Validation of Computer-Aided Diagnosis of Diabetic Retinopathy From Retinal Photographs of Diabetic Patients

Published: Tue, 12/07/21

Join TMT’s Bibliodiverse Universe of Esteemed Authors!

TMT brings you today’s most practical front line research, pilots, clinical insights and opinions from around the globe to build knowledge and consensus for value based virtual care delivery services. For study details click the link below and get up to speed today!

Validation of computer-aided diagnosis of diabetic retinopathy from retinal photographs of diabetic patients from Telecamps
Sheila John et al

Objective: To validate an algorithm previously developed by the Healthcare Technology Innovation Centre, IIT Madras, India for screening of diabetic retinopathy (DR), in fundus images of diabetic patients from telecamps to examine the screening performance for DR.

Main Outcome Measures: Fundus images were evaluated for presence or absence of DR using a computer-assisted algorithm, by an ophthalmologist at a tertiary eye care center (reference standard) and by a fundus photographer.

Results: The algorithm demonstrated 85% sensitivity and 80% specificity in detecting DR compared to ophthalmologist. The algorithm identified 100% of vision-threatening retinopathy just like the ophthalmologist.

Conclusions: All findings of vision-threatening retinopathy could be detected with reasonable accuracy and will help to reduce the workload for human graders in remote areas.

Submit your original research manuscript to

https://telehealthandmedicinetoday.com/index.php/journal/about/submissions

Deadline for April TMT submissions: March 1, 2022

For a complimentary subscription, register at: https://telehealthandmedicinetoday.com/index.php/journal/user/register

About

Telehealth and Medicine Today (TMT) is a gold open access international peer reviewed journal examining the value of telehealth and clinical automation, its use and scalable developments, business process guidance, market research and the economic impact of digital health innovations in an evolving health technology sector. Articles feature original research, pilot studies, case use, best practices and perspectives from multidisciplinary stakeholders. Authors are encouraged to submit outcomes data for cost efficiencies realized in health system(s), patient populations or clinical practices in a value based system. A world-class review board includes constructive commentary through rapid and rigorous peer review. TMT timestamps article provenance on the blockchain.

TMT’s audience includes leadership at hospitals and medical research centers, universities, payor organizations, IT/IS, healthcare providers, consultants, companies (early and more established), entrepreneurs, developers & start-ups, life sciences and device companies, pharmacy, NGO, government, and policy leadership around the globe.

Endorsed by

Published By

Building Trust Through Truth