A Multimodal AI Agent for Ophthalmic Clinical Decision Support

NCT07401459 | Not Yet Recruiting

• 1 other identifier: PolyU-IRB-2025-001
• Study Type: interventional
• Target: 300
• Locations: 1 country
• Sites: 1

Brief Summary

This study is a multicenter randomized controlled trial evaluating the effectiveness and safety of EyeAgent, a multimodal artificial intelligence (AI) agent designed to assist ophthalmologists in clinical decision-making. Participants will be recruited from ophthalmology clinics and hospitals in Hong Kong and mainland China. The AI agent acts as a digital co-pilot, analyzing patient images and clinical history to provide diagnostic and management recommendations. The trial aims to determine whether the use of the AI agent improves diagnostic accuracy, treatment decision-making performance, report generation, workflow efficiency, and user satisfaction compared to standard clinical practice.

Conditions

Ophthalmology; Large Language Models; AI Agent; Eye Disease; Retinal Disease

Keywords

medical AI agent; large language model; ophthalmology; tool integration; clinical decision support; real world study

Outcome Measures

Primary Outcomes (2)

• Diagnostic accuracy rate

  Proportion of diagnoses consistent with a reference expert panel.

  Immediately after the intervention.

• Rate of inappropriate treatment decisions

  The frequency of treatment recommendations (e.g., injection, laser therapy, or observation) that deviate from clinical guidelines as determined by the senior expert panel gold standard. Expert adjudication is conducted post-hoc after the enrollment phase concludes.

  Immediately after the intervention.

Secondary Outcomes (4)

• Report quality

  Within 1 month after enrollment.

• Clinician confidence

  Immediately after the intervention.

• Workflow efficiency

  During the index diagnostic session.

• Satisfaction and usability

  At the end of each clinician's participation period, approximately 2 months.

Study Arms (2)

AI-assisted care arm

EXPERIMENTAL

Clinicians perform report generation, diagnosis, and treatment planning with support from the EyeAgent system.

Device: EyeAgent AI system

Standard care arm

NO INTERVENTION

Clinicians provide routine ophthalmic care without support from the EyeAgent system.

Interventions

EyeAgent AI system DEVICE

EyeAgent is a multimodal AI agent assistant for ophthalmology that integrates imaging, electronic health records, and curated clinical knowledge. In this arm, EyeAgent supports clinicians in clinical consultation, including report generation, diagnostic interpretation, and treatment planning.

AI-assisted care arm

Eligibility Criteria

• Age: 6 Years - 75 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)

You may qualify if:

• Outpatient participants aged 6 to 75 years.
• Participants who undergo ophthalmic examinations for medical purposes during the study period.
• Participants who can produce clear ophthalmic images in both eyes.
• Agree to participate in this study with written informed consent:
• Participants aged 18 years or older provide their own consent.
• Participants aged 6-17 years require consent from a parent or legal guardian.

You may not qualify if:

• Participants who are reluctant to participate in this study.
• Participants presenting with acute or emergency ocular conditions requiring immediate intervention.
• Participants with poor quality of ophthalmic images, including blurriness, artifacts, underexposure, or overexposure.
• Other unsuitable reasons determined by the evaluators.

Sponsors & Collaborators

• The Hong Kong Polytechnic University: lead

Study Sites (1)

The Hong Kong Polytechnic University

Hong Kong, China

Location

MeSH Terms

Conditions

Eye Diseases; Retinal Diseases

Study Officials

• Mingguang He

  The Hong Kong Polytechnic University

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Xiaolan Chen

CONTACT

+85295822773; yuewy.wu@connect.polyu.hk

Danli Shi, Dr

CONTACT

danli.shi@polyu.edu.hk

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: DOUBLE
• Who Masked: PARTICIPANT, OUTCOMES ASSESSOR
• Purpose: OTHER
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: November 17, 2025
• First Posted: February 10, 2026
• Study Start: March 1, 2026
• Primary Completion (Estimated): October 31, 2026
• Study Completion (Estimated): December 31, 2026
• Last Updated: February 23, 2026

Record last verified: 2025-09

Locations

CN (1)