Diabetes Detection from Diabetic Retinopathy-Absent Images Using Deep Learning Methodology

Abstract

Aims Diabetes is one of the leading causes of morbidity and mortality in the United States and worldwide. This research aimed to develop an artificial intelligence (AI) machine learning model which can detect the presence of diabetes from fundus imagery of eyes without diabetic eye disease. Methods Our researchers trained a machine learning algorithm on the EyePACS dataset, consisting of 47,076 images. Patients were also divided into cohorts based on disease duration, each cohort consisting of patients diagnosed within the timeframe in question (e.g., 15 years) and healthy patients. Results The algorithm achieved 0.83 area under receiver operating curve (AUC) in detecting diabetes per image, and AUC 0.86 on the task of detecting diabetes per patient. Conclusion Our results suggest that diabetes may be diagnosed non-invasively using fundus imagery alone. This may enable diabetes diagnosis at point of care, as well as other, accessible venues, facilitating the diagnosis of many undiagnosed people with diabetes.