人工智能(artificial intelligence，AI)为解决中国患者“看病难”问题提供了可行方案。眼科AI已实现为患者提供筛查、远程诊断及治疗建议等方面的服务，能显著减轻医疗资源不足的压力和患者的经济负担。而AI的应用过程中，给医疗管理带来的挑战应引起重视。本文从医疗管理的角度，总结分析AI在眼科医疗过程中，尤其是交接环节中出现的主要问题，提出对策与建议，并讨论AI在眼科医疗的应用展望。
Artificial intelligence (AI) has been proposed as a potential solution to address the shortage of ophthalmologists in China. With the increasingly extensive application of AI in the field of ophthalmology, many potential patients with eye diseases have access to a higher quality of medical services. At the same time, new challenges will emerge and proliferate with the advancement of AI application. This paper focuses on the patient handoffs process and discusses two challenges brought by the application of AI, namely “communication” and “standardization”. Natural language processing techniques and the development of standardized databases are proposed to solve each of these challenges. The application prospects of AI in ophthalmology are eventually discussed.
目的：探讨青光眼日间手术患者的自我管理行为现状及影响因素分析。方法：采用便利抽样法选取2021年9月—2022年5月于广州市某三级甲等眼科专科医院就诊的223例青光眼日间手术患者。采用一般资料调查表、青光眼自我管理行为量表、慢性疾病自我效能量表和青光眼知识学习问卷进行问卷调查。结果：青光眼日间手术患者的自我管理行为得分为(54.03±6.95)分，其中生活调整维度得分最低。慢性病自我效能与自我管理行为呈正相关(r=0.368, P<0.001)。疾病知识与自我管理行为无显著相关性(r=0.077, P=0.252)。多因素线性回归分析结果显示，患者的文化程度(P<0.001)和自我效能(P=0.028)是自我管理行为的影响因素，可解释自我管理行为总变异的12.4%。结论：青光眼日间手术患者具有良好的自我管理行为，较低的自我效能和文化程度是自我管理行为的危险因素，因此应优先提高患者的自我效能，并提供个性化教育。
Objective: To determine self-management and its association with self-efficacy and knowledge among glaucoma patients undergoing day surgery. Methods: A total of 223 glaucoma patients were recruited from September 2021 to May 2022and they were investigated with the Glaucoma Self Management Questionnaire (GSMQ), The Self- Efficacy in Chronic Disease Scale (SECD-6), and the glaucoma knowledge questionnaire. Results: Of the 223 study participants, the study population had a total GSMQ score of 54.03±6.95 with the lowest score found in the life adjustment dimension. The total SECD-6 score was showing a significantly positive correlation with the total GSMQ score(r =0.368, P <0.001). The total score of disease knowledge was without significant correlation with the total GSMQ score (r =0.077, P =0.252). Multivariate linear regression analysis showed that self-efficacy (P <0.001) and education level was independently associated with self-management(P =0.028). Conclusions: Glaucoma patients undergoing daytime surgery demonstrated good overall self-management, yet further improvement was required in terms of life adjustment. Low self-efficacy and educational level were identified as risk factors for self-management. Therefore, self-management programs should prioritize enhancing patients' self-efficacy and delivering individualized education.
目的：结合眼科住院医师规范化培训(住培)的特点，建立基于钉钉平台的全面质量管理模式(total quality management, TQM)，探索一种高效的顺应时代特征的眼科教学管理模式。方法：研究团队依托中山大学中山眼科中心，选取82名眼科四证合一的住培一年级的学生作为研究对象，并将其随机分为两组，试验组41人采用基于钉钉平台的TQM模式进行全过程教学管理，采用全员参与、全程跟踪、全面评价的管理模式以保障教学质量。对照组41人接受传统的教学管理模式。观察指标为两组间教学前后测试分数、教学后满意度调查的问卷得分等。结果：通过对两组学生进行课前课后的测试，TQM模式组相较于传统模式组在学习成绩有所提升，课前课后分数的差值分别为40(30,40)分和30(20,50)分，比较差异有统计学意义(P =0.031)。问卷调查结果显示，两组满意度总分比较差异无统计学意义[10(10,10) 分 vs. 10(9,10)分，P =0.207]，但在满意度分项内容掌握性上，TQM模式组分值高于传统模式组[5(5,5)分 vs. 5(4,5)分，P =0.046]。结论：基于钉钉平台的TQM模式在眼科教学中能够有效提高住培的教学质量与学生满意度，相比传统教学管理模式具有更大的教学优势，可为眼科住培提供了一种创新且实用的教学管理模式，对于培养适应时代需求的高水平眼科医师具有重要意义。
Objective: To combine the characteristics of standardized training for ophthalmic resident physicians, establishes a Total Quality Management (TQM) model based on the DingTalk platform, and explored an efficient ophthalmic teaching management model that adapts to the characteristics of the times. Methods: The research team, based at Zhongshan Ophthalmic Center, selected 82 first-year postgraduate students undergoing the national standardized training for resident doctors (STRD) as participants, randomly allocating them into two groups. The experimental group consisting of 41 trainees received TQM-modeled online learning via the DingTalk platform, adopting a management model of full participation, full process tracking, and comprehensive evaluation to ensure teaching quality. While the control group, also comprising 41 trainees, underwent traditional offline instruction. The TQM group engaged in live streaming lectures on the DingTalk platform, whereas the conventional group continued with face-to-face teaching in classroom. Data including pre- and post-teaching scores, as well as scores from satisfaction surveys are analyzed. Results: Comparing pre- and post-teaching scores, significant statistical differences were found between the TQM and traditional groups, with mean score improvements of 40(30,40) points and 30(20,50) points, respectively, indicating statistical significance (P =0.013). Furthermore, the questionnaire survey revealed that the TQM group scored higher than the traditional group in aspects such as course design, clinical relevance, content mastery, and instructor satisfaction. In addition, the questionnaire survey showed that there was no statistically significant difference in the total satisfaction score between the two groups (10(10,10) points vs. 10(9,10)points P =0.207), but in terms of mastery of satisfaction sub items, the TQM model group scored higher than the traditional model group (5(5,5) points vs. 5(4,5) points, P =0.046). Conclusions: The application of a TQM-based model on the DingTalk platform significantly enhances the teaching quality and student satisfaction in the residency training of ophthalmologists, demonstrating greater pedagogical advantages over traditional methods. This efficient ophthalmic teaching management model thus provides a promising solution for standardized residency training in ophthalmology, and holds considerable importance for nurturing highly competent ophthalmologists who can meet the demands of the current era.
目的：建立和验证一个涉及多级临床场景的白内障协作通用的人工智能(artificial intelligence,AI)管理平台，探索基于AI的医疗转诊模式，以提高协作效率和资源覆盖率。方法：训练和验证的数据集来自中国AI医学联盟，涵盖多级医疗机构和采集模式。使用三步策略对数据集进行标记: 1)识别采集模式；2)白内障诊断包括正常晶体眼、白内障眼或白内障术后眼；3)从病因和严重程度检测需转诊的白内障患者。此外，将白内障AI系统与真实世界中的居家自我监测、初级医疗保健机构和专科医院等多级转诊模式相结合。结果：通用AI平台和多级协作模式在三步任务中表现出可靠的诊断性能: 1)识别采集模式的受试者操作特征(receiver operating characteristic curve,ROC)曲线下面积(area under the curve,AUC)为99.28%~99.71%)；2)白内障诊断对正常晶体眼、白内障或术后眼，在散瞳-裂隙灯模式下的AUC分别为99.82%、99.96%和99.93%，其他采集模式的AUC均 > 99%；3)需转诊白内障的检测(在所有测试中AUC >91%)。在真实世界的三级转诊模式中，该系统建议30.3%的人转诊，与传统模式相比，眼科医生与人群服务比率大幅提高了10.2倍。结论：通用AI平台和多级协作模式显示了准确的白内障诊断性能和有效的白内障转诊服务。建议AI的医疗转诊模式扩展应用到其他常见疾病和资源密集型情景当中。
Objective: To establish and validate a universal artificial intelligence (AI) platform for collaborative management of cataracts involving multilevel clinical scenarios and explored an AI-based medical referral pattern to improve collaborative efficiency and resource coverage. Methods: The training and validation datasets were derived from the Chinese Medical Alliance for Artificial Intelligence, covering multilevel healthcare facilities and capture modes. The datasets were labelled using a three step strategy: (1)capture mode recognition; (2) cataract diagnosis as a normal lens, cataract or a postoperative eye and (3) detection of referable cataracts with respect to aetiology and severity. Moreover, we integrated the cataract AI agent with a real-world multilevel referral pattern involving self-monitoring at home, primary healthcare and specialised hospital services. Results: The universal AI platform and multilevel collaborative pattern showed robust diagnostic performance in three-step tasks: (1) capture mode recognition (area under the curve (AUC) 99.28%–99.71%), (2) cataract diagnosis (normal lens, cataract or postoperative eye with AUCs of 99.82%, 99.96% and 99.93% for mydriatic-slit lamp mode and AUCs >99% for other capture modes) and (3)detection of referable cataracts (AUCs >91% in all tests). In the real-world tertiary referral pattern, the agent suggested 30.3% of people be ’referred’, substantially increasing the ophthalmologist-to-population service ratio by 10.2-fold compared with the traditional pattern. Conclusions: The universal AI platform and multilevel collaborative pattern showed robust diagnostic performance and effective service for cataracts. The context of our AI-based medical referral pattern will be extended to other common disease conditions and resource-intensive situations.
目的：评价并汇总眼科成人日间手术患者病区护理管理的最佳证据，提高临床护理质量。方法：检索国内外数据库建库至2022年6月的日间手术患者病区护理管理的相关证据，包括系统评价、临床决策、证据总结、指南及专家共识。由2名研究人员独立对文献进行质量评价后，根据主题对证据进行提取和汇总。结果：根据纳入标准，共筛选出13篇文献，包括5篇专家共识、3篇证据总结、1篇循证实践、2篇系统评价、1篇指南。通过文献阅读、证据提取和归类，从日间手术护士准入资质、制定临床护理路径、院前管理、病历标准化、手术当日术前管理、术后管理、出院评估、康复及随访指导8个方面形成17条最佳证据。结论：该项目总结了眼科成人日间手术患者病区护理管理的最佳证据，可为护理管理者制定眼科日间手术病区流程方案、实践标准提供循证依据。
Objective: To evaluate and summarize the evidences of nursing management of ophthalmic postoperative adult patients intra-day ward, and improve the quality of clinical nursing. Methods: The related databases were searched from the establishment to June 2022. The searching contents include systematic review, clinical decision-making, evidence summary, guidelines and expert consensus on nursing management in postoperative patients intra-day wards at home and aboard. Based on the theme, the evidences were extracted and summarized after independent literature quality evaluation was conducted by 2 researchers. Results: Base on the inclusion criteria, a total of 13 pieces of literature were selected, including 5 expert consensus, 3 evidence summaries, 1 evidence-based practice, 2 systematic reviews and 1 guideline. Through literature review, evidence extraction and classification, a total of 17 pieces of evidence on 8 aspects were summarized, including admission qualifications for daytime surgical nurses, development of clinical nursing path, pre-hospital management, medical record standardization, preoperative management on the day of surgery, postoperative management, discharge assessment, rehabilitation and follow-up guidance. Conclusion: This article summarized the best evidence of nursing management for ophthalmic adult day surgery patients in intra-day ward,to provide scientific evidences for nursing managers to develop ophthalmic intra-day ward guidelines and practical standards.
糖尿病视网膜病变是糖尿病引起的微血管病变之一，是不可逆性致盲的眼病。根据其病程可分为根据其病程可分为非增殖期和增殖期，其中还包括糖尿病性黄斑水肿。全科医师需要检测量裸眼视力、矫正视力和眼压，通过裂隙灯显微镜评估眼前节以及眼底检查来评估眼部整体情况。控制血糖、血压、血脂对改善预后很重要。需要重视餐前、餐后血糖，糖化血红蛋白和代谢记忆，一线降血压药物包括血管紧张素转化酶抑制剂和血管紧张素Ⅱ受体阻断剂，调脂药物首选他汀类，而非诺贝特有额外的视网膜保护作用。干预生活方式，宣教，早期发现也同样重要。全科医师需要进行眼底筛查和评分，及时转诊至眼科治疗。眼科治疗包括全视网膜激光光凝术、经平坦部玻璃体切除术、玻璃体抗血管内皮生长因子药物注射术。
Diabetic retinopathy is one of the microvascular diseases caused by diabetes, it is an irreversible blindness eye disease. According to its course, it can be divided into non-proliferative diabetic retinopathy and proliferative diabetic retinopathy, including diabetic macular edema. Te general practitioner needs to measure the uncorrected visual acuity, corrected visual acuity intraocular pressure, use the slit lamp microscope to exam the anterior segment and fundus to evaluate the overall condition of the eye. Controlling blood glucose, blood pressure and blood lipid is very important to improve the prognosis. Attach importance to pre- and postprandial blood glucose, glycosylated hemoglobin and metabolic memory should be carried out. The first-line antihypertensive drugs are angiotensin converting enzyme inhibitors and angiotensin II receptor blockers. Statins are the first choice for lipid-lowering drugs, fenofibrate has additional protective efect of retinal. Intervention in lifestyle, education and early detection are is important. Te general practitioner needs to perform fundus screening and scoring, timely refer to ophthalmology department for treatment. Ophthalmic treatment includes panretinal laser photocoagulation, pars plana vitrectomy, and intravitreal injection of anti-vascular endothelial growth factor drugs.
目的：检索并总结开角型青光眼患者眼部用药规范化护理管理的最佳证据，为临床实践提供参考。方法：通过护理循证方法提出实践问题，按照循证证据检索数据库的“6S”分类模型，检索有关开角型青光眼患者眼部用药管理的所有证据资源类型，包括临床指南、最佳实践信息册、证据总结、系统评价和专家共识等。由2名循证护理研究员对纳入文献的质量进行独立评价并进行证据的归纳总结。结果：最终纳入12篇文献，包括4篇指南、3篇证据总结和5篇系统评价；汇总了19条有关开角型青光眼眼部用药管理的最佳证据，包括滴眼技术指导、依从性管理和信息提供3个方面。结论：总结开角型青光眼眼部用药管理的最佳证据，可为临床医务人员管理患者提供参考和借鉴，以达到患者规范用药、控制眼压和延缓疾病进展的目的。
Objective: To retrieve and summarize the best evidence on standardized ocular medication management among open-angle glaucoma patients. Methods: With evidence-based nursing method, practical problemswere identified. According to the “6S” pyramid model of evidence resource, studies on standardized ocular medication management among open-angle glaucoma patients were retrieved, including clinical guidelines, best practice information booklet, systematic reviews, and expert consensus. Two evidence-based nursing researchers independently evaluated the quality of the included literature and summarized the evidence. Results: A total of 12 articles were ultimately enrolled, including 4 clinical guidelines, 3 evidence summaries and 5 systematic reviews. Finally, 3 aspects including 19 pieces of best evidence were summarized, which were Eye drop technical instruction, medication adherence management and related information provision. Conclusion: The best evidence for the medication management of open-angle glaucoma patients were summarized, which provide reference for clinical medical staffs to manage patients, so as to achieve the purpose of standardizing medication,controlling intraocular pressure and preventing disease progression.
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。
