Automated Analysis of Retinal Images for Detection of Diabetic Retinopathy using Artificial Intelligence (AI)

• Conditions: Image analysis; Patients with any type of diabetes mellitusDiabetic retinopathy screening; Image enhancement; Color retinal image; Artificial intelligence; Diabetic retinopathy

• Registration Number: TCTR20211122006
• Lead Sponsor: ational Higher Education Science Research and Innovation Policy Council (NXPO)

Brief Summary

Not available

Detailed Description

Not available

Study Timeline

• Study Start: 2021-11-22
• Study Completion: 2023-12-29
• Last Update Posted: 19 August 2024

Recruitment & Eligibility

• Status: Pending (Not yet recruiting)
• Sex: All
• Target Recruitment: 10000

Inclusion Criteria

1. Type 1 or 2 diabetes mellitus who come for a diabetic retinopathy screening at the eye clinic of Songklanagarind Hospital, 2. At least 18 years old of age, 3. Able to take fundus photography

Exclusion Criteria

1. Poor quality of fundus photograph that could not be evaluated, 2. Retinal pathologies other than diabetic retinopathy

Study & Design

• Study Type: Observational
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Correction of DR severity grading by AI 1 year Sensitivity and Specificity

Secondary Outcome Measures

Name	Time	Method
Agreement between AI and specialist grading 6 months Kappa statistic