AI that reads slit‑lamp and smartphone photos to diagnose and triage anterior eye conditions
Development and Validation of Multimodal Deep Learning Model for Autonomous Diagnosis, Generative Reporting, and Specialist Referral in Ophthalmic Diseases: An International Multicenter Cohort Study
This study will test an AI that uses slit‑lamp and smartphone photos to diagnose and suggest next steps for people with anterior segment eye problems and for volunteers without eye concerns.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 2000 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Guangdong Provincial People's Hospital Academic / other |
| Locations | 1 site (Guangzhou, Guangdong) |
| Trial ID | NCT07447973 on ClinicalTrials.gov |
What this trial studies
This observational, multicenter effort will develop and validate an agent‑based framework that combines vision‑language models and large language models to support diagnosis and triage of anterior segment eye diseases. Participants with and without eye complaints will provide slit‑lamp and smartphone photographs alongside routine clinical data to train and validate the model. The AI's multi‑task outputs (diagnoses and triage suggestions) will be compared against clinical diagnoses and documented workflows. The project is coordinated at Guangdong Provincial People's Hospital and Southern Medical University with bilingual (Chinese/English) enrolment.
Who should consider this trial
Good fit: Ideal candidates are adults who can give informed consent, read Chinese or English, and either have specific anterior eye complaints or have no eye concerns and can provide the required photos and clinical data.
Not a fit: People who cannot provide complete clinical data, are too medically unstable to participate safely, do not speak Chinese or English, or who have eye conditions outside the anterior segment may not benefit from this intervention.
Why it matters
Potential benefit: If successful, the tool could speed up diagnosis, improve diagnostic accuracy, and help guide appropriate next steps for people with front‑of‑eye conditions using clinic or phone photos.
How similar studies have performed: AI has shown strong results for retinal imaging and some anterior segment tasks, but combining vision‑language models with large language models for multi‑task diagnosis and triage is a relatively novel approach.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: 1. Informed consent obtained; 2. Participants should be sufficiently able to read, write, and understand Chinese or English; 3. For normal participants: individuals should have no concerns related to their eyes. 4. For participants with eye-related chief complaints: individuals should have specific concerns or issues related to their eyes. Exclusion Criteria: 1. Incomplete clinical data to support final diagnosis; 2. Patients who, in the opinion of the attending physician or clinical study staff, are too medically unstable to participate in the study safely.
Where this trial is running
Guangzhou, Guangdong
- Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University — Guangzhou, Guangdong, China (Recruiting)
Study contacts
- Study coordinator: Honghua Yu
- Email: yuhonghua@gdph.org.cn
- Phone: +8618688888422
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.