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.
目的：在硅油取出联合白内障手术患者中，使用扫频源光学相干断层扫描生物测量仪OA-2000进行生物测量，比较10种人工晶状体(IOL)屈光力计算公式的准确性。方法：回顾性分析2021年3月—7月于中山大学中山眼科中心接受硅油取出联合白内障手术的患者共62例(62眼)，所有患者均使用扫频源光学相干断层扫描生物测量仪OA-2000进行生物学参数测量。计算并比较新公式[Barrett Universal II (BUII)、Emmetropia Verifying Optical(EVO) 2.0、Hill-Radial Basis Function (Hill-RBF) 3.0、Hoffer QST、Kane、Pearl-DGS]及传统公式(Haigis、Hoffer Q、Holladay 1、SRK/T)的预测准确性，主要评价指标为绝对预测误差中位数(MedAE)及平均绝对预测误差(MAE)。按眼轴长度≤23 mm(组1)，>23 mm且≤26 mm(组2)与>26 mm(组3)进行亚组分析。结果：6个新公式、Haigis、SRK/T公式均出现近视漂移(-0.47 ~-0.27 D，P<0.05)，而HofferQ及Holladay 1公式无系统误差(P>0.05)。Kane公式的MedAE(0.55 D)及MAE(0.81 D)最小，但公式间比较差异无统计学意义(P>0.05)。组1中所有公式均出现近视漂移(-1.46~ -1.25 D，P<0.05)，而其他亚组比较差异无统计学意义(-0.32 ~ 0.41 D，P>0.05)。在组1中，Pearl-DGS公式的MedAE(0.97 D)及MAE(1.26 D)最小，且优于Hill-RBF 3.0(P=0.01)及SRK/T公式(P=0.02)；组2中，Kane公式具有最小的MedAE(0.44 D)及MAE(0.66 D)；组3各个公式屈光预测准确性比较差异无统计学意义(P>0.05)。结论：在使用OA-2000进行术前生物测量时，Kane公式在接受硅油取出联合白内障手术患者中的预测准确性较高；而眼轴长度≤23 mm时，Pearl-DGS公式可能更为准确。
Objective: To compare the accuracy of 10 intraocular lens (IOL) power calculation formulas in patients undergoing combined silicone oil removal and cataract surgery, biometry is performed using the swept-source optical coherence tomography biometer OA-2000. Methods: A retrospective analysis. A total of 62 patients (62 eyes) who underwent combined silicone oil removal and cataract surgery in Zhongshan Ophthalmic Center, Sun Yat-sen University from March to July in 2021 were enrolled. Preoperative biometry was performed by OA-2000 in all patients. New-generation formulas (Barrett Universal II [BUII], Emmetropia Verifying Optical [EVO] 2.0, Hill-Radial Basis Function [Hill-RBF] 3.0, Hoffer QST, Kane and Pearl-DGS) and traditional formulas (Haigis, Hoffer Q, Holladay 1 and SRK/T) were evaluated. The median absolute prediction error (MedAE) and mean absolute prediction error (MAE) were the main parameters used to assess accuracy. Subgroup analyses were performed based on the axial length of 23 mm and 26 mm. Results: Six new-generation formulas, Haigis, and SRK/T showed myopic shift (-0.47 ~ -0.27 D, P<0.05), while no systematic bias was found in Hoffer Q and Holladay 1 displayed (P>0.05). The smallest MedAE (0.55 D) and MAE (0.81 D) were found in Kane formula, but there was no statistically significant difference compared with other formulas (P>0.05). The myopic shift (-1.46 ~ -1.25 D, P<0.05) in eyes shorter than 23 mm were found in all formulas, while there was no significant systematic bias (-0.32 ~ 0.41 D, P>0.05) in other subgroups. In axial length shorter than 23 mm, the Pearl-DGS formula stated the smallest MedAE (0.97 D) and MAE (1.26 D), and was significantly more accurate than Hill-RBF 3.0 (P=0.01) and SRK/T (P=0.02). In eyes with an axial length between 23 mm and 26 mm, the Kane formula had the lowest MedAE (0.44 D) and MAE (0.66 D). No significant difference was found in eyes longer than 26 mm. Conclusion: The Kane formula showed the highest accuracy in patients undergoing combined silicone oil removal and cataract surgery measured by OA-2000, whereas the Pearl-DGS formula could be more accurate in eyes with an axial length shorter than 23 mm.
准分子激光原位角膜磨镶术(laser-assisted in situ keratomileusis,LASIK)是矫正屈光不正的重要角膜屈光手术方式之一。经过准分子激光切削的角膜，生物测量数据发生改变。对于此类患者，通过常规测量获得的参数数据以及使用常规计算公式确定的IOL屈光度将变得不再准确，由此将会导致术后较大的屈光误差，进而影响患者的视觉质量。本文报道一例46岁的男性白内障患者。该患者既往双眼屈光不正，曾接受过LASIK手术治疗。白内障术前角膜地形图检查发现该患者双眼存在角膜偏心切削，这为IOL屈光度的确定带来困难。手术医生通过角膜地形图判断角膜切削的居中性，在特定区域内选择角膜曲率K值，并采用Barrett True K公式计算出IOL屈光度。白内障术后患眼屈光误差相对较小，视力提高，视觉质量改善。
Laser-assisted in situ keratomileusis (LASIK) is a crucial corneal refractive surgery for correcting refractive errors. The cornea, after undergoing excimer laser ablation, undergoes changes in biometric measurements. For such patients, conventional measurements and IOL power calculations based on standard formulas may no longer be accurate, leading to significant postoperative refractive errors and subsequently impacting the patient's visual quality. This article presents a case of a 46-year-old male cataract patient who had a history of refractive errors in both eyes and had previously undergone LASIK surgery. Preoperative corneal topography revealed corneal eccentric ablation in both eyes, posing challenges in determining IOL power. The surgeon assessed the centration of corneal ablation using corneal topography, selected the keratometry value (K value) within specific corneal regions, and calculated the IOL power using the Barrett True K formula. Postoperatively, the cataract patient experienced relatively minor refractive errors, leading to improved vision and enhanced visual quality.
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：观察超声乳化白内障吸除人工晶状体植入术（phacoemulsification with intraocular lens implantation, PEI）联合房角分离术（goniosynechialysis, GSL）及房角切开术（goniotomy, GT）治疗中晚期原发性慢性闭角型青光眼（chronic primary angle-closure glaucoma , CPACG）合并白内障的安全性和有效性。方法：采用回顾性病例研究。收集2020年6月至2024年1月在成都市中西医结合医院行PEI联合GSL及GT的中晚期CPACG合并白内障患者94例133眼，观察最佳矫正视力（best corrected visual acuity, BCVA）、眼压、抗青光眼药物使用数量及术后并发症等情况。采用重复测量方差分析、Wilcoxon秩检验进行统计学处理。结果：术后1天，1周，1、3、6个月94例患者133眼的BCVA（logMAR）均较术前有所提升（P＜0.05）；从术后1天到6个月的所有随访时间点眼压均较术前明显下降（F = 189.79，P＜0.001）；术后6个月，患者使用的降眼压药物数量明显低于术前 ( Z = -2.392，P＜0.001)。术后1周中31眼（23%）出现角膜水肿，15眼（11%）出现前房积血，均在1周内消退；术后1个月内1眼出现眼压反跳，予以前房穿刺放液等治疗后眼压恢复到正常范围。术后6个月，121眼（91%）手术完全成功，10眼（8%）手术条件成功。结论：PEI联合GSL及GT治疗中晚期CPACG合并白内障可有效地提高视力、降低眼压，且无严重并发症。
Objective: To observe the safety and efficacy of phacoemulsification with intraocular lens implantation (PEI) combined with goniosynechialysis (GSL) and goniotomy (GT) in treating advanced chronic primary angle-closure glaucoma (CPACG) complicated by cataract. Methods: This was a retrospective case series study. We collected data from a total of 94 patients (133 eyes) who had advanced CPACG along with cataract and underwent PEI+GSL+GT at Chengdu Integrated TCM&Western Medicine Hospital between June 2020 and January 2024. We observed the best corrected visual acuity (BCVA), intraocular pressure (IOP), the number of anti-glaucoma drugs used, and postoperative complications. Repeated measures ANOVA and Wilcoxon rank test were used for statistical analysis. Results: The BCVA (logMAR) at 1 day, 1 week, 1, 3, and 6 months after surgery showed significant improvement compared to the pre-surgical values (F = 189.79，P < 0.001); The IOP at 1 day, 1 week, 1, 3, and 6 months post-surgery was significantly lower than that pre-surgical IOP (P < 0.001). The number of IOP-lowering drugs used at 6 months after surgery was also significantly reduced compared to the pre-surgical (Z = -2.392, P < 0.001). One week after surgery, corneal edema occurred in 31 eyes (23%) and hyphema in 15 eyes (11%) , both of which resolved spontaneously within 1 week. Within one month after surgery, 1 eye experienced an IOP spike, and the intraocular pressure returned to normal range after treatments such as anterior chamber puncture and drainage. Six months after surgery, the operation was completely successful in 121 eyes (91%), and conditionally successful in 10 eyes (8%), resulting in an overall surgical success rate of 99%. Conclusions: PEI combined with GSL and GT can effectively improve vision and reduce IOP in patients with advanced CPACG complicated by cataract, without causing serious complications.
目的：关于大气污染物是否与年龄相关性白内障有关联的研究有限，以往的研究结果也不一致。本研究旨在评估多种大气污染物与年龄相关性白内障之间的关系。方法：采用双样本孟德尔随机化（Mendelian Randomization, MR）设计，并使用了来自亚洲及欧洲两个人群的独立全基因组关联研究（Genome-Wide Association Study, GWAS）的汇总统计数据。大气污染物数据包括颗粒物2.5（particulate matter2.5, PM2.5）、PM2.5-10、PM10、二氧化氮和氮氧化物。主要分析方法是逆方差加权（inverse variance weighted, IVW）法，辅以多变量孟德尔随机化分析（multivariable Mendelian randomization, MVMR）校正污染物间混杂效应，并通过敏感性分析验证结果的稳健性。Cochran Q检验法被用来评估各个单核苷酸多态性（single nucleotide polymorphism, SNP）之间是否存在显著的异质性。并采用MR PRESSO方法来识别并排除SNP中的异常值，同时利用MR Egger回归模型评估SNP之间可能存在的多效性，并通过逐一排除每个SNP进行敏感性分析，以确保MR分析结果不受单一SNP的显著影响。结果：关于5种大气污染物特征，亚洲人群结果中，二氧化氮暴露与年龄相关性白内障存在正相关（OR=1.03, 95%CI 1.00~1.06，P=0.026），但在多变量分析中效应方向反转（OR=0.86, 95%CI 0.77~0.97, P=0.013）；在欧洲人群中，PM2.5-10与年龄相关性白内障显著相关（OR=1.35, 95%CI 1.12~1.62，P=0.002），且在多变量分析中因果效应依然显著（OR=1.58, 95%CI 1.27~3.70, P=0.03）。敏感性分析支持结果的稳健性，未发现异质性或多效性偏倚。结论：环境中PM2.5-10和二氧化氮与年龄相关性白内障存在复杂因果关系，且因人群而异。亚洲人群中，二氧化氮单变量分析呈正相关，多变量分析效应反转，倾向多变量分析结果，即其降低年龄相关性白内障风险；欧洲人群中，PM2.5-10单、多变量分析均呈正相关，显示其会增加年龄相关性白内障风险。
Objective: Research exploring the association between atmospheric pollutants and age-related cataracts is scarce, and previous studies have yielded inconsistent findings. This study aims to assess the relationship between various atmospheric pollutants and age-related cataracts. Methods: We adopted a two-sample Mendelian randomization (MR) design, using summary statistics from independent genome-wide association studies (GWAS) conducted on Asian and European populations. The atmospheric pollutant considered in this study included PM2.5, PM2.5-10, PM10, nitrogen dioxide, and nitrogen oxides. The primary analysis method was the inverse variance weighted (IVW) approach. Additionally, multivariable MR (MVMR) was used to adjust for confounding effects among pollutants. Sensitivity analyses were conducted to verify the robustness of the results. The Cochran Q test was employed to assess significant heterogeneity among SNPs. The MR PRESSO method was applied to identify and exclude outliers SNPs, while the MR Egger regression model was used to evaluate potential pleiotropy among SNPs. Furthermore, sensitivity analyses were performed by excluding each SNP one by one to ensure that the MR analysis results were not significantly influenced by a single SNP. Results: Among the five atmospheric pollutants studied, we discovered a significant positive correlation between nitrogen dioxide exposure and age-related cataracts in the Asian population (OR=1.03, 95%CI 1.00-1.06, P=0.026). However, the direction of the effect was reversed in the multivariable analysis (OR=0.86, 95%CI 0.77-0.97, P=0.013). In the European population, PM2.5-10 was significantly associated with age-related cataracts (OR=1.35, 95%CI 1.12-1.62, P=0.002), and the causal effect remained significant in the multivariable analysis (OR=1.58, 95%CI 1.27-3.70, P=0.03). Sensitivity analyses supported the robustness of the results, with no evidence of heterogeneity or pleiotropy bias. Conclusions: This study revealed a complex causal relationship between environmental PM2.5-10 and NO₂ and age-related cataracts, which varied across populations. In Asian populations, the univariate analysis of nitrogen dioxide showed a positive correlation, but the effect was reversed in multivariate analysis, leaning towards the multivariate results and indicating a reduced risk of age-related cataracts. In European populations, both univariate and multivariate analyses of PM2.5-10 showed a positive correlation, increasing the risk of age-related cataracts. The study provides genetic evidence for the prevention and control of air pollution and highlights the importance of using multi-pollutant models to assess environmental health effects.
