目的：评估新一代基于人工智能(artificial intelligence,AI)的人工晶状体(intraocular lens,IOL)计算公式的准确性。方法：本研究为回顾性研究，纳入因白内障行晶状体超声乳化联合IOL植入术的262例患者262眼。在术前，通过IOLMaster700获取角膜曲率、角膜白到白、中央角膜厚度、前房深度、晶状体厚度以及眼轴长度。使用第三代公式(SRK/T、Holladay 1和Hoffer Q)、Barrett UniversalⅡ(BUⅡ)、新一代AI公式(Kane、Pearl-DGS、Hill-RBF 3.0、Hoffer QST和Jin-AI)对术后屈光状态进行计算，并与术后实际的屈光状态进行比较。在将预测误差(prediction error,PE)归零后，分析了各公式的标准差(standard deviation,SD)、绝对误差均值(mean absolute error,MAE)、绝对误差中位数(median absolute error,MedAE)以及PE在±0.25、±0.50、±1.00、±2.00 D范围内的百分比。结果：基于AI的IOL屈光力计算公式的SD、MAE和MedAE的范围分别为0.37 D(Kane和Jin-AI)至0.39 D(Hoffer QST)、0.28 D(Hill-RBF 3.0和Jin-AI)至0.31 D(Hoffer QST)以及0.21 D(Hill-RBF3.0和Jin-AI)至0.24 D(HofferQST)；均低于第三代公式(SD：0.43 D~0.45 D；MAE：0.34 D；MedAE：0.25 D~0.28 D)。在所有公式中，Jin-AI公式预测误差在±0.50 D的比例最高，为84.73%，Kane(84.35%)和BUⅡ(83.97%)公式次之。结论：在IOL屈光力预测上，与传统第三代公式相比，新一代基于AI的公式表现出更高的准确性，可以使更多的患者在术后获得预期的屈光状态。

Objective: To evaluate the accuracy of new generation artificial intelligence (AI)-based intraocular lens (IOL)power calculation formulas. Methods: This retrospective study included a total of 262 eyes from 262 patients with cataract who underwent uneventful phacoemulsification combined with IOL implantation. Keratometry, corneal white-to-white, central corneal thickness, anterior chamber depth, lens thickness, and axial length were measured by the IOL Master 700 before surgery. Predicted refractive errors were calculated by the third-generation formulas (SRK/T, Holladay 1, and Hoffer Q), Barrett UniversalⅡ (BUⅡ), and the newer-generation AI formulas (Kane, Pearl-DGS, Hill-RBF 3.0, Hoffer QST, and Jin-AI), and were compared with the actual postoperative refractive value. After adjusting the prediction error (PE) to zero, the standard deviation (SD), mean absolute error (MAE), median absolute error (MedAE), and the percentage of a PE within the range of ±0.25 diopter (D), ±0.50 D, ±1.00 D, and ±2.00 D were analyzed. Results: The SD, MAE, and MedAE of the AI-based formulas ranged from 0.37 D (Kane and Jin-AI) to 0.39 D (Hoffer QST), 0.28 D (Hill-RBF 3.0 and Jin-AI) to 0.31 D (Hoffer QST), and 0.21 D (Hill-RBF 3.0 and Jin-AI) to 0.24 D (Hoffer QST), respectively. These values were all lower than those of the third-generation formula (SD: 0.43 D to 0.45 D; MAE: 0.34 D; MedAE: 0.25 D to 0.28 D). Among all the formulas, the Jin-AI formula had the highest proportion of a PE within ±0.50 D (84.73%), followed by Kane (84.35%) and BUⅡ (83.97%) formulas. Conclusion: The new AI-based IOL formulas show higher accuracy compared with the traditional third-generation ones in predicting IOL power. thereby enabling more patients to achieve the expected refractive outcomes after surgery

视网膜是中枢神经系统的一部分。在胚胎起源上，视网膜和大脑均由神经管发育而来。因此，许多发生在大脑的神经退行性疾病往往会同时累及视网膜。而神经退行性疾病过程中相关的特征性病理改变，如病理性蛋白聚集和神经血管单元破坏也常能在视网膜组织中被检测到。在一些神经退行性疾病中，眼部的病理改变甚至在临床症状出现之前就已发生；其次视网膜易于观察且局部治疗操作便捷，因此近年来视网膜在中枢神经退行性疾病发病机制研究、早期诊断和新型治疗方式探究等方面备受关注。该文对常见神经退行性疾病的眼部病理改变进行综述，旨在为大脑和视网膜神经退行疾病的发病机制、诊断以及治疗研究提供新的见解。

The retina is a part of the central nervous system. Developmentally, both retina and brain are derived from the neural tube. Therefore, many neurodegenerative diseases that occur in the brain tend to involve both the retina. In the process of neurodegenerative diseases, related characteristic pathological changes, such as pathological protein aggregation, neurovascular unit impairment can often be detected in retinal tissue. In some neurodegenerative diseases, pathological changes in the eye occur even before clinical symptoms appear. In addition, the retina are easy to observe and local treatments are convenient. In recent years, the manifestations of the retina have attracted much attention in the study of pathogenesis, early diagnosis, and new treatments of systemic central neurodegenerative diseases. In this way, this article reviews the ocular pathological changes of common neurodegenerative diseases, aiming to provide new insights into the pathogenesis, diagnosis, and treatment of brain and retinal neurodegenerative diseases.

当前，药物临床试验面临着两大难题：数据真实性及相关人员操作规范性。现阶段国内外在药物临床试验方面的监管主要以事后监查为主，在数据质量管理以及操作规划标准的监查方面存在一定的时延性。而区块链通过非对称加密、哈希算法及智能合约等技术，可以在保证受试者隐私信息的前提下，提高政府相关监督机构的监管效率，提升药物临床试验数据管理的透明度；同时，与物联网的紧密结合可以实现对标准操作规范的进一步核查，与人工智能的结合有望实现受试者的自动招募。

Clinical drug trials are confronted with two major issues: first, data authenticity, for instance, if any data falsification is conducted during the whole trial; second, whether the standard of procedure is accordingly conducted throughout the whole trial or not. Currently, both domestic and overseas clinical drug trials are not supervised without delay (ex-post inspection). Blockchain technology can improve the efficiency of Food and Drug Administration and the transparency of trials while the rights and safety of human research subjects are guaranteed by the integrated technology such as chained structure, asymmetry key algorithm, hash algorithm, and smart contract. Furthermore, with the assistance of internet of things (IoT) and artificial intelligence (AI), the actual supervision over the whole trial and automatic recruitment of human research subjects are expected to achieve.

传统的眼底手术要求眼科医生具备精细的操作技术，但即便拥有再精湛的操作技术，眼底手术还是存在很大的风险性。因此，为了减少手术风险，提高手术质量，对传统眼底手术进行改进是十分必要的。近年来，在我国对于人工智能产业的大力支持之下，应用于各类行业的机器人随之诞生。机器人辅助系统(robot auxiliary system，RAS)在医学领域，特别是眼科学中应用广泛。对近几年RAS应用于眼底手术的案例进行整理总结，并将RAS参与的眼底手术以及传统的眼底手术进行对比，可以发现RAS在眼底手术中的应用可以显著提高手术效率，并降低手术风险。未来RAS的发展趋势可能着重聚焦于与深度学习算法的紧密结合。通过算法对手术中的视野图像进行预测、优化，从而让高精度的眼底手术更加高效、安全。

Traditional fundus surgery requires ophthalmologists to be equipped with sophisticated operating techniques, but even with the most sophisticated operating techniques, fundus surgery still has great risks. Therefore, in order to reduce the risk of surgery and improve the quality of surgery, it is very necessary to improve the traditional fundus surgery. In recent years, with China’s strong support for the artificial intelligence industry, robots used in various industries have been born. Robot auxiliary system (RAS) is widely used in the medical field, especially in ophthalmology. By summarizing the cases of fundus surgery with RAS in recent years and comparing the fundus surgery involving RAS with traditional fundus surgery, it can be found that the application of RAS in fundus surgery can significantly improve the efficiency of surgery and reduce the risk of surgery. The future development trend of RAS may focus on the close integration with deep learning algorithms, which can predict and optimize the field of view images during surgery so that high-precision fundus surgery can be more efficient and safer.

目的：开发细胞级高分辨率、结构与功能一体化的双模态全视场光学相干层析系统(full-field optical coherence tomography,FFOCT)，实现角膜缘组织的双模态FFOCT成像。方法：基于Linnik干涉成像原理，利用高数值孔径显微物镜(NA=0.8)及高速平面互补金属氧化物半导体(complementary metal oxide semiconductor,CMOS)相机，设计搭建高分辨率的组织静态结构和内源动态功能成像一体化双模态FFOCT系统；构建基于四相位调制结构影像提取及时域干涉信号动态频谱分析的功能影像重建算法；对人供体角膜缘组织开展各深度层的双模式FFOCT成像有效性验证。结果：搭建的双模态FFOCT成像系统可实现横向分辨率0.5 μ m，轴向分辨率1.7 μ m，成像视野320 μ m×320 μ m，相机采集速度100 Hz。系统实现角膜缘组织无外源标记情况下的细胞级分辨率三维结构和内源功能成像，FFOCT静态结构影像清晰显示角膜缘上皮、Vogt栅栏、隐窝、基质、血管及淋巴管等结构，FFOCT动态功能影像突出显示了代谢活跃细胞(角膜缘上皮细胞、免疫细胞等)。结论：双模态FFOCT高分辨率成像系统可提供角膜缘微观结构和活细胞无标记内源功能可视化信息，将为角膜缘疾病的研究及临床诊疗提供全新的成像分析技术。

Objective: To develop a cellular-level, high-resolution, integrated dual-modal full-field optical coherence tomography (FFOCT) system capable of simultaneously imaging the structure and function of limbus tissue. Methods: Utilizing the Linnik interference imaging principle, a high-resolution dual-modal FFOCT system was designed and constructed using a high numerical aperture (NA=0.8) microscope objective and a high-speed flat CMOS camera. A functional imaging reconstruction algorithm based on four-phase modulation structure image extraction and dynamic frequency spectrum analysis of temporal interference signals was developed. The effectiveness of dual-mode FFOCT imaging at various depth layers of human corneal limbal tissue was validated. Results: The constructed dual-modal FFOCT imaging system achieved lateral resolution of 0.5 μ m, axial resolution of 1.7 μ m, imaging field of view of 320 μ m × 320 μ m, and camera acquisition speed of 100 Hz. The system enabled cellular-level resolution three-dimensional structural and intrinsic functional imaging of corneal limbal tissue without exogenous labeling. Static structural FFOCT images clearly displayed limbal epithelium, palisades of Vogt, crypts, stroma, blood vessels, and lymphatic vessels, while dynamic functional FFOCT images highlighted metabolically active cells (limbal epithelial cells, immune cells, etc.). Conclusion: The dual-modal FFOCT high-resolution imaging system provides visualization of corneal limbal microstructural and live cell intrinsic functional information without labeling, offering a novel imaging analysis technique for research and clinical diagnosis and treatment of limbal diseases.

目的：利用双向孟德尔随机化方法(mendelian randomization,MR)探索骨关节炎与青光眼的潜在因果关系。方法：使用全基因组关联研究(genome-wide association studies,GWAS)数据，挑选出与骨关节炎和青光眼高度相关的单核苷酸多态性(single nucleotide polymorphism,SNP)作为工具变量。本研究以逆方差加权法(inverse variance weighted,IVW)作为主要的分析手段，以加权中位数法、加权模型法、简单众数法及MR-Egger回归法作为辅助方法，采用F统计量、Cochran Q检验、MR Egger截距测试、留一法(leave one out)及多效性残差和离群值法(mendelian randomization pleiotropy RESidual sum and outliers,MR-PRESSO)进行敏感性分析。本研究采用比值比(odds ratio,OR)作为主要的效应量度指标，以95%置信区间(confidence interval,CI)评估关联强度，探讨骨关节炎与青光眼的双向因果关系。结果：IVW结果表明骨关节炎可增加青光眼的患病风险(95%CI: 1.00~1.20，OR=1.10，P=0.043)，辅助方法的结果显示了相同的因果方向，但无统计学意义。在反向MR分析中，IVW结果表明，青光眼不会增加患骨关节炎的风险(OR=1.02，95%CI: 0.97~1.08)，4种辅助方法均支持IVW结果。所选SNP的F统计量均超过10，无弱工具变量。Cochran Q检验、MR-Egger截距检验以及MR-PRESSO分析结果均未显示所选SNP之间存在异质性或水平多效性。反向MR分析结果显示Cochran Q检验有异质性，但未发现水平多效性。留一法结果显示没有对整体分析结果产生了显著影响的SNP。结论：正向MR分析表明骨关节炎可能会增加患青光眼的风险，二者之间存在正相关。反向MR分析结果表明，青光眼对骨关节炎无因果效应。

Objective: To investigate the potential bidirectional causal association between osteoarthritis and glaucoma through the application of bidirectional Mendelian randomization (MR). Methods: Instrumental variables were selected in this study based on single nucleotide polymorphisms (SNP) strongly associated with osteoarthritis and glaucoma, as utilizing genome-wide association studies (GWAS) data. The inverse variance weighting (IVW) method was served as the primary analytical approach, while the weighted median mode, simple plurality and MR-Egger regression methods were employed as complementary methods. Sensitivity analyses were conducted using F-statistic, Cochran Q-test, MR Egger's intercept test, leave-one-out, and multiplicity of residuals and outliers method (MR-PRESSO). The ratio of odds ratios (OR) was adopted as the primary effect estimate, and the strength of association was evaluated by 95% confidence interval (CI) to explore the bidirectional causal relationship between osteoarthritis and glaucoma. Results: The IVW analysis revealed that osteoarthritis elevates the risk of glaucoma with an odds ratio of (OR) of 1.10(95% CI: 1.00-1.20). While the adjunctive methods concurred with this causal direction, their findings did not reach statistical significance. In contrast, the inverse Mendelian randomization (MR) analysis utilizing the inverse variance weighting method demonstrated that glaucoma does not enhance the risk of developing osteoarthritis (OR=1.02, 95% CI: 0.97-1.08). This conclusion was upheld by all four auxiliary methods. The F-statistic values for the selected SNP exceeded 10, indicating the absence of weak instrumental variables. Furthermore, the Cochran Q test, MR-Egger intercept test, and MR- PRESSO analyses revealed no evidence of heterogeneity or horizontal pleiotropy among the SNP. However, the inverse MR analysis displayed heterogeneity in the Cochran Q test, yet no horizontal pleiotropy was detected. The leave-one-out method analysis identified no significant influence of any individual SNP on the overall results. Conclusions: Forward MR analyses indicated that osteoarthritis may serve as a risk factor for glaucoma, indicating a positive correlation between the two conditions. Conversely, reverse MR analysis failed to establish a causal link between glaucoma and osteoarthritis.

目的：总结MAB21L2基因的变异和临床特点，并与高度同源的MAB21L1基因进行比较。 方法：对中山眼科中心临床基因数据库中MAB21L2基因变异患者进行基因型和表型分析，回顾性分析既往文献报道的MAB21L2基因和高度同源基因MAB21L1变异的表型-基因型的关系。结果：在2个小眼畸形家系中发现2个MAB21L2基因杂合变异：先证者1携带已知变异c.151C>G/p.(Arg51Gly)，患者双眼小眼畸形伴虹膜脉络膜缺损，伴骨关节屈曲。母亲携带相同杂合变异但表型正常；先证者2携带未报道的变异c.1042G>T/p.(Glu348*)，左眼小眼畸形，右眼正常且无全身异常。结合文献回顾发现，在显性遗传模式下，80%的MAB21L2杂合致病变异(20/25)和100%的MAB21L1杂合致病变异(25/25)发生在氨基酸49-52 区域，导致小眼无眼或眼缺损异常(microphthalmia, anophthalmia or coloboma,MAC)；携带该区域MAB21L2基因杂合突变的患者除MAC外，部分还伴骨骼关节发育异常(12/24，50%)；杂合截短变异发生在MAB21L2基因可导致MAC(5/5，100%)，而发生在MAB21L1则不致病。 结论：在2个小眼畸形家系中发现了MAB21L2基因1个新致病变异和1个已知热点致病变异，通过文献综述比较和总结了MAB21L1和MAB21L2基因的突变频谱以及基因型-表型相互关系，为此类基因缺陷导致遗传病的诊断和鉴别诊断提供依据。

Objective: To summarize the genetic variations and clinical features of the MAB21L2 and compare them with the highly homologous MAB21L1 gene. Methods: A genotype -genotype analysis was performed on the patients with MAB21L2 gene variants in the clinical genetic database of Zhongshan Ophthalmic Center, Sun Yat-sen University. A retrospective review was undertaken to analyze the phenotype-genotype correlations of MAB21L2 gene variants and the highly homologous MAB21L1 gene variants reported in the previous literature. Results: Two heterozygous MAB21L2 gene variants were identified in two families with microphthalmia: Proband 1 carried the known variant c.151C>G/p.(Arg51Gly), presenting with bilateral microphthalmia with iris-choroidal coloboma and flexion of joints. The mother carried the same heterozygous variant but had a normal phenotype. Proband 2 carried the unreported variant c.1042G>T/p.(Glu348*), manifesting as left-sided microphthalmia with a normal right eye and no other systemic abnormalities. Through literature review, we found that under a dominant inheritance pattern, 80% of heterozygous pathogenic MAB21L2 variants (20/25) and 100% of heterozygous pathogenic MAB21L1 variants (25/25) occurred in the amino acid region 49-52, resulting in microphthalmia, anophthalmia, and coloboma (MAC). Some patients with heterozygous MAB21L2 variants in this region exhibited additional skeletal and joint dysplasia (12/24, 50%). Heterozygous truncating variants in MAB21L2 led to MAC (5/5, 100%), while those in MAB21L1 were non-pathogenic. Conclusions: This study identified a novel pathogenic variant and a known hotspot pathogenic variant of MAB21L2 in two families with microphthalmia. Through a comprehensive literature review, we compared and summarized the mutation spectrums and genotype-phenotype correlations of MAB21L1 and MAB21L2 genes, providing valuable insights for the diagnosis and differential diagnosis of genetic diseases caused by these gene defects.

目的：比较六种新一代人工晶状体(intraocular lens,IOL)屈光力计算公式[Barrett Universal Ⅱ(BUⅡ)、Emmetropia Verifying Optical(EVO)、Hill-Radial Basis Function (Hill-RBF)、Kane、Ladas Super Formula(LSF)、T2]和传统公式(Haigis、Hoffer Q、Holladay 1、SRK/T)的准确性。方法：纳入2022年1—6月于温州医科大学附属眼视光医院接受白内障手术患者。收集患者的年龄、性别、眼轴(axial length,AL)、平均角膜曲率(mean keratometry,Kmean)、前房深度、IOL常数和屈光力，术后医学验光结果。对上述10种公式进行准确性分析，包括平均预测误差(mean prediction error,ME)及其标准差、平均绝对预测误差(mean absolute prediction error,MAE)、绝对预测误差中位数(median absolute prediction error,MedAE)、绝对预测误差最大值(maximum absolute prediction error,MaxAE)、预测误差落在±0.25、±0.5、±0.75、±1.00 D范围内的百分比(%±0.25 D、%±0.50 D、%±0.75 D、%±1.00 D)。结果：共纳入506例(506眼)。Kane的MAE最低(0.411)。Hill-RBF的%±0.25 D最高(40.91%)，EVO的%±0.50 D或%±0.75 D最高(分别为69.37%、86.17%)，BUⅡ和Hill-RBF的%±1.00 D最高(均为94.07%)。总体上各种公式间，MAE、%±0.50 D、%±0.75 D、%±1.00 D比较差异存在统计学意义(P<0.05)，但两两比较仅发现%±0.75 D中，EVO(86.17%)、Hill-RBF(85.97%)、Kane(85.57%)与HofferQ(81.42%)比较差异存在统计学意义(均P<0.05)。AL亚组中，长AL组的EVO(0.390)、Hill-RBF(0.388)、T2(0.423)、Kane(0.393)四种公式的MAE与Hoffer Q(0.681)、Holladay 1(0.654)比较差异存在统计学意义(均P<0.05)，EVO(74.47%)的%±0.50 D与Hoffer Q(46.81%)比较差异存在统计学意义(P=0.017)。结论：新一代IOL屈光力计算公式在IOL屈光力计算上均具有较好的准确性，但对于不同的眼轴长度与角膜曲率值的眼球，需要选择适合的计算公式，以进一步提高预测准确性。

Objective: This study aimed to compare the accuracy of six new generation intraocular lenses (IOL) refractive power calculation formulas (Barrett Universal Ⅱ [BU Ⅱ ], Emmetropia Verifying Optical [EVO], Hill-Radial Basis Function [Hill-RBF], Kane, Ladas Super Formula [LSF], T2) and traditional formulas (Haigis, Hoffer Q, Holladay 1, SRK/ T). Methods: The patients who received cataract surgery in the Eye Hospital of Wenzhou Medical University from January 2022 to June 2022 were included in this study. Age, gender, axial length (AL), mean keratometry, anterior chamber depth, IOL constant and power, and postoperative refraction results were collected. The prediction accuracy of these ten IOL power calculation formulas was analyzed, including mean prediction error (ME) and its standard deviation, mean absolute prediction error (MAE), median absolute prediction error (MedAE), maximum absolute prediction error (MaxAE), the percentage of eyes of PE within the range of ±0.25 D, ±0.5 D, ±0.75 D, ±1.0 D (%±0.25 D,%±0.50 D, %±0.75 D, %±1.00 D). Results: 506 eyes of 506 patients were included. Kane has the lowest MAE (0.411).%±0.25 D of Hill-RBF was the highest (40.91%), %±0.50 D or %±0.75 D of EVO was the highest (69.37%, 86.17%), and %±1.00 D of BU Ⅱ and Hill-RBF was the highest (94.07%). There are significant differences in MAE, %±0.50 D, %±0.75 D, and %±1.00 D among all formulas (P<0.05). Still, pairwise comparison only found differences between EVO (86.17%), Hill-RBF (85.97%), Kane (85.57%), and Hoffer Q (81.42%) in %±0.75 D (all P<0.05). In AL subgroup, the MAE of EVO (0.390), Hill-RBF (0.388), T2 (0.423) and Kane (0.393) in long AL group was different from that of Hoffer Q (0.681) and Holladay 1 (0.654) (all P<0.05), the difference of %±0.50D of EVO (74.47%) compared with Hoffer Q (46.81%) (P=0.017). Conclusion: The new generation of IOL power calculation formulas have good accuracy in IOL power prediction, but for eyes with different axial lengths and keratometry, it is necessary to optimize the selection of formulas to improve the prediction accuracy further.

作为一种新型无创且操作简单的主观检查手段，临界闪烁融合频率(critical flicker fusionfrequency,CFF)可动态反映人眼视功能变化情况。作为早期识别脱髓鞘病变和评估视功能恢复情况的敏感指标，上个世纪已被国外学者用于视网膜和视神经疾病研究中，包括氯喹中毒性视网膜病变、糖尿病视网膜病变、中心性浆液性视网膜病变、年龄相关的黄斑病变、乙胺丁醇中毒性视神经病变、视神经炎和非动脉炎性前部缺血性视神经病变。在视网膜和视神经疾病中，CFF均有不同程度下降，依据CFF改善程度以及主要损害的色光可能有助于视网膜和视神经疾病的鉴别，且CFF与其他视功能，视力、视野、视觉诱发电位的潜时具有较好的相关性。目前国内相关研究尚处于起步阶段，本文就CFF在视网膜和视神经疾病的应用情况做一总结。

As a new non-invasive and simple subjective examination method, critical flicker fusion frequency (CFF) can dynamically reflect the changes of visual function of human eyes. As a sensitive indicator for early identification of demyelinating diseases and assessment of visual function recovery, it has been used by foreign scholars in the last century in the field of retinal and optic nerve diseases, including chloroquine toxic retinopathy, diabetic retinopathy, central serous retinopathy, age-related macular degeneration, ethambutol-induced optic neuropathy, optic neuritis and non-arteritic anterior ischemic optic neuropathy. Though there was a different decrease of CFF in retina and optic nerve diseases, it may be helpful for the differentiation of retinal and optic nerve diseases according to the degree of CFF improvement and the main damaged color light. Moreover, CFF has a good correlation with other visual functions, visual acuity, visual field, and peak time of visual evoked potential. At present, and relevant domestic studies is still in its infancy. This article summarizes the application of CFF in retinal and optic nerve diseases.

    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.