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.

目的：评价StarEyes 900(万灵帮桥，中国)与IOLMaster 500(蔡司，德国)2种眼科光学生物测量仪测量健康受试者眼部参数的差异性、相关性及一致性。方法：前瞻性观察2021年6月至7月于中山大学中山眼科中心进行眼部检查的62例健康受试者共124只眼，分别通过StarEyes 900与IOLMaster 500完成眼轴长度(axial length，AL)、最小角膜屈光力径线上角膜曲率(keratometry for the flattest meridian，Kf)、最大角膜屈光力径线上角膜曲率(keratometry for the steepest meridian，Ks)、平均角膜曲率(mean keratometry，Km)、角膜白到白直径(white-to-white corneal diameter，WTW)等参数的测量，采用配对t检验、Pearson相关分析和Bland-Altman法对其测量结果的差异进行评价。结果：StarEyes 900与IOLMaster 500测量的AL分别为(24.18±1.08) mm和(24.16±1.08) mm；Kf分别为(42.84±1.65) D和(43.04±1.57) D；Ks分别为(44.34±1.90) D和(44.17±1.80) D；Km分别为(43.59±1.73) D和(43.61±1.64) D；WTW分别为(11.64±0.29) mm和(11.64±0.30) mm。StarEyes 900与IOLMaster 500在测量Km、WTW时，其差异无统计学意义(P>0.05)，而在AL、Kf、Ks的测量上差异有统计学意义(P<0.01)。其中StarEyes 900所测的AL和Ks值大于IOLMaster 500，而Kf、Km和WTW值则小于IOLMaster 500。经Pearson相关分析，2种仪器的测量结果均表现出较高的相关性；经Bland-Altman法评价，2种仪器的测量结果均表现出较高的一致性。结论：StarEyes 900与IOLMaster 500测量的Km、WTW均表现出较高的一致性，2种方法可互为参考；测量的AL、Kf、Ks存在的差异具有统计学意义；各项参数的测量均具有较好的相关性和一致性。

Objective: To evaluate the difference, correlation and agreement of eye parameters measured by StarEyes 900 visual function analyzer (Wan Ling Bang Qiao, China) and IOLMaster 500 (Carl Zeiss, Germany) swept-source optical coherence tomography biometer. Methods: A prospective study was designed involving 62 healthy subjects (124 eyes) undergoing ophthalmic examinations in Zhongshan Ophthalmic Center from June 2021 to July 2021. Data from their both eyes were selected for analysis in all patients. Axial length (AL), keratometry for the steepest meridian (Ks), keratometry for the flattest meridian (Kf), mean keratometry (Km) and corneal diameter (WTW) were measured by the StarEyes 900 visual function analyzer and IOLMaster 500 swept-source optical coherence tomography biometer. A paired t-test was used to analyze the differences in measurement results. The Pearson correlation coefficient was used to analyze the correlation. Bland-Airman method was used to assess the agreement of the instruments. Results: The AL, Kf, Ks, Km and WTW obtained by StarEyes 900 and IOLMaster 500 were (24.18±1.08) mm and (24.16±1.08) mm, (42.84±1.65) D and (43.04±1.57) D, (44.34±1.90) D and (44.17±1.80) D, (43.59±1.73) D and (43.61±1.64) D, and (11.64±0.29) mm and (11.64±0.30) mm, respectively. The Km and WTW of the two devices showed no significant difference (P>0.05), while the AL, Ks and Kf showed significant differences (all P<0.01). The AL and Ks obtained by StarEyes 900 were higher than by IOLMaster 500, while the Kf, Km and WTW were lower. The measurements of five aforementioned biometric parameters by both devices showed good correlation by Pearson correlation coefficient and good agreement by Bland-Airman. Conclusion: The Km and WTW measured by the two devices showed no significant difference, and provided references to one another. The difference in AL, Kf and Ks between the two devices showed significant differences. All of the measurements showed good correlation by Pearson correlation coefficient and good agreement by Bland-Airman.