目的：探索和实践人工智能辅助诊断的闵行区视觉健康管理模式。方法：介绍闵行区人工智能辅助诊断的视觉健康管理模式；分析对比传统视觉健康管理模式和人工智能辅助诊断视觉健康管理模式下，社区视觉健康筛查情况，眼病发现、需转诊、复诊情况等；工作人员配置、眼科门诊接诊情况、居民眼病知识率和视觉健康服务满意情况等。结果：传统视觉健康管理模式和人工智能辅助诊断模式主要眼病（糖尿病视网膜病变、青光眼、年龄相关性黄斑变性、高度近视）发现率比较差异均有统计学意义（c²=954.03，P ＜0.01），需转诊率差异有统计学意义（c²=431.07，P ＜0.01）。人工智能辅助诊断管理模式与传统视觉健康管理模式的居民在青光眼的知晓率比较差异有统计学意义（c²=4.24，P＜0.05）。传统视觉健康管理模式和人工智能辅助诊断模式居民对视觉健康服务中的服务质量和服务时间的满意度比较差异有统计学意义（Z=-2.75，Z=-2.18，P ＜0.05）。结论：人工智能辅助诊断视觉健康管理模式，糖尿病视网膜病变、青光眼等主要眼病发现率高于传统模式，需转诊率降低，居民对青光眼的知晓率提升，在服务质量和服务时间上的居民满意度较高。基于人工智能辅助诊断的视觉健康筛查与管理模式值得本区其他社区的推广和应用。

Objective To explore and practice the visual health management mode of Minhang District . Methods Introduce the visual health management mode of AI-assisted diagnosis in Minhang District; analyze and compare the traditional visual health management mode and AI-assisted visual health management mode, community visual health screening projects and completion conditions, screening files, eye disease discovery , referral, actual referral and return ; analyze and compare the visual health management mode, staff allocation, ophthalmic outpatient reception, and the satisfaction of visual health service. Results The difference in the discovery rate of major eye diseases (Diabetic Retinopathy,Glaucoma,Age-related Macular Degeneration,High Myopia) between the traditional model and artificial intelligence-assisted diagnosis mode in both communities (c²=954.03, P<0.01), the referral rate (c²=431.07, P<0.01). The awareness of AI-assisted diagnosis management improved in glaucoma in the two modes was statistically significant (c²=4.24, P<0.05). Traditional model and artificial intelligence assisted diagnosis model of visual health service quality and service time is statistically significant (Z=-2.75, Z=-2.18, P<0.05). Conclusion The visual health screening and management mode based on AI-assisted diagnosis is worthy of the promotion and application in other communities in the region.

目的：评估白内障人工智能辅助诊断系统在社区筛查中的应用效果。方法：采用前瞻性观察性研究方法对白内障人工辅助诊断系统的应用效果进行分析，结合远程医疗的模式，由社区卫生人员对居民进行病史采集、视力检查和裂隙灯眼前节检查等，将数据上传至云平台，由白内障人工智能辅助诊断系统和人类医生依次进行白内障评估。结果：受检人群中男性所占比例为35.7%，年龄中位数为66岁，裂隙灯眼前节照片有98.7%的图像质量合格。该白内障人工智能辅助诊断系统在外部验证集中检出重度白内障的曲线下面积为0.915。在人类医生建议转诊的病例中，有80.3%也由人工智能系统给出了相同的建议。结论：该白内障人工智能辅助诊断系统在白内障社区筛查的应用中具有较好的可行性和准确性，为开展社区筛查疾病提供了参考依据。

Objective: To evaluate the effectiveness of an artificial intelligence-assisted diagnostic system for cataract screening in community. Methods: A prospective observational study was carried out based on a telemedicine platform. Patient history, medical records and anterior ocular segment images were collected and transmitted from community healthcare centers to Zhongshan Ophthalmic Center for evaluation by both ophthalmologists and artificial intelligence-assisted cataract diagnostic system. Results: Of all enumerated subjects, 35.7% were male and the median age was 66 years old. Of all enumerated slit-lamp images, 98.7% met the requirement of acceptable quality. This artificial intelligence-assisted diagnostic system achieved an AUC of 0.915 for detection of severe cataracts in the external validation dataset. For subjects who were advised to be referred to tertiary hospitals by doctors, 80.3% of them received the same suggestion from this artificial intelligence-assisted diagnostic system.Conclusion: This artificial intelligence-assisted cataract diagnostic system showed high applicability and accuracy in community-based cataract screening and could be a potential model of care in community-based disease screening.