Artificial Intelligence-assissted Glaucoma Evaluation

NCT03268031 | Completed DMC

• 1 other identifier: ProjectAGE
• Study Type: observational
• Target: 10,800
• Locations: 1 country
• Sites: 1

Brief Summary

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.

Conditions

Artificial Intelligence; Glaucoma

Keywords

artificial intelligence; glaucoma

Outcome Measures

Primary Outcomes (1)

• 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 Outcomes (2)

• Sensitivity of diagnosis by artificial intelligence algorithm

  from August 2017 to February 2021

• Specificity of diagnosis by artificial intelligence algorithm

  from August 2017 to February 2021

Study Arms (2)

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

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

Interventions

Visual field and OCT tests DIAGNOSTIC_TEST

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.

Glaucoma patients; Non-glaucoma participants

Eligibility Criteria

• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• 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.

You may qualify if:

• BCVA\>0.1
• able to complete reliable visual field test
• no history of intraocular surgery or fundus laser

You may not qualify if:

• \. unable to complete visual field test

Sponsors & Collaborators

• Sun Yat-sen University: lead
• Chinese Academy of Sciences: collaborator

Study Sites (1)

Zhongshan Ophthalmic Center

Guangzhou, Guangdong, 510000, China

Location

Related Publications (3)

• Diprose W, Buist N. Artificial intelligence in medicine: humans need not apply? N Z Med J. 2016 May 6;129(1434):73-6.

  PMID: 27349266 RESULT

• Quigley HA. Glaucoma. Lancet. 2011 Apr 16;377(9774):1367-77. doi: 10.1016/S0140-6736(10)61423-7. Epub 2011 Mar 30.

  PMID: 21453963 RESULT

• 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.

  PMID: 27395766 RESULT

MeSH Terms

Conditions

Glaucoma

Interventions

Visual Fields

Condition Hierarchy (Ancestors)

Ocular Hypertension; Eye Diseases

Intervention Hierarchy (Ancestors)

Ocular Physiological Phenomena

Study Officials

• Xiulan Zhang, Doctor

  Sun Yat-sen University

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Director of Clinical Research Center

Study Record Dates

• First Submitted: August 29, 2017
• First Posted: August 31, 2017
• Study Start: August 15, 2017
• Primary Completion: December 1, 2019
• Study Completion: February 1, 2020
• Last Updated: October 22, 2020

Record last verified: 2020-10

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)