随着智能手机覆盖率的增加与可用性的提升，实现智能健康管理的应用程序成为新兴研究热点。新一代智能手机可通过追踪步数，监测心率、睡眠，拍摄照片等方式进行健康分析，成为新的医学辅助工具。随着深度学习技术在图像处理领域的不断进展，基于医学影像的智能诊断已在多个学科全面开花,有望彻底改变医院传统的眼科疾病诊疗模式。眼科疾病的常规诊断往往依赖于各种形式的图像，如裂隙灯生物显微镜、眼底成像、光学相干断层扫描等。因此，眼科成为医学人工智能发展最快的领域之一。将眼科人工智能诊疗系统部署在智能手机上，有望提高疾病诊断效率和筛查覆盖率，改善医疗资源紧张的现状，具有极大的发展前景。综述的重点是基于深度学习和智能手机的眼病预防与远程诊疗的进展，以糖尿病性视网膜病变、青光眼、白内障3种疾病为例，讲述深度学习和智能手机在眼病管理方面的具体研究、应用和展望。

With the increasing coverage and availability of smart phones, the application of realizing intelligent health management has become an emerging research hotspot. The new generation of smart phones can perform health analysis by tracking the step numbers, monitoring heart rate and sleep quality, taking photos and other approaches, thereby becoming a new medical aid tool. With the continuous development of deep learning technology in the field of image processing, intelligent diagnosis based on medical imaging has blossomed in many disciplines, which is expected to completely change the traditional eye diseases diagnosis and treatment mode of hospitals. The conventional diagnosis of ophthalmic diseases often relies on various forms of images, such as slit lamp biological microscope, fundus imaging, optical coherence tomography, etc. As a result, ophthalmology has become one of the fastest growing areas of medical artificial intelligence (AI). The deployment of ophthalmological AI diagnosis and treatment system on smart phones is expected to improve the diagnostic efficiency and screening coverage to relieve the strain of medical resources, which has a great development prospect. This review focuses on the prevention and telemedicine progress of eye diseases based on deep learning and smart phones, taking diabetic retinopathy, glaucoma and cataract as examples to describe the specific research, application and prospect of deep learning and smart phones in the management of eye diseases.

在大力发展精准医疗的时代背景下，北京大学第三医院眼科中心率先建立干眼精准医疗平台。通过规范和优化干眼诊疗流程，为患者提供个性化的治疗方案和预防指导意见，有效提高了干眼诊断的精确性与治疗的有效性，同时提升了干眼门诊接诊效能，改善了患者就诊体验。本文将从干眼精准医疗平台体系的建设内容、标准化的检查流程、个性化的诊疗方案等方面进行阐述，并结合实际临床案例，综合分析北京大学第三医院在干眼精准医疗方面进行的探索，展望干眼精准医疗平台的前景与未来。

In the era of developing precision medicine, the Ophthalmic Center of Peking University Third Hospital has taken the lead in establishing a dry eye precision medical platform. By standardizing and optimizing the diagnosis and treatment process of dry eye, this center provides personalized treatment plan and prevention guidance for patients, effectively improves the accuracy of dry eye diagnosis and the effectiveness of treatment, at the same time,improves the reception efficiency of dry eye clinic, and improves the patient’s clinic experience. In this paper, the construction content, standardized inspection process and personalized diagnosis and treatment scheme of dry eye precision medicine platform system will be described. Combined with the actual clinical cases, the exploration of the Peking University Third Hospital in dry eye precision medicine will be comprehensively analyzed, and the future of dry eye precision medical platform will be prospected.

目的：探索基于眼底彩照和人工智能构建冠心病智能诊断系统的可行性。方法：于2013—2014年收集广东省人民医院530例患者共2117张眼底彩照，其中冠心病217例共909张眼底彩照。根据患者有无冠心病的情况进行标记，使用Inception-V3深度卷积神经网络训练人工智能模型，随后使用验证数据判断模型的准确率。计算深度卷积网络模型的准确性、一致率、敏感性、特异性和受试者工作特性曲线下面积(area under the curve，AUC)。结果：在2117张眼底彩照中，1903张用于模型训练，214张用于模型的性能评估。在测试集中，该算法的准确性为98.1%，一致率为98.6%，敏感性为100.0%，特异性为96.7%，AUC为0.988(95%CI：0.974~1.000)。结论：眼底彩照联合人工智能技术可精准判定冠心病，该模型具备较高的敏感性和特异性，但须进一步增加样本量，使用大样本量数据验证该模型，排除过拟合的可能性。

Objective: To explore the feasibility of developing a deep learning algorithm for detecting coronary heart diseases based on fundus color photography and artificial intelligence (AI). Methods: A total of 2 117 fundus  color photographs were taken from 530 patients in Guangdong Provincial People’s Hospital from 2013 to 2014,including 909 fundus color photographs from 217 patients with coronary heart disease (CHD). According to whether the patient had coronary heart disease or not, the Inception-V3 depth convolution neural network was used to train the deep learning model, and then the validation data were used to judge the accuracy of the model. The accuracy, consistency rate, sensitivity and specificity of the deep convolution network model and the area under the working characteristic curve (AUC) were calculated. Results: Among the 2 117 fundus color photographs, 1 903 were used for model training, and 214 were used to test the accuracy of the model. In the test dataset, the accuracy of the algorithm was 98.1%, the consistency rate was 98.6%, the sensitivity was 100.0%, and the specificity was 96.7%. The AUC was 0.988 (95% CI, 0.974–1.000). Conclusion: The combination of fundus color photography and artificial intelligence can achieve the accurate diagnosis of the coronary heart disease, and the model has high sensitivity and specificity. However, future studies are warranted to validate our model and exclude the possibility of over-fitting.

目的：分析医学人工智能通识课程“眼科人工智能的研发与应用”的开展效果，为相关医学人工智能通识课程的开展提供参考和借鉴。方法：纵向观察性研究。观察分析2020年秋季学期眼科人工智能的研发与应用通识课程学生人群，课程考核结果以及学生对课程的整体评价。结果：共有118名本科生同学参与了课程学习。其中大部分为低年级临床医学专业本科生。期中考核得分为77.21±10.07，有56位同学(47.46%)达到80分以上。期末考核得分为82.24±6.77，有91位同学(77.12%)达到80分以上。同学对课程的评分为98.76±3.55，超过90%的同学表示课程备课认真、授课条理清晰、表达准确。结论：本课程的顺利进展证明医学人工智能联合教学模式的可行性，理论和实践穿插的教学设置帮助同学们更好地掌握知识技术，完成教学目标。

Objective: To analyze the effectiveness of medical education curriculum named “Development and Application of Ophthalmic Artificial Intelligence”, and provide reference for the development of other related curriculums. Methods: Longitudinal observational study method was adopted. During the fall semester of 2020, we conducted an education curriculum named “Development and Application of Ophthalmic Artificial Intelligence” and analyzed the results of mid-term and final examinations, and curriculum evaluation of students. Results: There were 118 undergraduate students taking the course and most of them were junior students majoring in clinical medicine. The score of the mid-term examination was in the range of 77.2±10.07, and 56 students (47.46%) got more than 80 points. The score of the final examination was in the range of 82.24±6.77, and 91 students (77.12%) got more than 80 points. The score of course evaluation of students was in the range of 98.76±3.55, and more than 90% of the students thought that teachers have made full preparations before class, together with clear teaching logic and accurate expressions in class. Conclusion: The smooth progress of our course proved the feasibility of medical artificial intelligence teaching. The teaching setting interspersed with theory and practice could help students to master knowledge and technology better, so as to achieve the teaching objectives.