Background: Diabetic retinopathy (DR) is regarded as a major cause of preventable blindness, which can be detected and treated if the cases are identified by screening. Screening for DR is therefore being practiced in developed countries, and tele screening has been a prominent model of delivery of eye care for screening DR.
Aim: Our study has been designed to provide inputs on the suitability of a computer-assisted DR screening solution, for use in a larger prospective study.
Methods: Computer-assisted screening technology for grading diabetic retinopathy from fundus images by a set of machine learning algorithms.
Results: The preliminary recommendations from a pilot study of a system built using the public datasets and retrospective images, showed a good sensitivity and specificity.
Conclusion: The machine learning algorithms has to be validated on a larger dataset of a population level study.