborator

Study Sites (2)

Emory University

Atlanta, Georgia, 30307, United States

Location

University of Pennsylvania

Philadelphia, Pennsylvania, 19104, United States

Location

Related Publications (1)

• Parikh RB, Kolla L, Beothy EA, Ferrell WJ, Laventure B, Guido M, Girard A, Li Y, Dosoky KEM, Tarabishy K, Patel PS, Andalcio A, Maloney K, Mena JU, Salloum W, Chen J, Emanuel EJ. Human-AI teaming to improve accuracy and efficiency of eligibility criteria prescreening for oncology trials: a randomized evaluation trial using retrospective electronic health records. Nat Commun. 2026 Feb 3. doi: 10.1038/s41467-026-68873-8. Online ahead of print.

  PMID: 41634037 DERIVED

MeSH Terms

Conditions

Neoplasms

Results Point of Contact

• Title: Ravi B. Parikh, MD, MPP
• Organization: Emory University School of Medicine

ravi.bharat.parikh@emory.edu

(352) 422-4285

Publication Agreements

• PI is Sponsor Employee: Yes
• Restrictive Agreement: No

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: August 16, 2024
• First Posted: August 19, 2024
• Study Start: August 18, 2023
• Primary Completion: July 12, 2024
• Study Completion: July 12, 2024
• Last Updated: July 25, 2025
• Results First Posted: July 25, 2025

Record last verified: 2025-07

Data Sharing

• IPD Sharing: Will not share

Locations

US (2)