Artificial Intelligence for Detecting Retinal Diseases

Artificial Intelligence Clinical Trial

Official title:

Classification of Retinal Diseases by Artificial Intelligence

Clinical Trial Details — Status: Completed

Administrative data

• NCT number: NCT04678375
• Other study ID #: AI in retinal diseases
• Status: Completed
• Start date: June 1, 2018
• Est. completion date: October 1, 2020

Study information

• Verified date: June 2018
• Source: Beijing Tongren Hospital
• Contact: n/a
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

The objective of this study is to apply an artificial intelligence algorithm to diagnose multi retinal diseases from fundus photography. The effectiveness and accuracy of this algorithm was evaluated by sensitivity, specificity, positive predictive value, negative predictive value, and area under curve.

Description:

The objective of this study is to apply an artificial intelligence algorithm to diagnose referral diabetes retinopathy, referral age-related macular degeneration, referral possible glaucoma, pathological myopia, retinal vein occlusion, macular hole, macular epiretinal membrane, hypertensive retinopathy, myelinated fibers, retinitis pigmentosa and other retinal lesions from fundus photography. The effectiveness and accuracy of this algorithm was evaluated by sensitivity, specificity, positive predictive value, negative predictive value, area under curve, and F1 score.

Recruitment information / eligibility

• Status: Completed
• Enrollment: 1000000
• Est. completion date: October 1, 2020
• Est. primary completion date: June 30, 2020
• Accepts healthy volunteers: Accepts Healthy Volunteers
• Gender: All
• Age group: 18 Years to 80 Years

Eligibility

Inclusion Criteria:

• fundus photography around 45° field which covers optic disc and macula

• complete identification information

Exclusion Criteria:

• insufficient information for diagnosis.

Related Conditions & MeSH terms

• Artificial Intelligence
• Retinal Diseases

Intervention

Diagnostic Test:
• Retinal diseases diagnosed by artificial intelligence algorithm
An artificial intelligence algorithm was applied to diagnose referral diabetes retinopathy, referral age-related macular degeneration, referral possible glaucoma, pathological myopia, retinal vein occlusion, macular hole, macular epiretinal membrane, hypertensive retinopathy, myelinated fibers, retinitis pigmentosa and other retinal lesions from fundus photography.

Locations

Country	Name	City	State
China	Wen-Bin Wei	Beijing	Beijing

Sponsors (2)

Lead Sponsor	Collaborator
Beijing Tongren Hospital	Beijing Tulip Partner Technology Co., Ltd, China

Country where clinical trial is conducted

China, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Area under curve	We used the receiver operating characteristic (ROC) curve and area under curve to examine the ability of this artificial intelligence algorism recognition and classification of retinal diseases.	1 week
Primary	Sensitivity and specificity	We used sensitivity and specificity to examine the ability of this artificial intelligence algorism recognition and classification of retinal diseases.	1 week
Primary	Positive predictive value, negative predictive value	We used positive predictive value and negative predictive value to examine the ability of this artificial intelligence algorism recognition and classification of retinal diseases.	1 week
Primary	F1 score	We used F1 score to examine the ability of this artificial intelligence algorism recognition and classification of retinal diseases.	1 week
Secondary	Systemic biomarkers and diseases	Using medical records as the gold standard, we test the accuracy of this artificial intelligence algorism recognition and classification of systemic biomarkers and diseases: age, sex, blood pressure, blood hemoglobin, cardiovascular diseases, thyroid function and kidney function.	1 week