The Diabetic Retinopathy Screening, Prevention and Control Program

Overview

The greatest harm of diabetes is various acute and chronic complications, especially diabetic retinopathy(DR), leading to extremely high rates of disability and blindness. Early screening, early diagnosis, and early treatment are the keys to maintaining vision in patients with DR. However, compared with the high prevalence of diabetes in China, the DR screening ability is relatively inadequate. To change this situation, deep learning(DL), a form of artificial intelligence (AI), might be a potential effective method to solve this dilemma.

The greatest harm of diabetes is various acute and chronic complications, especially DR, leading to extremely high rates of disability and blindness. However, if the fundus examination is carried out regularly in the early stages of onset, the risk of blindness can be significantly reduced. Therefore, early screening, early diagnosis, and early treatment are the keys to maintaining vision in patients with DR. However, compared with the high prevalence of diabetes in China, the DR screening ability is relatively inadequate. The Diabetic Retinopathy Screening and Prevention Program is a branch project of MMC. Its purpose is to carry out an efficient workflow for early detecting, timely managing of DR, and to establish a referral system for implementing treatment and the long-term follow-up of DR by means of DL. First, In order to improve its sensitivity and specificity, more participants are involved in other medical institutes besides MMCs, then we can effectively explore the prevalance of DR in China and helps to early screening, prevention, treatment and referal process of DR. Secend, we collect participants' serum, plasma,DNA, several medical stastistics and life styles to explore genetics, new biomarkers, risk factors of DR. Objective: 1. To validate the methodology and feasibility of DR screening using a DL based automated DR grading system in clinical practice. 2. To explore the prevalence of DR and subgroup identification, and fundus images analysis, etc. 3. To explore the genetics, new biomarkers, risk factors of DR. 4. To explore the methods of early screening, prevention, treatment and referal process of DR.

Conditions