眼健康是国民健康的重要组成部分，包括盲在内的视觉损伤严重影响人民群众的身体健康和生活质量，加重家庭和社会负担，威胁社会经济生产活动，是涉及民生的重大公共卫生问题和社会问题。弱视作为幼儿期起病的主要视觉障碍性疾病之一，是致使青少年低视力的首要因素，影响青少年自身学业和心理健康，增加致盲风险，故做好弱视的预防及康复工作刻不容缓。通过梳理研究发现，国内外对弱视的传统治疗方法有遮盖疗法、屈光矫正、压抑疗法等，知觉学习、视功能训练、电子视频游戏、针灸等则是近年逐渐新兴起并被广泛运用的弱视康复治疗方法，近年来关于年龄对弱视康复治疗影响的相关研究也较多。通过整理前人研究成果，提出建立儿童青少年视力档案、建立五位一体弱视康复治疗布局模式、进行联合临床治疗青少年弱视的对策，以期为青少年弱视提供康复治疗手段参考和选择，促进青少年弱视康复治疗眼健康事业发展。

Eye health is an important part of national health. Visual impairment, including blindness, seriously affects people’s physical health and quality of life, increases the burden on families and society, threatens social and economic production activities, and is a major public health and social problem related to people’s livelihood. Amblyopia,as one of the main visual disorders in early childhood, is the primary factor causing low vision in adolescents, which affects their academic and mental health and increases the risk of blindness. Therefore, it is urgent to do a good job in the prevention and rehabilitation of amblyopia. By summarizing existing studies, it is found that traditional treatment methods for amblyopia at home and abroad include occlusion therapy, refractive correction, and depressive therapy, while perceptual learning, visual function training, electronic video games, acupuncture and so on are gradually emerging in recent years and widely used in recent years. There are numerous studies on the impact of age on the rehabilitation of amblyopia. By sorting out the previous research results, this paper puts forward the countermeasures of establishing visual acuity files for children and adolescents, establishing the five- in-one rehabilitation treatment layout model, and combining clinical treatment for adolescent amblyopia, in order to provide reference and choice for the rehabilitation treatment of adolescent amblyopia, and promote the development of the eye health cause of adolescent amblyopia rehabilitation.

目的：探讨督导式教学门诊在眼科住院医师规范化培训中的具体实践和教学效果。方法：通过合理排班、限制号源等措施设立每周固定的督导式教学门诊时间，安排老师和学员出诊；在教学门诊开展4个月后，通过问卷调查和临床技能考核的形式采集反馈意见并评估教学效果。 结果：共有16名老师和8名学员参加了督导式教学门诊，调查问卷结果显示100%的带教老师和学员认可该教学模式，参加过教学门诊的学员临床技能考核得分显著高于对照组(t =3.631， P<0.05)。结论：督导式教学门诊应用于眼科住院医师规范化培训具有实际可行性，并可以提高学员的临床技能水平。

Objective: To explore the application and effects of supervised teaching clinic in standardized training of ophthalmology residents. Methods: A weekly supervised teaching clinic was set through reasonable scheduling and limiting the registration numbers. After 4 months of application, feedbacks were collected through questionnaire survey from both the teachers and residents. Clinical skills assessments were also taken to evaluate the teaching effect. Results: A total of 16 teachers and 8 residents participated in the supervised teaching clinic. The results of the questionnaire showed that 100% of the teachers and residents agreed with the teaching mode. The clinical skill assessment scores of the residents who participated in the teaching clinic were significantly higher than those of the control group (t=3.631, P<0.05). Conclusion: The application of supervised teaching clinic in standardized training of ophthalmology residents is feasible and can improve the clinical skills of the residents. 

近年来，使用人工智能(artificial intelligence，AI)技术对临床大数据及图像进行分析，对疾病做出智能诊断、预测并提出诊疗决策，AI正逐步成为辅助临床及科研的先进技术。生物样本库作为收集临床信息和样本供科研使用的平台，是临床与科研的桥梁，也是临床信息与科研数据的集成平台。影响生物样本库使用效率及合理共享的因素有信息化建设水平不均衡、获取的临床及检验信息不完全、各库之间信息不对称等。本文对AI和区块链技术在生物样本库建设中的具体应用场景进行探讨，展望大数据时代智能生物样本库信息化建设的核心方向。

In recent years, artificial intelligence (AI) technology has been applied to analyze clinical big data and images and then make intelligent diagnosis, prediction and treatment decisions. It is gradually becoming an advanced technology to assist clinical and scientific research. Biobank is a platform for collecting clinical information and samples for scientific research, serving as a bridge between clinical and scientific research. It is also an integrated platform of clinical information and scientific research data. However, there are some challenges. First, clinical and laboratory information obtained is incomplete. Additionally, the information among different databases is asymmetric, which seriously impedes the information sharing among different Biobanks. In this article, the specific application scenarios of AI technology and blockchain in the construction of a Biobank were discussed, aiming to pinpoint the core direction of the information construction of an intelligent Biobank in the era of big data.

当下，我国眼科的发展存在失衡现象，大城市与农村及偏远地区在眼科相关诊疗设施水平、诊疗技术等方面存在巨大差异，仍需探寻新的智能诊疗模式以解决失衡问题。由于眼球是唯一可以直接观察人体血管和神经的器官，眼部可反映其他脏器的健康状态，部分眼科检查的医学图像可对眼部疾病做出诊断等特点，眼科开展人工智能(artificial intelligence，AI)具有独到的优势。此外，人工智能可在一定程度上提高跨时间空间传递信息的精准度及效率。人工智能在眼科及远程信息传递的优势为解决眼科发展失衡状况提供了助力。本文从眼科人工智能在眼科远程医疗相关应用的角度，主要分析并总结当下我国人工智能在眼科相关疾病远程医疗中的发展程度、所具优势以及存在问题，并讨论眼科人工智能在远程医疗的应用展望。

At present, there is an imbalance in the development of ophthalmology in China. There are huge differences in the level of ophthalmology related facilities, diagnosis and treatment technologies between big cities and rural, remote areas. New intelligent diagnosis and treatment models are still needed to solve the imbalance. Since the eye is the only organ that can directly observe the blood vessels and nerves of the human body, the eye can reflect the health status of other organs and diagnosis of eye diseases based on medical images of some ophthalmic examinations can be made as well as other characteristics. Therefore, the development of artificial intelligence in ophthalmology has unique advantages. In addition, artificial intelligence can improve the accuracy and efficiency of information transmission across time and space to a certain extent. The advantages of artificial intelligence in ophthalmology and telematics are helping to solve the imbalance in ophthalmology development. From the perspective of the application of ophthalmic artificial intelligence in telemedicine, this paper mainly analyzes and summarizes the development degree, advantages and existing problems of artificial intelligence in the telemedicine of ophthalmic diseases in China, and discusses the prospect of the application of ophthalmic artificial intelligence in telemedicine.

帕金森病(Parkinson’s disease，PD)是老年人常见的神经系统退行性疾病，眼部及视觉功能障碍是PD常见的非运动症状之一，进一步影响其生活质量。已有研究表明PD患者视网膜内存在多巴胺浓度的减少以及α突触核蛋白的沉积。目前，PD仍缺乏有效的早期诊断及病情评估工具，光学相干断层扫描及光学相干断层扫描血管成像技术可以显示视网膜各层微细结构及微血管的异常，应用该技术研究者发现PD患者视乳头旁视网膜神经纤维层及黄斑区视网膜的厚度均存在不同程度的变薄，视网膜浅层及深层毛细血管丛的毛细血管密度和复杂性下降。进一步研究者应用该技术在PD临床应用中进行了探索，并发现其可用于检测早期PD中发生的病理变化，反映疾病的病程及严重程度，并且在鉴别诊断中起到一定的作用。总而言之，视网膜相关检测可能成为评估PD患者脑病理严重程度的指标，并且帮助疾病诊断和监测疾病的进展，不过这仍需要大样本、多中心的重复研究以提供更多理论依据。

Parkinson’s disease is a common neurodegenerative disease in the elderly, and ocular and visual dysfunction is one of the common non-motor symptoms of PD, further affecting PD patients’quality of life. Reduced dopamine concentrations and deposition of α-synuclein in the retina of PD patients have been shown in studies. At present, there is still a lack of effective tools for early diagnosis and assessment of PD. Optical coherence tomography and optical coherence tomography angiography can reveal abnormalities in the microstructure and microvasculature of the retinal layers, and researchers applying these techniques have found that the thickness of the parapapillary retinal nerve fiber layer and the retina in the macula in PD patients have had varying degrees of thinning, and the density and complexity of capillaries in the superficial and deep capillary plexus of the retina have been reduced. Further, investigators have explored the clinical application of these techniques in PD and have found that they can be used to detect pathological changes occurring in early PD, reflect the course and severity of the disease, and play a role in differential diagnosis. In conclusion, retinal-correlated testing may be an indicator to assess the severity of brain pathology in PD patients and to aid in disease diagnosis and monitoring the progression of PD, although large sample, multicenter replication studies are still needed to provide more reliable results.

大型语言模型（large language models, LLMs）在眼科的应用为医疗领域带来了巨大的潜力，尤其是在提升诊断效率、优化医患沟通和促进个性化医疗方面。通过自然语言处理技术，LLMs可以协助医生进行临床数据的归纳和分析，可以结合患者的病史、影像资料和症状描述，提供精准的辅助诊断，并在复杂病例中提供参考。LLMs还可以帮助医生快速撰写病历报告，改善医疗记录管理效率。在医患沟通中，LLMs能够通过生成通俗易懂的解释，帮助患者理解疾病状况及治疗方案，缩短医生与患者之间的沟通障碍。在远程医疗场景下，LLMs可通过实时分析患者上传的图像文本信息，提供初步诊断建议，助力医生远程诊疗。个性化医疗也是LLMs的重要应用方向，借助患者的遗传数据和生活习惯，可以帮助医生制定更为精准的个性化治疗方案，并预测手术后的恢复情况。此外，LLMs可以通过与临床数据的不断交互进行自我优化，提升其在眼科诊疗中的智能化程度。尽管LLMs在眼科领域的应用前景广阔，但仍面临数据隐私、模型解释性、语言理解等方面的挑战。未来LLMs将继续作为医生的辅助工具，形成“人机协同”的诊疗新模式，为患者提供更好、更精准的医疗服务。

The application of Large Language Models (LLMs) in ophthalmology presents tremendous potential for the healthcare field, particularly in enhancing diagnostic efficiency, optimizing doctor-patient communication, and promoting personalized medicine. Through natural language processing technology, LLMs can assist doctors in summarizing and analyzing clinical data. They can integrate a patient's medical history, imaging data, and symptom descriptions to provide precise diagnostic support and reference for complex cases. LLMs can also help physicians quickly draft case reports, improving the management efficiency of medical records. In doctor-patient communication, LLMs can generate easy-to-understand explanations that help patients comprehend their conditions and treatment plans, thereby reducing communication barriers between doctors and patients. In telemedicine scenarios, LLMs can provide preliminary diagnostic suggestions by real-time analyzing images and textual information uploaded by patients, aiding doctors in remote diagnosis and treatment.

Personalized medicine is another significant application direction for LLMs. By utilizing patients' genetic data and lifestyle habits, LLMs can assist physicians in formulating more precise personalized treatment plans and predicting postoperative recovery outcomes. Additionally, LLMs can self-optimize through continuous interaction with clinical data, enhancing their intelligence in ophthalmic diagnosis and treatment. Despite the broad application prospects of LLMs in the field of ophthalmology, challenges remain, including data privacy, model interpretability, and language understanding. In the future,  LLMs will continue to serve as auxiliary tools for physicians, forming a new model of "human-machine collaboration" in diagnosis and treatment, ultimately providing better and more precise medical services to patients.

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.

慢性中心性浆液性脉络膜视网膜病变(cCSC)以广泛的脉络膜视网膜异常为特征，包括脉络膜血管扩张及其引发的弥漫性视网膜色素上皮病变和浆液性视网膜脱离，常累及黄斑区，引起视功能损害。传统观点认为其可能由急性CSC演变而来，但近期研究显示两者在临床上存在明显差异。其病情反复、迁延，预后较差。随着光学相干断层扫描血管造影(OCTA)、超广角成像和en face重建成像等新多模式影像(MMI)技术的出现和人工智能及机器学习的发展，更多有意义的cCSC影像学特征不断出现。文章详细介绍了cCSC在眼底成像、眼底自发荧光(FAF)、光学相干断层扫描(OCT)、眼底荧光素血管造影(FFA)、吲哚菁绿血管造影和OCTA等影像技术中的表现，并探讨了人工智能在识别CSC分类及其OCT 生物标志物等方面的应用。不同影像技术在cCSC的诊断和研究中各有优势，如FAF可能是评估疾病进展及变化的有效手段，OCT可更直观地观察视网膜结构的改变，FFA是识别渗漏点的重要检查手段，而OCTA可能是评估脉络膜微循环的的最佳手段等。这些MMI研究进展为深入了解cCSC的病理生理机制及临床特征提供了重要线索，有助于提高诊断的准确性和效率，改善患者的预后和生活质量。

Chronic central serous chorioretinopathy (cCSC) is characterized by extensive retinochoroidal abnormalities. This includes difuse retinal pigment epitheliopathy and serous retinal detachment associated with choroidal vasodilatation, ofen involving the macula and cause visual impairment. It was originally considered that it might evolve from acute CSC, but recent studies have shown significant clinical differences between the two. It tends to recur, be prolonged, and have an unfavorable prognosis. With the advent of new multimodal imaging (MMI) techniques such as optical coherence tomography angiography (OCTA), ultra-wide-feld imaging, and en face reconstruction imaging, along with the advancement of artificial intelligence and machine learning, more significant cCSC imaging characteristics have been constantly emerging. Tis article provides a comprehensive overview of cCSC’s imaging features across various modalities, including fundus photography, fundus autofluorescence (FAF), optical coherence tomography (OCT), fuorescein angiography (FFA), indocyanine green angiography, and OCTA. It also explores the application of artifcial intelligence in identifying CSC classifications and OCT biomarkers. Different imaging techniques have their own advantages in the diagnosis and study of cCSC, such as FAF being an efective means to assess disease progression and changes, OCT providing a more intuitive observation of retinal structural changes, FFA being an important tool for identifying leakage points, and OCTA possibly being the best means to assess choroidal microcirculation. Tese MMI research advancements ofer crucial insights for clinicians, aiding in more accurate diagnosis and efective treatment, thereby potentially improving patient outcomes and quality of life.

目的：探讨一站式玻璃体腔注药中心成立前后不同管理模式下的成效，分析其对患者就医时间和就医体验的影响。方法：采用回顾性临床研究。选择2023年1月—2024年3月在汕头大学·香港中文大学联 合汕头国际眼科中心接受玻璃体腔注药的2955例患者纳入研究。将2023年1月—2023年8月玻璃体腔注 药中心成立前接受玻璃体腔注药的1399例患者作为对照组；2023年9月—2024年3月玻璃体腔注药中心成立后接受玻璃体腔注药的1556例患者作为观察组。对照组采用常规日间手术流程，观察组成立一 站式玻璃体腔注药中心，优化诊疗和护理服务流程。通过使用问卷调查比较两组患者就医期间从预约手术、手术当天到术后复查各节点的等待时间、健康教育知晓率、患者满意度及不良事件发生率的差异。结果：问卷调查结果显示，对照组、观察组患者间预约等待手术时间分别为(3.93±2.98) d、 (1.34±2.38) d，手术时间分别为(2.53±2.11) min、(1.93±1.82) min，在院时间分别为(313.62±184.96) min、(85.43±34.14) min，术后复查耗时分别为(45.92±48.44) min、(25.82±16.21) min，差异均有统计学意义(P＜0.001)；患者的总体健康教育知晓率成立前后分别为(95.50%、98.70%)，差异有统计学意义 (χ2 =16.09，P＜0.001)；患者满意度调查结果显示，各项就医体验选项“非常满意”的占比成立后比 成立前明显提高。结论:一站式玻璃体腔注药中心护理模式简化了就医流程，极大地减少了患者就医期 间从预约手术、手术当天到术后复查各节点的等待时间、可显著提升工作效率，明显改善患者整体就 医体验。

To explore the application effects of different nursing models before and after the establishment of a one-stop intravitreal injection center, and to analyze their impact on patient's medical time and experience. Methods: A retrospective clinical study was conducted. From January 2023 to March 2024, 2955 patients who received anti-VEGF drug treatment at the Shantou International Eye Center, a joint initiative of Shantou University and the Chinese University of Hong Kong, were included in the study. The 1399 patients who received anti-VEGF drug treatment before the establishment of the intravitreal injection center from January 2023 to August 2023 were set as the control group; the 1556 patients who received anti-VEGF drug treatment after the establishment of the intravitreal injection center from September 2023 to March 2024 were set as the observation group. The control group followed the routine day surgery process, while the observation group established a one-stop intravitreal injection center to optimize the diagnosis, treatment, and nursing service process. A questionnaire survey was used to compare the differences in waiting time at various points from appointment to surgery, on the day of surgery, and postoperative review, health education awareness rate, patient satisfaction, and adverse event rate between the two groups. Results: The questionnaire survey showed that the waiting time for surgery between the control group and the observation group was (3.93±2.98) d, (1.34±2.38) d, respectively, the surgery time was (2.53±2.11) min, (1.93±1.82) mi, the in-hospital time was (313.62±184.96 min, 85.43±34.14) min, and the postoperative review time was (45.92±48.44) min, (25.82±16.21) min, with all differences being statistically significant (P <0.001); the overall health education awareness rate before and after the establishment was (95.50%, 98.70%), with a significant difference (P <0.001, χ²=16.09); the patient satisfaction survey showed that the proportion of "very satisfied" in various medical experience options was significantly higher after the establishment than before. Conclusions: The one-stop intravitreal injection center nursing model has simplified the medical process, greatly reducing the waiting time at various points from appointment to surgery, on the day of surgery, and postoperative review, significantly improving work efficiency, and significantly improving the overall medical experience of patients.