Artificial Intelligence for Screening of Multiple Corneal Diseases

Tianjin Eye Hospital

Status: Enrolling

Conditions: Deep Learning; Screening; Corneal Disease

Treatments: Diagnostic Test: Cornea diseases diagnosed by artificial intelligence algorithm

Study type: Observational

Funder types: Other

Identifiers

NCT06211218

KY-2023083

Details and patient eligibility

About

This study developed a deep learning algorithm based on anterior segment images and prospectively validated its ability to identify corneal diseases.The effectiveness and accuracy of this algorithm was evaluated by sensitivity, specificity, positive predictive value, negative predictive value, and area under curve.

Enrollment: 3,000 estimated patients

Sex: All

Volunteers: No Healthy Volunteers

Inclusion criteria

1. The quality of slit-lamp images should clinical acceptable.
2. More than 90% of the slit-lamp image area including three main regions (sclera, pupil, and lens) are easy to read and discriminate.

Exclusion criteria

1）Insufficient information for diagnosis.

Trial design

3,000 participants in 1 patient group

Cornea diseases diagnosed by artificial intelligence algorithm

Treatment:

Diagnostic Test: Cornea diseases diagnosed by artificial intelligence algorithm