Using AI to screen for corneal diseases
Application of Deep Learning for Screening Multiple Corneal Diseases
Tianjin Eye Hospital · NCT06211218
This study is testing a new AI tool that looks at eye images to see if it can help doctors find corneal diseases more accurately.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 3000 (estimated) |
| Sex | All |
| Sponsor | Tianjin Eye Hospital (other) |
| Locations | 1 site (Tianjin, Tianjin Municipality) |
| Trial ID | NCT06211218 on ClinicalTrials.gov |
What this trial studies
This study focuses on developing a deep learning algorithm that analyzes anterior segment images to identify various corneal diseases. The algorithm's effectiveness is validated through metrics such as sensitivity, specificity, and predictive values. By prospectively evaluating its performance, the study aims to enhance the accuracy of corneal disease diagnosis using advanced technology.
Who should consider this trial
Good fit: Ideal candidates are individuals with high-quality slit-lamp images that clearly show the sclera, pupil, and lens.
Not a fit: Patients with insufficient information for diagnosis or poor-quality images will not benefit from this study.
Why it matters
Potential benefit: If successful, this approach could lead to more accurate and timely diagnoses of corneal diseases, improving patient outcomes.
How similar studies have performed: Other studies utilizing AI for medical imaging have shown promising results, indicating potential success for this approach.
Eligibility criteria
Show full inclusion / exclusion criteria
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.
Where this trial is running
Tianjin, Tianjin Municipality
- Tiajin Eye Hospital — Tianjin, Tianjin Municipality, China (RECRUITING)
Study contacts
- Study coordinator: Yan Huo, Master
- Email: hy13102118953@163.com
- Phone: 13102118953
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions: Deep Learning, Corneal Disease, Screening