Development and Validation of a Deep Learning System for Multiple Ocular Fundus Diseases Using Retinal Images

Ophthalmological Disorder Clinical Trial

Official title:

Development and Validation of a Deep Learning System for Multiple Ocular Fundus Diseases Using Retinal Images: a Multi-center Prospective Study

Clinical Trial Details — Status: Recruiting

Administrative data

• NCT number: NCT04213430
• Other study ID #: CCPMOH2019- China8
• Status: Recruiting
• Start date: January 2014
• Est. completion date: May 2020

Study information

• Verified date: December 2019
• Source: Sun Yat-sen University
• Contact: Haotian Lin, PhD
• Phone: 13802793086
• Email: gddlht[@]aliyun.com
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

Retinal images can reflect both fundus and systemic conditions (diabetes and cardiovascular disease) and firstly to be used for medical artificial intelligence (AI) algorithm training due to its advantages of clinical significance and easy to obtain. Here, the investigators developed a single network model that can mine the characteristics among multiple fundus diseases, which was trained by plenty of fundus images with one or several disease labels (if they have) in each of them. The model performance was compared with those of both native and international ophthalmologists. The model was further tested by datasets with different camera types and validated by three external datasets prospectively collected from the clinical sites where the model would be applied.

Recruitment information / eligibility

• Status: Recruiting
• Enrollment: 300000
• Est. completion date: May 2020
• Est. primary completion date: February 2020
• Accepts healthy volunteers: Accepts Healthy Volunteers
• Gender: All
• Age group: N/A and older

Eligibility

Inclusion Criteria:

• The quality of fundus images should clinical acceptable. More than 80% of the fundus image area including four main regions (optic disk, macular, upper and lower retinal vessel archs) are easy to read and discriminate.

Exclusion Criteria:

• Images with light leakage (>30% of area), spots from lens flares or stains, and overexposure were excluded from further analysis.

Related Conditions & MeSH terms

• Eye Diseases
• Ophthalmological Disorder

Intervention

Other:
• diagnostic
Training dataset was used to train the deep learning model, which was validated and tested by other two datasets.

Locations

Country	Name	City	State
China	Zhongshan Ophthalmic Center, Sun Yat-sen Univerisity	Guangzhou	Guangdong

Sponsors (1)

Lead Sponsor	Collaborator
Sun Yat-sen University

Country where clinical trial is conducted

China, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Area under the receiver operating characteristic curve of the deep learning system	The investigators will calculate the area under the receiver operating characteristic curve of deep learning system and compare this index between deep learning system and human doctors.	baseline
Secondary	Sensitivity of the deep learning system	The investigators will calculate the sensitivity of deep learning system and compare this index between deep learning system and human doctors.	baseline
Secondary	Specificity of the deep learning system	The investigators will calculate the specificity of deep learning system and compare this index between deep learning system and human doctors.	baseline