人工智能(artificial intelligence，AI)在白内障手术中的应用越来越广泛，二者结合对于白内障手术的术前诊断和分级管理、术中人工晶状体选择、位置预测及术后管理(视力预测、并发症预测及随访)、手术培训和教学方面均起到巨大的促进作用。诚然，AI在与白内障手术相关的管理、分析和研究中还面临着许多问题，但其广泛的应用前景不可忽视。现对AI在白内障手术治疗和教学中的应用做以总结，并对其未来的发展做出展望。

Artificial intelligence (AI) has been widely used in cataract surgery. The combination of the two can play a great role in improving preoperative diagnosis, grading management of cataract surgery, intraoperative intraocular lens selection and location prediction, postoperative management (vision prediction, complication prediction and follow-up), surgical training and teaching. It is true that AI still faces many problems in the management, analysis and research related to cataract surgery, but its broad application prospects cannot be ignored. This review summarizes the application of AI in cataract surgery and teaching, and the future prospects of AI.

目的：分析角膜后前表面曲率半径比值(B/F比值)与年龄相关性白内障患者术后屈光误差的关系，探讨B/F比值对人工晶状体(intraocular lens,IOL)度数计算精确性的影响。方法：选取2019年3—11月在天津医科大学眼科医院白内障中心就诊，并拟行单眼白内障手术的年龄相关性白内障患者共197例(197眼)，术前应用Pentacam眼前节分析仪测量患者眼前节生物参数，并以B/F比值下限25%、上限25%为界将患者分为下25%组、25%～75%组、上25%组。术后3个月应用全自动电脑验光仪评估患者术后屈光状态，并计算患者术后屈光误差(postoperative refractive error,PE)，比较三组平均屈光误差(mean refractive error,ME)、平均绝对误差(mean absolute error,MAE)、中位数绝对误差(median absolute error,MedAE)以及屈光误差在±0.25、±0.50、±0.75、±1.00、>±1.00 D范围内百分比差异。结果：B/F比值与年龄相关性白内障患者术后屈光误差呈中度相关(r=?0.445, P<0.001)。随着B/F比值增大，患者术后屈光状态由远视向近视漂移，术后3个月MAE、MedAE分别为0.55 D、0.46 D。屈光误差在±0.25、±0.50、±0.75、±1.00、>±1.00 D范围的百分比分别为29.4%、52.8%、71.6%、87.6%、12.7%。根据正常年龄相关性白内障人群B/F比值优化得到的矫正角膜折射指数计算角膜曲率后，MAE、MedAE分别为0.51、0.43 D，均低于矫正前(P<0.05)。结论：B/F比值对年龄相关性白内障患者术后屈光状态有影响。随着B/F比值的增加，白内障患者术后屈光状态由远视逐渐向近视漂移，且B/F比值越偏离正常平均值，患者的屈光误差绝对值越大。

Objective: To analyze the relationship between corneal B/F ratio and postoperative refractive error in age-related cataract patients, and to explore the impact of B/F ratio on the accuracy of intraocular lens power calculation. Methods: A total of 197 age-related cataract patients (197 eyes) who were treated in the cataract center of our hospital from March 2019 to November 2019 and were going to undergo monocular cataract surgery were selected. The biological parameters of the anterior segment were measured by Pentacam anterior segment analyzer before surgery, and the patients were divided into three groups (25% below the B/F ratio, 25%~75%, and 25% below the B/F ratio) with the lower limit and the upper limit of 25%. Three months after surgery, the postoperative refractive state of patients was evaluated by automatic computerized refractometer, and the postoperative refractive error (PE) was calculated, and the percentage differences of mean refractive error (ME), mean absolute error (MAE), median absolute error (MedAE) and refractive error in the range of ±0.25, ±0.50, ±0.75, ±1.00 and < ±1.00D were evaluated. Results: The B/F ratio was moderately correlated with postoperative refractive error in age-related cataract patients (r= ?0.445, P < 0.001). With the increase of B/F ratio, the refractive state of patients shifted from hyperopia to myopia after surgery, and the MAE and MedAE were 0.55 D and 0.46 D respectively in 3 months after surgery. The percentages of refractive error in the range of ±0.25, ±0.50, ±0.75, ±1.00 and < ±1.00 D were 29.4%, 52.8%, 71.6%, 87.6% and 12.7%, respectively. After adjusting the corneal curvature according to the B/F ratio of the population based on our previous study, MAE and MedAE were 0.51 D and 0.43 D, respectively, which were lower than those before correction (P< 0.05). Conclusions: There is a correlation between B/F ratio and postoperative refractive error in age-related cataract patients. As the B/F ratio increased, the refractive state of the patient gradually drifted from farsightedness to myopia after cataract surgery, and the more the B/F ratio deviated from the normal average, the greater the absolute value of the patient's refractive error.

目的：探讨白内障人群角膜屈光力(corneal refractive power,CRP)的分布特点及与眼生物学参数的相关因素分析。方法：回顾性横断面研究福州眼科医院2019年3月至2022年7月就诊的40岁以上白内障人群共23035眼，使用OA-2000测量其眼轴(axial length,AL)、CRP、前房深度(anterior chamber depth,ACD)、晶状体厚度(lens thickness,LT)、角膜水平直径即白到白(white-to-white,WTW)、中央角膜厚度(central corneal thickness,CCT)。绘制各眼生物学参数及年龄Spearman相关性热力图，绘制CRP与AL、CRP与WTW散点拟合图。将CRP与上述参数及年龄进行Spearman相关性分析，分段数据的线性关系使用Pearson分析及线性回归分析。结果：白内障人群CRP为(44.36±1.52)D，在总体数据中CRP与AL为非线性相关；但在分段数据中存在线性相关：当AL≤25.06 mm，CRP与AL负线性相关(R² =0.397，P<0.001)；当AL>25.06 mm，CRP与AL正线性相关(R² =0.045，P<0.001)；无论AL长短，CRP与WTW、CCT均呈负相关。在总体数据中，CRP与WTW也存在非线性关系；但在分段数据中存在线性相关：当10.52 mm≤WTW≤12.46 mm，CRP与WTW负线性相关(R² =0.149，P<0.001)，并与AL、ACD、CCT呈负相关。结论：CRP与AL、WTW呈非线性相关，使用CRP优化计算人工晶状体(intraocular lens,IOL)屈光力时需适当考虑AL、WTW与CRP的相关性。

Objective: To investigate the distribution characteristics of corneal refractive power (CRP), and analyze the correlation between corneal refractive power and ocular biometric parameters in cataract patients. Methods: A retrospective cross-sectional study was conducted on 2,3035 eyes of cataract patients over 40 years old, who visited Fuzhou Eye Hospital during the period between March 2019 and July 2022. The subjects' examination results of axial length (AL), corneal refractive power (CRP), anterior chamber depth (ACD), lens thickness (LT), horizontal corneal diameter (WTW), central corneal thickness (CCT) were measured by OA-2000. Spearman correlation thermograms of bilological parameters and age for each eyes were worked out. The plot scatter fitting plots of CRP and AL, CRP and WTW were made. Spearman correlation analysis was made among CRP, above-mentioned parameters and age. Linear relationships of the segmented data were analyzed with Pearson and linear regression analysis. Results: In the cataract patients, CRP was (44.36 ± 1.52) D. There was a non-linear correlation between CRP and AL in the total data. However, there was a linear relationship in the segmented data. When AL ≤ 25.06 mm, CRP was negatively linearly correlated with AL (R² =0.397, P<0.001). When AL>25.06 mm, CRP was weakly positively correlated with AL (R² =0.045, P<0.001). Regardless of the length of AL, CRP was negatively correlated with WTW and CCT. There was also a nonlinear relationship between CRP and WTW in the total data. But there was a linear correlation in the segmented data.When 10.52 mm ≤ WTW ≤ 12.46 mm, the negative linear correlation was found between CRP and WTW (R² =0.149, P<0.001), while there was negative correlation among CRP, AL, ACD, and CCT. Conclusion: There is a non-linear correlation among CRP, AL and WTW. To optimize the calculation of intraocular lens (IOL) refractive power with CRP, it is necessary to consider the correlation between AL, WTW, and CRP.

该文报道一例激光原位角膜磨镶(laser-assisted in situ keratectomy,LASIK)术后行白内障超声乳化摘除联合多焦点散光矫正型人工晶状体植入术的病例。该患者为42岁女性患者，20年前外院行双眼LASIK手术，现因右眼视物模糊1年就诊。术前IOLMaster检查患者右眼眼轴长度29.66 mm，前房深度3.18 mm，晶状体厚度4.75 mm，白到白距离11.6 mm，前表面及全角膜散光分别为1.01 D@67 °及0.91 D@56 °。Pentacam角膜地形图15 °范围模拟角膜屈光力得到的角膜散光为1.2 D@58.1 °，为规则领结型。患者眼底检查未见明显异常，因其脱镜意愿强烈，植入双焦点散光矫正型IOL(德国Zeiss公司AT LISA toric 909M)。根据Barrett True-K Toric公式测量的后表面散光计算结果进行手术规划，选择+17 D球镜1.5 D柱镜Zeiss 909M IOL，植入轴位55 °。术后1个月患者裸眼远视力0.8，35 cm裸眼近视力1.0，最佳矫正远视力–0.25 DS/–0.5 DC×120 °至1.0，患者满意。提示经过详细的术前评估及规划，并与患者充分沟通，多焦点散光矫正型人工晶状体可以在部分适合的LASIK术后患者中取得良好效果。

It is reported a case of cataract phacoemulsification combined with toric multifocal intraocular lens (IOL) implantation after LASIK surgery in this article. A 42 year-old female patient who underwent bilateral LASIK surgery in other hospital 20 years ago. She visited our hospital due to blurred vision in her right eye for one year. The preoperative IOL Master examination results showed an axial length of 29.66 mm, anterior chamber depth of 3.18 mm, lens thickness of 4.75 mm, white to white distance of 11.6 mm, and anterior surface and total corneal astigmatism of 1.01 D @ 67 ° and 0.91 D @ 56 °, respectively in right eye. The corneal astigmatism measured by Pentacam using 15°range simulated keratometry is 1.2 D@ 58.1 °, which is a regular bow tie shape.No obvious abnormalities was found in the patient's fundus examination. Due to her strong desire to get rid of the glassesa toric bifocal IOL (AT LISA Toric 909M, Zeiss, Germany) was implanted.Based onthe IOL power calculation results of Barrett True-K Toric formula with measured posterior corneal astigmatism, an IOL with Sph 17.0 D/Cyl1.5 D/A 55°was chosen. One month after surgery, the patient's uncorrected distance visual acuity was 20/25, 35 cm uncorrected near visual acuity was 20/20, and the best corrected distance visual acuity was 20/20 with a prescription of –0.25 DS/–0.5 DC × 120 °. The patient was satisfied with the outcome. After detailed preoperative evaluation and design, and sufficient communication with patients, toric multifocal IOL implantation can achieve good results in some apropriated for the patients after LASIK surgery.

球形晶状体是一种罕见的先天性晶状体悬韧带疾病，表现为晶状体前后径增加，赤道半径减小，类似球形。临床特点包括浅前房、晶状体源性高度近视、晶状体脱位及继发青光眼等。治疗上早期可以通过验光配镜提高视力，当继发晶状体脱位及青光眼时需尽早进行手术治疗。本例报道一例72岁男性患者，因右眼视力下降2年入院。既往近视，近视逐渐加深，近2年患者双眼配镜-10D，视力无明显改善。就诊后考虑球形晶状体所致晶状体不全脱位合并白内障，入院后行囊袋拉钩固定下白内障超声乳化+人工晶状体悬吊+前段玻璃体切除术。患者术后1个月后复诊，发现黄斑水肿，予以复方平地木颗粒口服，溴芬酸钠滴眼液滴眼。2周后复诊视力及黄斑水肿明显好转。

Microspherophakia (MSP) is a rare congenital zonular dysplasia characterized by increased anteroposterior lens thickness and reduced equatorial diameter, resembling a spherical shape. The related ocular manifestations of MSP include shallow anterior chamber, lens derived high myopia, ectopia lentis and secondary glaucoma. In the early stage of MSP, vision acuity may be improved by glasses. Cataract surgery is necessary once secondary lens dislocation and glaucoma occur. A 72-year-old male hospitalized patient was reported who complained increased blurred vision of his right eye for 2 years. In the past 2 years, the power of his binocular glasses was increased to -10 diopters without significant improvement in visual acuity. Lens dislocation and phakic insufficiency caused by MSP was diagnosed after he attending clinics at the Eye and ENT Hospital of Fudan University, Shanghai, China. Phacoemulsification with scleral sutured intraocular lens (IOL) implantation surgery and anterior vitrectomy were performed. One month after operation, macular edema was found at first follow-up. Compound pingdingmu granule was taken orally and Bromfenac sodium eye drops were applied three times a day. Two weeks later, visual acuity of his right eye was improved significantly and macular edema was eliminated dramatically.

该文报道了一例40岁女性患者，因“双眼渐进性视物模糊3个月”就诊。患者既往于2005年因高度近视行双眼准分子激光原位角膜磨镶术 (LASIK)。最佳矫正视力OD：0.2 (–11.00 DS/ –1.25 DC×170 °)，OS：0.7 (–4.00 DS/ –0.75 DC×25 °)。双眼角膜透明，前房中深，晶状体混浊，豹纹状眼底伴后巩膜葡萄肿。诊断为双眼并发性白内障，并行右眼白内障超声乳化联合人工晶状体 (IOL) 植入术，术中植入+14.0 D IOL一枚，目标屈光度为–0.5 D。术后1周裸眼视力0.3，验光结果示右眼屈光度+2.75 DS，最佳矫正视力0.7。术后2周行右眼IOL置换术，由+14.0 D置换为+17.0 D。右眼术后1周裸眼视力0.8，验光结果示右眼屈光度–0.75 DC×15 °。

It is reported in this article that a 40-year-old female patient presented with "progressive blurred vision of both eyes for 3 months". The patient underwent bilateral laser in situ keratomileusis (LASIK) because of high myopia in 2005. It was recorded that her best corrected visual acuity was 0.2 (–11.00 DS/ –1.25 DC×170 °) in the right eye and 0.7 (–4.00 DS/ –0.75 DC×25 °) in the left, and clear cornea, normal anterior chamber, cloudy lens, tessellated fundus with posterior staphyloma in both eyes. The patient was diagnosed with bilateral complicated cataract. Phacoemulsification combined with intraocular lens (IOL, +14.0 diopter (D)) implantation was performed on the right eye, with the target –0.5D refractive diopter . One week after surgery, it was recorded that the uncorrected visual acuity of the right eye was 0.3, and the best corrected visual acuity was 0.7 (+2.75 DS). IOL replacement of the right eye was performed two weeks after surgery, the +14.0 D IOL was replaced by +17.0 D IOL. One week after surgery, the uncorrected visual acuity of the right eye was 0.8 (–0.75 DC×15 °).

随着人工智能(artificial intelligence,AI)技术的快速发展，其在医疗领域的应用正带来革命性的变化。白内障作为全球范围内最常见的可逆性视力障碍之一，在管理和治疗方面依然存在着医疗资源不足、诊断精度低、转诊效率低等诸多实际问题。因此，利用AI技术强大的计算分析和智能决策能力，优化传统医疗实践方式，对于保障人们的视觉健康至关重要。该文探讨AI技术在推动白内障分级诊疗新模式方面的应用，包括白内障图像自动分析与识别、远程医疗和转诊支持等，这些应用能够为白内障患者、社会以及政府带来多方面的显著益处和重要影响，有助于提高白内障诊断和治疗效率，缓解医疗资源不均衡问题，优化医疗资源的配置和管理，推动社会健康进步。然而，AI技术的实际应用也面临风险和挑战，应当充分重视和保护患者数据隐私和安全，建立严格的监管和监督机制，并持续加强技术创新，全面评估AI算法的鲁棒性、公平性和可解释性，以进一步提高AI系统的准确度和可信度。

With the rapid development of artificial intelligence (AI) technology, its application in the field of healthcare is bringing revolutionary changes. Cataracts, as one of the most common reversible visual impairments worldwide, still face many practical issues in terms of limited medical resources, low diagnostic accuracy, and low referral efficiency. Therefore, it is crucial to utilize AI technology's powerful computational analysis and intelligent decision-making capabilities to optimize traditional medical practices and safeguard people's visual health.This article investigates the applications of AI technology on a new model of hierarchic diagnosis and treatment for cataracts, including automatic analysis and recognition of cataract images, remote healthcare, and referral support. These applications can bring significant benefits and important impacts to cataract patients, society, and governments. They can help improve the efficiency of cataract diagnosis and treatment, alleviate the imbalance of medical resources, optimize the allocation and management of healthcare resources, and promote societal health progress.However, the practical application of AI technology also faces risks and challenges. It is important to fully prioritize and protect patients' data privacy and security by establishing strict regulatory and oversight mechanisms. Additionally, continuous efforts should be made to enhance technological innovation and comprehensively evaluate the robustness, fairness, and interpretability of AI algorithms to further improve the accuracy and trustworthiness of AI systems.

人工智能(artificial intelligence，AI)在眼科领域的应用不断深入、拓展，目前在糖尿病性视网膜病变、白内障、青光眼以及早产儿视网膜病变在内的多种常见眼病的诊疗中逐渐成为研究热点。AI使医疗资源短缺、诊断标准缺乏、诊疗技术水平低下的现状得到改善，为白内障的诊疗开辟了一条“新赛道”。本文旨在综述AI在白内障诊疗中的应用现状、进展及局限性，为AI在白内障领域的进一步开发、应用及推广提供更多信息。

Artificial intelligence (AI) has been widely applied and promoted in ophthalmology, and has gradually become a research hotspot in the diagnosis and treatment of many common ophthalmopathies, including diabetic retinopathy, cataract, glaucoma, and retinopathy of prematurity. AI improves the shortage of medical care, the lack of diagnostic criteria and the low level of diagnosis and treatment technology, and explores a “new race track” for cataract diagnosis and treatment. The purpose of this article is to review the application status, progress and limitations of AI in the diagnosis and treatment of cataract, aiming to provide more information for further development, application and promotion of AI in the field of cataract.

随着微创玻璃体切除术(pars plana vitrectomy，PPV)的广泛开展和手术技术的提高，患者对手术后视觉质量的要求越来越高。白内障是PPV术后最常见并发症，而具有玻璃体切除史的白内障患者屈光变异大，预测难度高。本文综述了生物测量误差、人工晶状体屈光力计算公式选择以及有效晶状体位置预测等影响有玻璃体切除手术史的白内障患者术后屈光误差的主要因素，旨在为降低这一类特殊人群白内障术后屈光误差提供参考。

With the widespread application of minimally invasive vitrectomy and the improvement of surgical techniques, the demands of patients for better postoperative visual quality are increasing. Cataract is the most common complication after vitrectomy, whereas the refractive outcomes of cataract patients with prior vitrectomy are viable and difficult to predict. In this paper, the main factors affecting postoperative refractive error of cataract patients with a history of vitrectomy, such as biometric error, selection of intraocular lens calculation formulas and prediction of effective lens position, were reviewed in order to provide reference for reducing postoperative refractive error of this special group of cataract patients.

白内障是世界范围内致盲的主要原因之一，占中低收入国家致盲病例的50%。随着人口老龄化程度的加深，到2050年中国白内障致盲病例预计达到2 000万。卫生支出占比低、医疗设备及眼科医生紧缺、筛查费用昂贵仍是中低收入国家无法开展大规模白内障筛查的主要原因。人工智能(artificial intelligence，AI)协助白内障诊断具有便捷、低成本、可远程进行等优点，有望减少甚至避免白内障致盲的发生。文章将对AI通过结合裂隙灯眼前节图像、眼底照片及扫频源光学相干层析图像进行白内障自动诊断等研究进行简要综述。

Cataract is a primary cause of blindness globally, particularly accounting for 50% of blindness cases in low- and middle- income countries. As the population ages, it is predicated that cataract blindness cases in China will rise to 20 million by 2050. However, low health expenditures, scarcity of medical equipment and ophthalmologists, and high screening costs continue to hinder mass cataract screening in these countries. Artificial intelligence(AI)-assisted cataract diagnosis offers significant advantages, including convenience, cost-effectiveness, and remote accessibility, potentially reducing or even eliminating cataract blindness. This review aims to concisely summarize the research on automatic cataract diagnosis utilizing AI, incorporating slit lamp images of anterior eye segment, fundus photographs, and swept source optical coherence tomography images.