Can a proactive, structured GPT-4o interface help laypeople triage and diagnose better?
Official title: Improving AI-Assisted Medical Diagnosis and Triage by the General Public
Run by Lahore University of Management Sciences · NCT07728513 · Data updated 2026-11-12
This study tests whether a proactive, structured AI interface can help everyday people in diagnosing symptoms and deciding on next steps, compared with a standard AI chat platform.
Quick facts
| Study type | Interventional |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 220 (estimated) |
| Sponsor | Lahore University of Management Sciences Academic / other |
| Locations | 1 site (Lahore, Punjab Province) |
| Status | Recruiting |
| Started | July 1, 2026 |
| Main results expected | July 1, 2027 |
| Study ends | July 1, 2027 |
| Registry record updated | September 17, 2026 |
| Trial ID | NCT07728513 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults 18+ who are current students or administrative staff at LUMS, fluent in English, with no formal medical or healthcare training.
✕Probably not a fit
Individuals with medical training or who require clinical evaluation beyond self-assessment should not rely on AI-only triage for medical decisions.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This randomized controlled trial compares two AI interfaces for lay users: a new GPT-4o-based system that asks clinical history questions before delivering a clear diagnostic output, versus a standard LLM interface. The goal is to see if the structured approach improves diagnostic accuracy and triage suitability among non-professionals. Participants are enrolled students or staff at LUMS who are 18 or older and proficient in English, with those having formal healthcare training excluded. The study uses an interventional design with random assignment to the new interface or the control condition and focuses on how effectively each interface helps users interpret symptoms and decide on appropriate actions. Outcomes will address diagnostic accuracy, triage quality, and user experience, contributing to safer public-facing AI health tools.
Why it matters
Potential benefit: If successful, the structured interface could help non-experts better interpret symptoms and choose appropriate next steps when using AI health tools.
How similar studies have gone: Prior work has shown mixed results for lay users with standard LLMs, indicating potential for improvement with structured questioning and output.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Enrolled student or employed administrative staff at LUMS. * 18 years of age or older. * Able to read and understand English. Exclusion Criteria: * Individuals with any formal education or professional training in medicine, nursing, or any other healthcare profession.
Where it's running
-
Lahore University of Management Sciences
Lahore, Punjab Province, Pakistan Recruiting
Study contacts
- Principal investigator: Ayesha Ali, PhD — Lahore University of Management Sciences (LUMS)
- Study coordinator: Ihsan Ayyub Qazi, PhD
- Email: ihsan.qazi@lums.edu.pk
- Phone: +923233333766
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Benchmarking AI language models against tumor boards for oncology treatment decisions
This project tests whether frontier AI language models can match the treatment recommendations of multidisciplinary tumor boards for common cancers using standardized synthetic cases.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.