Validation of the Utility of Ophthalmology Intelligent Diagnostic System

Validation of the Utility of Ophthalmology Intelligent Diagnostic System: A Clinical Trial

The prevention and treatment of diseases via artificial intelligence represents an ultimate goal in computational medicine. Application scenarios of the current medical algorithms are too simple to be generally applied to real-world complex clinical settings. Here, the investigators use "deep learning" and "visionome technique", an novel annotation method for artificial intelligence in medical, to create an automatic detection and classification system for four key clinical scenarios: 1) mass screening, 2) comprehensive clinical triage, 3) hyperfine diagnostic assessment, and 4) multi-path treatment planning. The investigator also establish a telemedicine system and conduct clinical trial and website-based study to validate its versatility.

Study Overview

• Status: Completed
• Conditions: Artificial Intelligence; Ophthalmopathy
• Intervention / Treatment: Device: Ophthalmology diagnostic system.

• Study Type: Observational
• Enrollment (Actual): 615

Contacts and Locations

Study Locations

• China
  • Guangdong
    • Guangzhou, Guangdong, China, 510000
      • Zhongshan Ophthalmic Center, Sun Yat-sen University

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Probability Sample

Study Population

A prospective study of patients and residents who use the web platform for diagnosis.

Description

Inclusion Criteria:

• Patients and residents who underwent ophthalmic examination of the eye and recorded their ocular information in the outpatient clinic and community.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Eligible patients for AI test.; Device: ophthalmology diagnostic system. An artificial intelligence to make comprehensive evaluation and treatment decision of ocular diseases.	Device: Ophthalmology diagnostic system.; An artificial intelligence to make comprehensive evaluation and treatment decision of ocular diseases.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
The proportion of accurate, mistaken and miss detection of the ophthalmology diagnostic system.	Up to 5 years

Collaborators and Investigators

• Sponsor: Sun Yat-sen University
• Collaborators: Ministry of Health, China; Xidian University

Publications and helpful links

General Publications

• Li W, Yang Y, Zhang K, Long E, He L, Zhang L, Zhu Y, Chen C, Liu Z, Wu X, Yun D, Lv J, Liu Y, Liu X, Lin H. Dense anatomical annotation of slit-lamp images improves the performance of deep learning for the diagnosis of ophthalmic disorders. Nat Biomed Eng. 2020 Aug;4(8):767-777. doi: 10.1038/s41551-020-0577-y. Epub 2020 Jun 22.

Study record dates

Study Major Dates

• Study Start (Actual): April 1, 2018
• Primary Completion (Actual): August 31, 2019
• Study Completion (Actual): August 31, 2019

Study Registration Dates

• First Submitted: April 11, 2018
• First Submitted That Met QC Criteria: April 11, 2018
• First Posted (Actual): April 17, 2018

Study Record Updates

• Last Update Posted (Actual): October 21, 2019
• Last Update Submitted That Met QC Criteria: October 17, 2019
• Last Verified: October 1, 2019

More Information

Terms related to this study

• Keywords: conjunctivitis; cataracts; pterygium; keratitis
• Additional Relevant MeSH Terms: Eye Diseases
• Other Study ID Numbers: CCPMOH2018-China-2

Drug and device information, study documents

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