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：分析肺炎克雷伯菌导致内源性眼内炎在糖尿病患者中的临床特征，总结治疗经验及评估其预后。方法：回顾性病例分析2019年1月至2022年3月期间就诊于山东中医药大学附属眼科医院的肺炎克雷伯菌导致的内源性眼内炎糖尿病患者7例(8眼)。分析其年龄、性别、感染灶来源、就诊时间、治疗前后视力、眼压、裂隙灯检查、眼底检查、眼科B超、治疗方式、感染控制及复发情况。结果：7例患者年龄(63±17.6)岁。男性5例(71.4%)，女性2例(28.6%)。术后7眼(87.5%)视力NLP，1眼(12.5%)LogMAR视力0.2。视力与患者就诊时间及就诊时视力有关。6例(85.7%)就诊前发热。8眼(100%)结膜混合充血，1眼(12.5%)前房积脓。7眼(87.5%)行玻璃体切割术联合玻璃体腔注药术，1眼(12.5%)行单纯玻璃体腔注药术。8眼感染均控制，无眼球摘除。随访期间眼压正常，无感染复发。结论：肺炎克雷伯菌是内源性眼内炎的主要致病菌，易在糖尿病人群中发生。发病迅速进展快，早期临床表现不典型易被误诊，其预后和病程的长短及治疗的时机密切相关，尽早地治疗可挽回部分视力。

Objective: To analyze the clinical characteristics of endogenous endophthalmitis caused by Klebsiella pneumoniae in diabetic patients, and summarize the treatment experience and evaluate its prognosis. Methods: A retrospective case analysis was performed on 7 patients (8 eyes) with endogenous endophthalmitis caused by Klebsiella pneumoniae, who were admitted to the Affiliated Eye Hospital of Shandong University of Traditional Chinese Medicine from January 2019 to August 2022. The age, gender, origin of infection, time of treatment, visual acuity before and after treatment, intraocular pressure, slit lamp examination, fundus examination, ophthalmic B-mode ultrasound, treatment methods, infection control and recurrence were analyzed. Results: The mean age of the seven patients was (63±17.6). There were five males (71.4%) and 2 females (28.6%). Postoperative visual acuity was NLP in seven eyes (87.5%) and LogMAR visual acuity was 0.2 in one eye (12.5%). Visual acuity was related to the patient’s visit time and the visual acuity at visit. Six cases (85.7%) had fever before treatment. Fever was a risk factor for Klebsiella pneumoniae endophthalmitis infection. Eight eyes (100%) had mixed conjunctival congestion, and one eye (12.5%) had abscess in the anterior chamber. Seven eyes (87.5%) underwent vitrectomy combined with intravitreal drug injection, and one eye (12.5%) underwent intravitreal drug injection alone. Infections were controlled in all eight eyes without enucleation. Intraocular pressure was normal during the follow-up period, and there was no infection recurrence. Conclusions: Klebsiella pneumoniae is the main pathogen of endogenous endophthalmitis and is prone to occur in people with diabetes. The onset of the disease progresses rapidly. The early clinical manifestations are not typical, and the prognosis is closely related to the duration of the disease and the timing of treatment. Early treatment can restore some vision.