Chen Xinjian, Wang Jingtao, Qian Tianwei, Wang Jingcheng, Ding Yiming, Zhang Su, Liao Jingjing, Cheng Qian, Yang Ting, Mateen Muhammad, Fan Yu, Song Zongming, Chen Jili, Li Suyan, Hu Jianmin, Yan Wentao, Chen Haoyu, Wu Wencan, Huang Jing, Wong Tien Yin, Xu Xun
School of Electronics and Information Engineering, Soochow University, Suzhou, China.
State Key Laboratory of Radiation Medicine and Protection, Soochow University, Suzhou, Jiangsu, China.
NPJ Digit Med. 2025 Aug 29;8(1):559. doi: 10.1038/s41746-025-01959-7.
Millions of individuals worldwide suffer from retinal anomalies, which can lead to irreversible vision loss. However, the number of ophthalmologists is highly mismatched with the population base in China, especially in many rural and underdeveloped towns. To tackle these challenges, this paper developed an Artificial Intelligence Cloud Platform for OCT-based Retinal Anomalies Screening (AI-PORAS), which is capable of detecting 15 retinal anomalies in OCT images to enhance remote diagnostic efficiency. AI-PORAS has been trained, validated, and deployed to 207 medical institutions in 29 provinces in China. The validation on 165,384 eyes with 3,551,959 OCT B-scan slices, AI-PORAS achieved an average accuracy of 93.16%, an AUC of 93.64%, a FPR of 6.82%, a FNR of 7.87%, matching the average performance level of attending ophthalmologists. Additionally, Statistical analysis of the 116,717 remotely diagnosed patients provided insightful guidance for healthcare decision-making and the development of tailored treatment plans.
全球数以百万计的人患有视网膜异常，这可能导致不可逆转的视力丧失。然而，在中国，眼科医生的数量与人口基数严重不匹配，尤其是在许多农村和欠发达城镇。为应对这些挑战，本文开发了一种基于光学相干断层扫描（OCT）的视网膜异常筛查人工智能云平台（AI-PORAS），该平台能够在OCT图像中检测出15种视网膜异常，以提高远程诊断效率。AI-PORAS已经在中国29个省份的207家医疗机构进行了培训、验证和部署。通过对165384只眼睛的3551959个OCT B扫描切片进行验证，AI-PORAS的平均准确率达到93.16%，曲线下面积（AUC）为93.64%，假阳性率（FPR）为6.82%，假阴性率（FNR）为7.87%，与主治眼科医生的平均表现水平相当。此外，对116717名远程诊断患者的统计分析为医疗决策和制定个性化治疗方案提供了有见地的指导。
Cochrane Database Syst Rev. 2023-11-15
Cochrane Database Syst Rev. 2015-1-7
Cochrane Database Syst Rev. 2024-10-17
Cochrane Database Syst Rev. 2011-7-6
Therap Adv Gastroenterol. 2025-6-23
J Med Internet Res. 2025-6-23
NPJ Digit Med. 2024-1-26
JAMA. 2024-1-9
J Glob Health. 2023-11-3
Cell Rep Med. 2023-7-18
Zotero 插件
