Diagnostic Efficacy of CNN in Differentiation of Visual Field

Diagnostic Efficacy of Convolutional Neural Network Based Algorithm in Differentiation of Glaucomatous Visual Field From Non-glaucomatous Visual Field

Glaucoma is currently the leading cause of irreversible blindness in the world. The multi-center study is designed to evaluate the efficacy of the convolutional neural network based algorithm in differentiation of glaucomatous from non-glaucomatous visual field, and to assess its utility in the real world.

Study Overview

• Status: Completed
• Conditions: Diagnositic Efficacy of Deep Convolutional Neural Network in Differentiation of Glaucoma Visual Field From Non-glaucoma Visual Field
• Intervention / Treatment: Diagnostic test: AI diagnostic algorithm

Detailed Description

Glaucoma is the world's leading cause of irreversible blind, characterized by progressive retinal nerve fiber layer thinning and visual field defects. Visual field test is one of the gold standards for diagnosis and evaluation of progression of glaucoma. However, there is no universally accepted standard for the interpretation of visual field results, which is subjective and requires a large amount of experience. At present, artificial intelligence has achieved the accuracy comparable to human physicians in the interpretation of medical imaging of many different diseases. Previously, we have trained a deep convolutional neural network to read the visual field reports, which has even higher diagnostic efficacy than ophthalmologists. The current multi-center study is designed to evaluate the efficacy of the convolutional neural network based algorithm in differentiation of glaucomatous from non-glaucomatous visual field, compare its performance with ophthalmologists and to assess its utility in the real world.

• Study Type: Observational
• Enrollment (Actual): 437

Contacts and Locations

Study Locations

• China
  • Guangdong
    • Guangzhou, Guangdong, China, 51000
      • Zhongshan Ophthalmic Center

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (ADULT, OLDER_ADULT)
• Accepts Healthy Volunteers: Yes
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

Patients from clinics in different eye centers across China. Each subject must be diagnosed based on comprehensive medical tests and medical records. The leading center will read all the medical data to give out diagnosis as the gold standard.

Description

Inclusion Criteria:

1. Age≥18;
2. Informed consent obtained;
3. Diagnosed with specific ocular diseases;
4. Able to perform visual field test

Exclusion Criteria:

Incomplete clinical data to support diagnosis

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
AI group; The visual field reports in this group will be evaluated by the convolutional neural network.	Diagnostic test: AI diagnostic algorithm; The visual fields collected would be assessed by the algorithm and ophthalmologists independently. The performance of the algorithm and the ophthalmologists would be compared, including accuracy, AUC, sensitivity and specificity.; Other Names: Standard diagnostic procedure
Human group; The visual field reports in this group will be evaluated by 3 ophthalmologists independently.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Time Frame
AUC value of convolutional neural network in differentiation of Glaucoma visual field from non-glaucoma visual field	from Jan 2019 to Jan 2020

Secondary Outcome Measures

Outcome Measure	Time Frame
Sensitivity and specificity of convolutional neural network in detection of glaucoma visual field	from Jan 2019 to Jan 2020

Collaborators and Investigators

• Sponsor: Sun Yat-sen University

Study record dates

Study Major Dates

• Study Start (ACTUAL): March 15, 2019
• Primary Completion (ACTUAL): December 31, 2019
• Study Completion (ACTUAL): December 31, 2019

Study Registration Dates

• First Submitted: November 26, 2018
• First Submitted That Met QC Criteria: November 28, 2018
• First Posted (ACTUAL): November 30, 2018

Study Record Updates

• Last Update Posted (ACTUAL): January 27, 2020
• Last Update Submitted That Met QC Criteria: January 23, 2020
• Last Verified: January 1, 2020

More Information

Terms related to this study

• Keywords: Glaucoma; Visual field; Deep convolutional neural network
• Additional Relevant MeSH Terms: Eye Diseases; Ocular Hypertension; Glaucoma
• Other Study ID Numbers: 2018KYPJ125

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