Ophthalmic AI-Assisted Medical Decision-Making

A Study on Ophthalmic Multimodal AI-Assisted Medical Decision-Making Based on Imaging and Electronic Medical Record Data

This is a multi-center, prospective clinical study designed to evaluate the application and effectiveness of an AI-assisted medical decision support system, leveraging multimodal data fusion, in ophthalmic clinical practice.

Study Overview

• Status: Recruiting
• Conditions: Ocular Diseases
• Intervention / Treatment: Combination product: AI-associated strategy

Detailed Description

Visual impairments significantly affect an individual's quality of life. Early screening, diagnosis, and treatment of ocular diseases are crucial for preventing the onset and progression of vision disorders. In clinical practice, ophthalmologists often need to integrate a wide range of patient data, including demographic information, medical history, biochemical markers such as blood glucose and lipid levels, risk factors, as well as various ophthalmic data, such as fundus images, OCT scans, and visual field tests, to make an accurate diagnosis and develop an appropriate treatment plan.

In an era where precision and personalized medicine are at the forefront of healthcare, the early detection and diagnosis of eye diseases, as well as the selection of suitable diagnostic and therapeutic strategies at different stages of the disease, have become significant challenges in clinical settings. Recent advancements in medical imaging and analysis techniques have greatly enhanced the accuracy and effectiveness of ocular disease diagnosis.

This study aims to develop an ophthalmic artificial intelligence-assisted decision-making system by integrating multimodal data from imaging and electronic medical records, in combination with deep learning techniques. The objective is to improve diagnostic accuracy, streamline clinical workflows, and provide more personalized treatment options for patients. Ultimately, this system seeks to enhance treatment outcomes and improve the overall quality of life for patients suffering from ocular diseases.

• Study Type: Interventional
• Enrollment (Estimated): 100000
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Lan Wang, MD; Phone Number: +86-0577-85397527; Email: wl2832300533@163.com

Study Locations

• China
  • Guangdong
    • Zhuhai, Guangdong, China
      • Recruiting
      • ZhuHai Hospital
      • Contact: Bingzhou Li; Phone Number: +86-0756-2222569; Email: mr_jerry_99@163.com
  • Zhejiang
    • Wenzhou, Zhejiang, China, 325000
      • Recruiting
      • Second Affiliated Hospital of Wenzhou Medical University
      • Contact: Sian Liu, PhD.; Phone Number: +86-0577-88002888; Email: liusan@mail3.sysu.edu.cn
    • Wenzhou, Zhejiang, China, 325000
      • Recruiting
      • First Affiliated Hospital of Wenzhou Medical University
      • Contact: Cheng Tang, MD; Phone Number: +86-0577-55579999; Email: c249325687@163.com
    • Wenzhou, Zhejiang, China
      • Recruiting
      • The Eye Hospital of Wenzhou Medical University
      • Contact: Lan Wang, MD; Phone Number: +86-0577-85397527; Email: wl2832300533@163.com
      • Principal Investigator: Kang Zhang, PhD.
• Macau
  • Macau, Macau
    • Recruiting
    • Macau University of Science and Technology Hospital
    • Contact: Yang Liu, MD; Phone Number: +853-2882-1838; Email: liuyang.macau@gmail.com

Participation Criteria

Eligibility Criteria

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

Description

Inclusion Criteria:

1. Age Criteria: No age restrictions apply for inclusion in the study.
2. Ophthalmic Disease Diagnosis: Eligible patients must have a diagnosis of one or more ophthalmic conditions, with the diagnosis confirmed by a qualified ophthalmologist.
3. Imaging and Clinical Data Requirements: Patients must be able to provide complete ophthalmic imaging data and electronic medical records (EMR) that are comprehensive and accessible for the purposes of the study.
4. Informed Consent: All patients, or their legal representatives in the case of minors or individuals unable to provide informed consent, must sign a consent form that clearly outlines the study's objectives, procedures, potential risks and discomforts, data usage, and the rights and responsibilities of participants. In the case of minors or those unable to consent, informed consent must be obtained from the patient's legal guardian.
5. Treatment Adherence: Participants must demonstrate the ability to understand and adhere to the study's requirements, including compliance with follow-up visits, examination schedules, and treatment recommendations. Patients must agree to participate in regular assessments and data collection, including imaging exams, laboratory tests, and follow-up evaluations as required by the study protocol.
6. Clinical Physician Assessment: The attending physician must determine that the patient meets all inclusion criteria and has the capacity to comply with the necessary treatment, diagnostic tests, and follow-up protocols throughout the study duration.

Exclusion Criteria:

1. Acute or Severe Ocular Diseases: Patients with acute ocular conditions requiring immediate medical intervention, which necessitate exclusion from interventional studies due to the urgency of their treatment.
2. Serious Systemic Diseases: Patients with serious systemic illnesses that may interfere with the treatment of ocular diseases, impact the effectiveness of the intervention, or complicate the interpretation of study outcomes.
3. Prior Exposure to Study Interventions: Patients who have previously undergone the intervention being studied or participated in other experimental treatments within ongoing clinical trials, as this may introduce bias or confound the study results.
4. Incomplete Imaging or Clinical Data: Patients who are unable to provide complete or adequate ophthalmic imaging data or lack a comprehensive electronic medical record (EMR), which are essential for the integrity of the study data.
5. Pregnancy or Lactation: Pregnant or breastfeeding women, for whom there may be potential risks associated with ocular treatment or imaging procedures. Such cases will be evaluated on an individual basis to ensure patient safety.
6. Mental Health or Cognitive Impairment: Patients diagnosed with significant mental health disorders or cognitive impairments that prevent them from fully understanding the nature and risks of the study, or from complying with the treatment regimen and follow-up procedures.
7. Drug Allergies or Severe Reactions: Patients with known allergies or severe adverse reactions to any medications or ophthalmic treatments likely to be used during the study, which could pose a health risk to the patient.
8. Current Participation in Other Clinical Trials: Patients who are concurrently involved in other interventional clinical trials (especially those related to ophthalmology), as this may lead to conflicting treatments or interfere with the assessment of the study's outcomes.
9. Inability to Comply with Follow-up Requirements: Patients who, due to logistical, health-related, or personal factors, are unable to comply with the required follow-up visits, treatment regimens, or data collection, which are essential for the study's longitudinal analysis.
10. Other Clinical Exclusions: Patients whose participation, based on the clinical judgment of the treating physician, may not be in their best interest due to their health condition or other factors, or who may experience adverse outcomes from participating in the study.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Other
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: AI-assisted medical decision-making; Patients in the intervention group will receive AI-assisted medical decision-making based on multimodal data.	Combination product: AI-associated strategy; The intervention in this study involves an AI system that leverages multimodal data fusion to support the clinical decision-making and evaluation of ophthalmic diseases. Patients in the intervention group will undergo standard ophthalmic examinations, with clinical decisions guided by the recommendations generated by the AI system. In contrast, patients in the control group will receive only standard ophthalmic examinations and treatment, without the support of AI-assisted decision-making tools.
No Intervention: Traditional medical decision-making; Patients in the control group will receive traditional medical decision-making, where treatment and diagnostic decisions are made solely by the attending physician based on clinical judgment, without the support of AI-assisted system.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Area Under the Curve (AUC)	AUC of the ROC curve, used to quantify diagnostic accuracy. No unit (a ratio or percentage, typically expressed as a number between 0 and 1).	2 years
Sensitivity	Sensitivity (also called True Positive Rate) is a measure of how well a model identifies positive instances. It is defined as the proportion of actual positive cases correctly identified by the model. No unit (a ratio or percentage, typically expressed as a percentage).	2 years
Specificity	Specificity (also called True Negative Rate) measures the proportion of actual negative cases correctly identified by the model. No unit (a ratio or percentage, typically expressed as a percentage).	2 years
Accuracy	Accuracy measures the proportion of all correct predictions (true positives and true negatives) out of the total number of cases evaluated by the model. No unit (a ratio or percentage, typically expressed as a percentage).	2 years
False Positive Rate	False Positive Rate (FPR) measures the proportion of actual negative cases that are incorrectly identified as positive by the model. No unit (a ratio or percentage, typically expressed as a percentage).	2 years
False Negative Rate	False Negative Rate (FNR) measures the proportion of actual positive cases that are incorrectly identified as negative by the model. No unit (a ratio or percentage, typically expressed as a percentage).	2 years
Postoperative Complication Rate	Percentage (%) of patients experiencing postoperative complications.	2 years
Recurrence Risk Rate	Percentage (%) of patients experiencing recurrence during the follow-up period.	2 years
Survival Rate	Percentage (%) of patients alive, calculated using Kaplan-Meier survival curves.	2 years

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
System Usability Score	Evaluated using the System Usability Scale (SUS), with scores ranging from 0-100.	2 years
AI System Response Time	Average time (seconds) taken for the AI to provide recommendations after data input.	2 years
System Failure Rate	Frequency of AI system failures, measured as failures per thousand hours of use (failures/thousand hours).	2 years
User Interface Design Satisfaction	Evaluated using the User Experience Questionnaire (UEQ), with scores ranging from 1-7.	2 years
Patient Satisfaction Score	Measured using the Patient Satisfaction Questionnaire (CSQ-8), with scores ranging from 8-32.	2 years
Treatment Adherence	Percentage (%) of patients adhering to personalized treatment plans and regular follow-up visits.	2 years
Physician Acceptance of AI System	Evaluated using the Technology Acceptance Model (TAM) scale, with scores ranging from 1-7.	2 years
Effectiveness of Decision Support	Percentage (%) improvement in the accuracy of treatment decisions with AI assistance compared to traditional decisions.	2 years
Decision Time Efficiency	Average time (seconds) required for physicians to make diagnostic and treatment decisions, before and after AI assistance.	2 years

Collaborators and Investigators

• Sponsor: The Eye Hospital of Wenzhou Medical University
• Collaborators: Second Affiliated Hospital of Wenzhou Medical University; First Affiliated Hospital of Wenzhou Medical University; ZhuHai Hospital; Macau University of Science and Technology Hospital

Study record dates

Study Major Dates

• Study Start (Actual): December 1, 2024
• Primary Completion (Estimated): December 30, 2026
• Study Completion (Estimated): December 30, 2026

Study Registration Dates

• First Submitted: December 9, 2024
• First Submitted That Met QC Criteria: December 23, 2024
• First Posted (Actual): January 1, 2025

Study Record Updates

• Last Update Posted (Actual): August 20, 2025
• Last Update Submitted That Met QC Criteria: August 15, 2025
• Last Verified: August 1, 2025

More Information

Terms related to this study

• Keywords: Artificial Intelligence; ocular diseases; Ophthalmic Multimodal AI-Assisted Medical Decision-Making
• Other Study ID Numbers: Ophthalmic AI

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No