Deep-learning models for the detection and incidence prediction of chronic kidney disease and type 2 diabetes from retinal fundus images.

Abstract

Regular screening for the early detection of common chronic diseases might benefit from the use of deep-learning approaches, particularly in resource-poor or remote settings. Here we show that deep-learning models can be used to identify chronic kidney disease and type 2 diabetes solely from fundus images or in combination with clinical metadata (age, sex, height, weight, body-mass index and blood pressure) with areas under the receiver operating characteristic curve of 0.85-0.93. The models were trained and validated with a total of 115,344 retinal fundus photographs from 57,672 patients and can also be used to predict estimated glomerulal filtration rates and blood-glucose levels, with mean absolute errors of 11.1-13.4 ml min-1 per 1.73 m2 and 0.65-1.1 mmol l-1, and to stratify patients according to disease-progression risk. We evaluated the generalizability of the models for the identification of chronic kidney disease and type 2 diabetes with population-based external validation cohorts and via a prospective study with fundus images captured with smartphones, and assessed the feasibility of predicting disease progression in a longitudinal cohort.

• Authors: Kang Zhang, Xiaohong Liu, Jie Xu, Jin Yuan, Wenjia Cai, Ting Chen, Kai Wang, Yuanxu Gao, Sheng Nie, Xiaodong Xu, Xiaoqi Qin, Yuandong Su, Wenqin Xu, Andrea Olvera, Kanmin Xue, Zhihuan Li, Meixia Zhang, Xiaoxi Zeng, Charlotte L Zhang, Oulan Li, Edward E Zhang, Jie Zhu, Yiming Xu, Daniel Kermany, Kaixin Zhou, Ying Pan, Shaoyun Li, Iat Fan Lai, Ying Chi, Changuang Wang, Michelle Pei, Guangxi Zang, Qi Zhang, Johnson Lau, Dennis Lam, Xiaoguang Zou, Aizezi Wumaier, Jianquan Wang, Yin Shen, Fan Fan Hou, Ping Zhang, Tao Xu, Yong Zhou, Guangyu Wang
• Journal: Nature biomedical engineering (Nat Biomed Eng) Vol. 5 Issue 6 Pg. 533-545 (06 2021) ISSN: 2157-846X [Electronic] England
• PMID: 34131321 (Publication Type: Journal Article, Research Support, Non-U.S. Gov't)

Chemical References

• Blood Glucose

Topics

• Area Under Curve
• Blood Glucose (metabolism)
• Body Height
• Body Mass Index
• Body Weight
• Deep Learning
• Diabetes Mellitus, Type 2 (diagnostic imaging, metabolism, pathology)
• Disease Progression
• Female
• Fundus Oculi
• Glomerular Filtration Rate
• Humans
• Image Interpretation, Computer-Assisted (statistics & numerical data)
• Male
• Metadata (statistics & numerical data)
• Middle Aged
• Neural Networks, Computer
• Photography (methods, statistics & numerical data)
• Prospective Studies
• ROC Curve
• Renal Insufficiency, Chronic (diagnostic imaging, metabolism, pathology)
• Retina (diagnostic imaging, metabolism, pathology)