Duoru Lin1, Jianhao Xiong2, Congxin Liu2, Lanqin Zhao1, Zhongwen Li1, Shanshan Yu1, Xiaohang Wu1, Zongyuan Ge3, Xinyue Hu2, Bin Wang2, Meng Fu2, Xin Zhao2, Xin Wang4, Yi Zhu5, Chuan Chen6, Tao Li1, Yonghao Li1, Wenbin Wei7, Mingwei Zhao8, Jianqiao Li9, Fan Xu10, Lin Ding11, Gang Tan12, Yi Xiang13, Yongcheng Hu14, Ping Zhang14, Yu Han15, Ji-Peng Olivia Li16, Lai Wei1, Pengzhi Zhu17, Yizhi Liu1, Weirong Chen1, Daniel S W Ting18, Tien Y Wong19, Yuzhong Chen20, Haotian Lin21. 1. State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China. 2. Beijing Eaglevision Technology Development, Beijing, China. 3. Department of Electrical and Computer Systems Engineering, Faculty of Engineering, Monash University, Melbourne, VIC, Australia. 4. Centre for Precision Medicine, Sun Yat-sen University, Guangzhou, Guangdong, China. 5. Department of Molecular and Cellular Pharmacology, University of Miami Miller School of Medicine, Miami, FL, USA. 6. Sylvester Comprehensive Cancer Center, University of Miami Miller School of Medicine, Miami, FL, USA. 7. Beijing Tongren Eye Centre, Beijing Key Laboratory of Intraocular Tumour Diagnosis and Treatment, Beijing Tongren Hospital, Capital Medical University, Beijing, China. 8. Department of Ophthalmology, Ophthalmology and Optometry Centre, Peking University People's Hospital, Beijing, China. 9. Department of Ophthalmology, Qilu Hospital of Shandong University, Jinan, Shandong, China. 10. Department of Ophthalmology, People's Hospital of Guangxi Zhuang Autonomous Region, Nanning, Guangxi, China. 11. Department of Ophthalmology, People's Hospital of Xinjiang Uygur Autonomous Region, Urumqi, Shanxi, China. 12. Department of Ophthalmology, University of South China, Hengyang, Hunan, China. 13. Department of Ophthalmology, The Central Hospital of Wuhan, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China. 14. Bayannur Paralympic Eye Hospital, Bayannur, Inner Mongolia, China. 15. Department of Ophthalmology, Eye and ENT Hospital, Fudan University, Shanghai, China. 16. Moorfields Eye Hospital NHS Foundation Trust, London, UK. 17. Guangdong Medical Devices Quality Surveillance and Test Institute, Guangzhou, Guangdong, China. 18. State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China; Singapore Eye Research Institute, Singapore National Eye Centre, Singapore. 19. Singapore Eye Research Institute, Singapore National Eye Centre, Singapore. 20. Beijing Eaglevision Technology Development, Beijing, China. Electronic address: chenyuzhong@airdoc.com. 21. State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Centre, Sun Yat-sen University, Guangzhou, Guangdong, China; Centre for Precision Medicine, Sun Yat-sen University, Guangzhou, Guangdong, China. Electronic address: gddlht@aliyun.com.
Abstract
BACKGROUND: Medical artificial intelligence (AI) has entered the clinical implementation phase, although real-world performance of deep-learning systems (DLSs) for screening fundus disease remains unsatisfactory. Our study aimed to train a clinically applicable DLS for fundus diseases using data derived from the real world, and externally test the model using fundus photographs collected prospectively from the settings in which the model would most likely be adopted. METHODS: In this national real-world evidence study, we trained a DLS, the Comprehensive AI Retinal Expert (CARE) system, to identify the 14 most common retinal abnormalities using 207 228 colour fundus photographs derived from 16 clinical settings with different disease distributions. CARE was internally validated using 21 867 photographs and externally tested using 18 136 photographs prospectively collected from 35 real-world settings across China where CARE might be adopted, including eight tertiary hospitals, six community hospitals, and 21 physical examination centres. The performance of CARE was further compared with that of 16 ophthalmologists and tested using datasets with non-Chinese ethnicities and previously unused camera types. This study was registered with ClinicalTrials.gov, NCT04213430, and is currently closed. FINDINGS: The area under the receiver operating characteristic curve (AUC) in the internal validation set was 0·955 (SD 0·046). AUC values in the external test set were 0·965 (0·035) in tertiary hospitals, 0·983 (0·031) in community hospitals, and 0·953 (0·042) in physical examination centres. The performance of CARE was similar to that of ophthalmologists. Large variations in sensitivity were observed among the ophthalmologists in different regions and with varying experience. The system retained strong identification performance when tested using the non-Chinese dataset (AUC 0·960, 95% CI 0·957-0·964 in referable diabetic retinopathy). INTERPRETATION: Our DLS (CARE) showed satisfactory performance for screening multiple retinal abnormalities in real-world settings using prospectively collected fundus photographs, and so could allow the system to be implemented and adopted for clinical care. FUNDING: This study was funded by the National Key R&D Programme of China, the Science and Technology Planning Projects of Guangdong Province, the National Natural Science Foundation of China, the Natural Science Foundation of Guangdong Province, and the Fundamental Research Funds for the Central Universities. TRANSLATION: For the Chinese translation of the abstract see Supplementary Materials section.
BACKGROUND: Medical artificial intelligence (AI) has entered the clinical implementation phase, although real-world performance of deep-learning systems (DLSs) for screening fundus disease remains unsatisfactory. Our study aimed to train a clinically applicable DLS for fundus diseases using data derived from the real world, and externally test the model using fundus photographs collected prospectively from the settings in which the model would most likely be adopted. METHODS: In this national real-world evidence study, we trained a DLS, the Comprehensive AI Retinal Expert (CARE) system, to identify the 14 most common retinal abnormalities using 207 228 colour fundus photographs derived from 16 clinical settings with different disease distributions. CARE was internally validated using 21 867 photographs and externally tested using 18 136 photographs prospectively collected from 35 real-world settings across China where CARE might be adopted, including eight tertiary hospitals, six community hospitals, and 21 physical examination centres. The performance of CARE was further compared with that of 16 ophthalmologists and tested using datasets with non-Chinese ethnicities and previously unused camera types. This study was registered with ClinicalTrials.gov, NCT04213430, and is currently closed. FINDINGS: The area under the receiver operating characteristic curve (AUC) in the internal validation set was 0·955 (SD 0·046). AUC values in the external test set were 0·965 (0·035) in tertiary hospitals, 0·983 (0·031) in community hospitals, and 0·953 (0·042) in physical examination centres. The performance of CARE was similar to that of ophthalmologists. Large variations in sensitivity were observed among the ophthalmologists in different regions and with varying experience. The system retained strong identification performance when tested using the non-Chinese dataset (AUC 0·960, 95% CI 0·957-0·964 in referable diabetic retinopathy). INTERPRETATION: Our DLS (CARE) showed satisfactory performance for screening multiple retinal abnormalities in real-world settings using prospectively collected fundus photographs, and so could allow the system to be implemented and adopted for clinical care. FUNDING: This study was funded by the National Key R&D Programme of China, the Science and Technology Planning Projects of Guangdong Province, the National Natural Science Foundation of China, the Natural Science Foundation of Guangdong Province, and the Fundamental Research Funds for the Central Universities. TRANSLATION: For the Chinese translation of the abstract see Supplementary Materials section.
Authors: Jingting Luo; Yuning Chen; Yuhang Yang; Kai Zhang; Yueming Liu; Hanqing Zhao; Li Dong; Jie Xu; Yang Li; Wenbin Wei Journal: Front Med (Lausanne) Date: 2022-01-21