Ophthalmic Diseases and AI: an RCT Study

NCT07154680 | Completed DMC

• 1 other identifier: 2765326471-2024-1
• Study Type: observational
• Target: 2,000
• Locations: 1 country
• Sites: 1

Brief Summary

Ophthalmic diseases are a major category of conditions affecting visual health, including but not limited to cataracts, glaucoma, retinal and choroidal diseases, and refractive errors (such as myopia, hyperopia, and astigmatism). With the advancement of technology, artificial intelligence (AI) is being increasingly applied in the field of ophthalmology. This clinical trial aims to evaluate the potential of large language models (LLMs) in ophthalmology. The main questions to be addressed are:

1. 1.Assessing the effectiveness of large language models (LLMs) in the diagnosis and treatment of ophthalmic diseases: Through randomized controlled trials (RCTs), evaluate the diagnostic and treatment effectiveness of LLMs in the field of ophthalmic diseases, exploring their potential to improve the quality and efficiency of ophthalmic care.
2. 2.Investigating the role of LLMs in medical consultations: Explore the role and effectiveness of LLMs in medical consultations for ophthalmic diseases, including their ability to provide medical advice, explain diagnostic results, and help patients understand treatment plans.
3. 3.Examining the ability of LLMs to adhere to ethical standards: Study how to ensure that LLMs comply with ethical standards and moral principles in ophthalmic medical consultations, safeguarding patient privacy and rights.
4. 4.Providing new technological support for the field of ophthalmology: Through research on the application of LLMs in ophthalmic diseases, offer new technological support and innovations to enhance the quality and efficiency of ophthalmic care.
5. 5.Exploring the differences between LLMs and ophthalmologists: By utilizing multiple large language models, compare the differences between LLMs and ophthalmologists in diagnostic outcomes, case analysis processes, and patient experiences during diagnosis and treatment.
6. 6.Evaluating the effectiveness of LLMs in ophthalmic diseases: Collect patient complaints, fundus images, doctors' diagnoses, and diagnosis times from offline doctor consultations, as well as gather AI-generated medical advice, diagnostic efficiency, and diagnostic accuracy online. Ultimately, conduct comprehensive data analysis to determine the feasibility and effectiveness of LLMs in diagnosing and treating ophthalmic diseases.

Conditions

Eye Diseases

Outcome Measures

Primary Outcomes (1)

• Large Language Model Diagnostics

  The accuracy of the large language model in diagnosing eye diseases

  1 week

Secondary Outcomes (1)

• Large Language Model Medical Assistance

  1 week

Other Outcomes (1)

• Large Language Model Medical Explanation

  1 week

Study Arms (3)

Large Language Model Diagnostics Group

Diagnostic Test: GPT-4o mini;Claude 3 Haiku;Gemini 1.5 Flash;Llama 3.1 7OB;GPT-4o;Claude 3.5 Sonnet;Gemini 1.5 Pro;Llama 3.1 4O5B

Large Language Model Medical Assistance Group

Diagnostic Test: GPT-4o mini;Claude 3 Haiku;Gemini 1.5 Flash;Llama 3.1 7OB;GPT-4o;Claude 3.5 Sonnet;Gemini 1.5 Pro;Llama 3.1 4O5B

Large Language Model Medical Explanation Team

Diagnostic Test: GPT-4o mini;Claude 3 Haiku;Gemini 1.5 Flash;Llama 3.1 7OB;GPT-4o;Claude 3.5 Sonnet;Gemini 1.5 Pro;Llama 3.1 4O5B

Interventions

GPT-4o mini;Claude 3 Haiku;Gemini 1.5 Flash;Llama 3.1 7OB;GPT-4o;Claude 3.5 Sonnet;Gemini 1.5 Pro;Llama 3.1 4O5B DIAGNOSTIC_TEST

Input all the patient's information into the large language model and process it using a pre-defined prompt.

Large Language Model Diagnostics Group; Large Language Model Medical Assistance Group; Large Language Model Medical Explanation Team

Eligibility Criteria

• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Patients going to the hospital for regular eye check-ups

You may qualify if:

• There are patient complaints

You may not qualify if:

• No patient complaints

Sponsors & Collaborators

• North Sichuan Medical College: lead
• Affiliated Hospital of North Sichuan Medical College: collaborator

Study Sites (1)

Affiliated Hospital of North Sichuan Medical College

Nanchong, Sichuan, 637000, China

Location

MeSH Terms

Conditions

Eye Diseases

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator

Study Record Dates

• First Submitted: December 29, 2024
• First Posted: September 4, 2025
• Study Start: August 15, 2024
• Primary Completion: January 15, 2025
• Study Completion: January 30, 2025
• Last Updated: September 4, 2025

Record last verified: 2025-08

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, ICF, CSR, ANALYTIC CODE

Locations

CN (1)