Multimodal Deep Learning Model for Multi-task Diagnosis and Triage Suggestions of Ophthalmic Diseases

Development and Validation of Multimodal Deep Learning Model for Autonomous Diagnosis, Generative Reporting, and Specialist Referral in Ophthalmic Diseases: An International Multicenter Cohort Study

Accurate and comprehensive interpretation of anterior segment diseases from slit-lamp and smartphone photographs remains a clinical challenge due to the limited specificity and structure of existing Artificial Intelligence tools. The purpose of this international, multicenter clinical trial is to developed and validated an agent-based framework that integrates vision-language models and large language models to enhance the diagnostic workflow of anterior segment diseases.

Study Overview

• Status: Recruiting
• Conditions: Anterior Segment Diseases
• Intervention / Treatment: Diagnostic test: Multimodal Vision-language Model Diagnosis

• Study Type: Observational
• Enrollment (Estimated): 2000

Contacts and Locations

• Study Contact: Name: Honghua Yu; Phone Number: +8618688888422; Email: yuhonghua@gdph.org.cn

Study Locations

• China
  • Guangdong
    • Guangzhou, Guangdong, China, 510280
      • Recruiting
      • Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University
      • Contact: Honghua Yu; Phone Number: +8618688888422; Email: yuhonghua@gdph.org.cn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Probability Sample

Study Population

Individuals who have or do not have concerns related to their eyes.

Description

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.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Normal participants; Healthy individuals who have no concerns related to their eyes.	Diagnostic test: Multimodal Vision-language Model Diagnosis; Multimodal Vision-language Model for Multi-task Diagnosis and Triage Suggestions of Ophthalmic Diseases Patients presenting with complaints of anterior segment diseases first complete a slit-lamp examination or take a mobile phone eye photograph. A multimodal vision-language model uses patient-related images (such as selfies and eye exam photos) to make an intelligent diagnosis. The diagnosis is kept private. The patient then seeks medical attention and undergoes a clinical examination by an experienced clinician. A second experienced clinician then reviews the clinical diagnosis. If the diagnosis agrees, it is considered the gold standard. If there is a discrepancy in the diagnosis, the consensus between the two clinicians is used as the gold standard.
Patients with Eye-related Chief Complaints; Individuals who have specific concerns or issues related to their eyes, which they consider as the main reason for seeking medical attention or making a complaint.	Diagnostic test: Multimodal Vision-language Model Diagnosis; Multimodal Vision-language Model for Multi-task Diagnosis and Triage Suggestions of Ophthalmic Diseases Patients presenting with complaints of anterior segment diseases first complete a slit-lamp examination or take a mobile phone eye photograph. A multimodal vision-language model uses patient-related images (such as selfies and eye exam photos) to make an intelligent diagnosis. The diagnosis is kept private. The patient then seeks medical attention and undergoes a clinical examination by an experienced clinician. A second experienced clinician then reviews the clinical diagnosis. If the diagnosis agrees, it is considered the gold standard. If there is a discrepancy in the diagnosis, the consensus between the two clinicians is used as the gold standard.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic accuracy of multimodal vision-language model.	For each patient, the diagnoses generated by the multimodal vision-language model and the clinical diagnosis provided by skilled clinicians were documented and compared. Consistency between the two diagnoses indicates the program's precision in clinical practice.	from July 2025 to September 2025

Collaborators and Investigators

• Sponsor: Guangdong Provincial People's Hospital

Study record dates

Study Major Dates

• Study Start (Actual): July 28, 2025
• Primary Completion (Estimated): November 20, 2027
• Study Completion (Estimated): December 31, 2027

Study Registration Dates

• First Submitted: February 25, 2026
• First Submitted That Met QC Criteria: February 25, 2026
• First Posted (Actual): March 4, 2026

Study Record Updates

• Last Update Posted (Actual): March 5, 2026
• Last Update Submitted That Met QC Criteria: March 3, 2026
• Last Verified: March 1, 2026

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Anterior Segment Diseases
• Other Study ID Numbers: U24A20707

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No