Artificial Intelligence-assissted Glaucoma Evaluation (AGE)

Development of Artificial Intelligence-assissted Diagnostic Program of Glaucoma

Glaucoma is currently the second leading cause of irreversible blindness in the world. Our study intends to combine clinical data of glaucoma patients in Zhongshan Ophthalmic Center with Artificial Intelligence techniques to create programs that can screen and diagnose glaucoma.

Study Overview

• Status: Completed
• Conditions: Glaucoma; Artificial Intelligence
• Intervention / Treatment: Diagnostic test: Visual field and OCT tests

Detailed Description

Glaucoma is currently the second leading cause of irreversible blindness in the world, which brings heavy burden to human society. Compared to other ocular diseases, diagnostic process of glaucoma is complicated depends on multiple test results, including visual field test, OCT, etc. How to diagnose glaucoma correctly and fast has always been a hot topic in glaucoma researches. Artificial intelligence is used to study and develop theories and methods that can help simulate and extend human intelligence, which has been utilized in a lot of research fields such as automatic drive and medicine. The study intends to combine clinical data of glaucoma patients in Zhongshan Ophthalmic Center with Artificial Intelligence techniques to create programs that can screen and diagnose glaucoma.

• Study Type: Observational
• Enrollment (Actual): 10800

Contacts and Locations

Study Locations

• China
  • Guangdong
    • Guangzhou, Guangdong, China, 510000
      • Zhongshan Ophthalmic Center

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Non-Probability Sample

Study Population

Anyone who can complete visual field test and have BCVA>0.1 can be enrolled. We will collect visual field test result and OCT images of both glaucoma and non-glaucoma patients.

Description

Inclusion Criteria:

1. BCVA>0.1
2. able to complete reliable visual field test
3. no history of intraocular surgery or fundus laser

Exclusion Criteria:

1. unable to complete visual field test

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Glaucoma patients; Glaucoma patients will take visual field test and OCT imaging of optic nerve area. All of these data will be collected as source of machine learning.	Diagnostic test: Visual field and OCT tests; Visual field test and OCT are commonly used essential tests to make accurate diagnosis of glaucoma. Algorithms to classify Visual field and OCT tests would both be developed and verified.
Non-glaucoma participants; Non-glaucoma participants will take visual field test and OCT imaging of optic nerve area. All of these data will be collected as source of machine learning.	Diagnostic test: Visual field and OCT tests; Visual field test and OCT are commonly used essential tests to make accurate diagnosis of glaucoma. Algorithms to classify Visual field and OCT tests would both be developed and verified.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Accuracy of diagnosis by artificial intelligence algorithm	Accuracy of diagnosis by artificial intelligence algorithm and compare this result with glaucoma specialists	from August 2017 to February 2021

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Sensitivity of diagnosis by artificial intelligence algorithm	Sensitivity of diagnosis by artificial intelligence algorithm	from August 2017 to February 2021
Specificity of diagnosis by artificial intelligence algorithm	Specificity of diagnosis by artificial intelligence algorithm	from August 2017 to February 2021

Collaborators and Investigators

• Sponsor: Sun Yat-sen University
• Collaborators: Chinese Academy of Sciences
• Investigators: Principal Investigator: Xiulan Zhang, Doctor, Sun Yat-sen University

Publications and helpful links

General Publications

• Diprose W, Buist N. Artificial intelligence in medicine: humans need not apply? N Z Med J. 2016 May 6;129(1434):73-6.
• Quigley HA. Glaucoma. Lancet. 2011 Apr 16;377(9774):1367-77. doi: 10.1016/S0140-6736(10)61423-7. Epub 2011 Mar 30.
• Asaoka R, Murata H, Iwase A, Araie M. Detecting Preperimetric Glaucoma with Standard Automated Perimetry Using a Deep Learning Classifier. Ophthalmology. 2016 Sep;123(9):1974-80. doi: 10.1016/j.ophtha.2016.05.029. Epub 2016 Jul 7.

Study record dates

Study Major Dates

• Study Start (Actual): August 15, 2017
• Primary Completion (Actual): December 1, 2019
• Study Completion (Actual): February 1, 2020

Study Registration Dates

• First Submitted: August 29, 2017
• First Submitted That Met QC Criteria: August 30, 2017
• First Posted (Actual): August 31, 2017

Study Record Updates

• Last Update Posted (Actual): October 22, 2020
• Last Update Submitted That Met QC Criteria: October 19, 2020
• Last Verified: October 1, 2020

More Information

Terms related to this study

• Keywords: artificial intelligence; glaucoma
• Additional Relevant MeSH Terms: Eye Diseases; Ocular Hypertension; Glaucoma
• Other Study ID Numbers: ProjectAGE

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