Manual Versus AI-Assisted Clinical Trial Screening Using Large-Language Models

Part of paid clinical trials in Boston, Massachusetts.

Sponsor
Brigham and Women's Hospital
Study ID
NCT06588452
Status
Recruiting

Conditions

  • Comparing Manual and AI Patient Screening in Heart Failure

Eligibility Criteria

Sex
ALL
Age
18 Years - 90 Years
Healthy Volunteers
Accepted

Interventions

  • RECTIFIER - a generative artificial intelligence screening tool — OTHER
    RECTIFIER is a large-language model based, generative artificial intelligence-enabled inclusion and exclusion criteria assessment tool.
  • Manual clinical trial screening by study staff — OTHER
    The current gold standard - study staff manually review potentially eligible patients through chart review.

Study Details

A prospective randomized controlled trial comparing manual review and AI screening for patient eligibility determination and enrollments. A structured query will identify potentially eligible patients from the Mass General Brigham Electronic Data Warehouse (EDW), who will then be randomized into either the manual review arm or the AI-assisted review arm.

Key Dates

Start date
Mar 4, 2024
Status verified
Sep 2024
Primary completion
Sep 13, 2024
Completion
Sep 13, 2024

Study Design

Enrollment
4,500 participants (estimated)

Arms

  • Arm: Manual Review Arm
    Study staff manually reviews patient eligibility.
  • Arm: Artificial Intelligence (AI) Review Arm
    AI screens for eligibility, followed by an abbreviated final review by study staff.

Primary Outcome Measure

Determine study eligibility, analyzed using a survival analysis framework, specifically the Fine-Gray subdistribution hazards model, to account for competing risks. [ Time Frame: Through study completion, an average of 6 months ]

Central Contacts

Locations (1)

FacilityCityStateZIPSite coordinators
Brigham and Women's HospitalBostonMassachusetts02115
Alexander J Blood, MD, MSc
617-732-7144

Find similar trials in Boston, MA