国际期刊投稿平台
登录 | 注册
当前位置： 首页 > 亚太医学 > DME抗VEGF治疗应答异质性及早期预测
亚太医学

亚太医学

Journal of Medicine in the Asia-Pacific

  • 主办单位: 
    未來中國國際出版集團有限公司
  • ISSN: 
    3079-3483（P）
  • ISSN: 
    3080-0870（O）
  • 期刊分类: 
    医药卫生
  • 出版周期: 
    月刊
  • 投稿量: 
    2
  • 浏览量: 
    491

相关文章

暂无数据

DME抗VEGF治疗应答异质性及早期预测

Heterogeneity of Anti-VEGF Treatment Response in Diabetic Macular Edema and Early Prediction

发布时间：2026-06-17
作者: 刘雨桐 ,彭昌福 :湖南省人民医院 湖南长沙; LIU Yutong ,PENG Changfu :Hunan Provincial People's Hospital Changsha;
摘要: 糖尿病性黄斑水肿（diabetic macular edema，DME）是糖尿病患者视力损害的主要原因，抗血管内皮生长因子（anti-vascular endothelial growth factor，anti-VEGF）药物已成为一线治疗方案。然而，临床实践中约30%-40%的患者表现为应答不佳，这种治疗应答的异质性已成为制约DME精准治疗的关键瓶颈。近年来，围绕抗VEGF治疗应答异质性的机制探索及早期预测研究取得了重要进展。本文从应答异质性的病理生理机制入手，系统综述早期预测方法的研究现状与发展趋势，重点阐述临床预测因素、影像学生物标志物、炎症指标及人工智能预测模型的循证证据，分析现有研究的局限性，并展望未来多模态整合预测及个体化治疗策略的发展方向，以期为DME的精准诊疗提供理论参考。
Abstract: Diabetic macular edema (DME) is a leading cause of visual impairment in patients with diabetes. Antivascular endothelial growth factor (antiVEGF) agents have become the firstline treatment. However, in clinical practice, approximately 30%–40% of patients show a poor response, and this heterogeneity in treatment response has become a key bottleneck hampering precision therapy for DME. In recent years, significant progress has been made in exploring the mechanisms underlying heterogeneity of antiVEGF response and in early prediction. This article begins with the pathophysiological mechanisms of response heterogeneity and systematically reviews the current status and future trends in early prediction methods, with an emphasis on evidence regarding clinical predictors, imaging biomarkers, inflammatory indicators, and artificial intelligencebased prediction models. It also analyzes the limitations of existing studies and discusses future directions in multimodal integrated prediction and individualized treatment strategies, aiming to provide a theoretical reference for precision diagnosis and treatment of DME.
关键词: 糖尿病性黄斑水肿；抗血管内皮生长因子治疗；治疗应答异质性；早期预测；生物标志物
Keywords: diabetic macular edema; antiVEGF therapy; heterogeneity of treatment response; early prediction; biomarkers

引言

糖尿病性黄斑水肿（diabetic macular edema，DME）是糖尿病视网膜病变（diabetic retinopathy，DR）患者中心视力损害的主要原因。随着全球糖尿病患者数量持续增长，DME的疾病负担日益加重，已成为严重的公共卫生问题。抗血管内皮生长因子（anti-vascular endothelial growth factor，anti-VEGF）药物的问世极大地改善了DME患者的预后，多项大型临床试验证实其能有效减轻黄斑水肿、改善视力。

然而，临床实践揭示了一个重要现象：DME患者对抗VEGF治疗的反应存在显著的个体差异，约30%-40%的患者表现为“应答不佳”，即经过3-6次标准治疗后仍存在持续性黄斑水肿或视力改善不理想。这种治疗应答的异质性已成为制约DME精准治疗的关键瓶颈，不仅导致医疗资源浪费，更可能使患者错失最佳治疗时机，造成不可逆的视力损害。

深入理解治疗应答异质性的形成机制，建立可靠的早期预测方法，已成为DME临床研究的前沿热点。近年来，围绕这一方向的研究取得了显著进展：一方面，研究者从炎症反应、氧化应激、玻璃体视网膜界面异常等角度揭示了应答异质性的病理生理基础；另一方面，多种预测因素被证实与治疗应答相关，包括临床特征、OCT生物标志物、外周血炎症指标、遗传因素等。更重要的是，基于多模态数据的预测模型和人工智能技术的发展，为早期识别应答不佳者、实现个体化治疗提供了新的可能。

本文旨在系统综述DME抗VEGF治疗应答异质性的病理生理机制及早期预测方法的研究进展，分析现有研究的优势与不足，探讨未来多模态整合预测的发展方向，以期为DME的精准诊疗提供理论参考。

1 抗VEGF治疗应答异质性的病理生理基础

1.1 炎症反应的主导作用

DME的发病机制涉及多种病理因素，其中炎症反应与血管渗漏的相互作用是形成应答异质性的核心机制。研究表明，VEGF和各类炎性因子在疾病进展中形成正反馈环路：VEGF诱导血管渗漏和白细胞黏附，活化的炎性细胞释放更多炎性因子，进一步上调VEGF表达。当抗VEGF疗法效果不理想时，提示炎症通路可能在该类患者中占据主导地位。

长期高血糖可激活NF-κB、MAPK等信号通路，诱发局部微炎症反应。视网膜功能异常促使单核细胞、巨噬细胞、小胶质细胞及脉络膜肥大细胞等免疫细胞激活，释放IL-6、IL-1β、TNF-α、MCP-1等多种炎性因子。这些炎性因子一方面直接破坏血管内皮细胞间连接，另一方面通过激活基质金属蛋白酶降解细胞外基质，导致血-视网膜屏障持续破坏。当炎症反应成为主要驱动力时，单纯抗VEGF治疗往往难以达到理想效果。

1.2 氧化应激与线粒体功能障碍

氧化应激在DME治疗应答异质性中同样扮演关键角色。长期高血糖状态下，NADPH氧化酶途径被激活，导致活性氧簇（ROS）过度积累。ROS不仅直接损伤视网膜细胞大分子结构，还可通过诱导局部缺血上调VEGF和胎盘生长因子表达。更重要的是，氧化应激可诱导线粒体功能障碍和DNA损伤，导致视网膜神经元及胶质细胞凋亡，这种神经退行性改变即使在水肿消退后也难以完全恢复。

研究表明，氧化应激还可激活NF-κB炎症通路，放大炎症级联反应。因此，对于氧化应激占主导的患者，单纯抗VEGF治疗难以逆转已发生的神经损伤，导致治疗应答不佳。

1.3玻璃体视网膜界面异常

玻璃体视网膜界面的异常改变是导致DME向难治性转变的重要因素。不完全玻璃体后脱离、视网膜前膜形成、内界膜增厚等均可造成黄斑区的机械性牵拉，同时作为细胞因子的“蓄水池”，导致局部炎症因子浓度升高。研究发现，存在视网膜前膜的DME患者对抗VEGF治疗的反应显著差于无视网膜前膜者，更易发展为难治性DME。

内界膜增厚会阻碍玻璃体与视网膜之间的物质交换，限制抗VEGF药物在视网膜的分布，从而降低药物疗效。因此，对于存在明显玻璃体视网膜界面异常的患者，即使接受规范的抗VEGF治疗，其应答也往往不佳。

1.4 遗传因素的影响

遗传因素在抗VEGF治疗应答异质性中的作用日益受到关注。全基因组关联分析发现了与治疗应答相关的基因多态性，包括DIRC3、SLCO3A1、RAB2A等。与VEGF信号通路相关的基因多态性（如VEGF-A）已被证实与抗VEGF治疗应答相关。此外，DNA甲基转移酶在非应答者中表达显著上调，提示表观遗传学改变可能参与应答异质性的形成。这些发现为理解治疗应答异质性提供了新的视角。

2早期预测方法的研究进展

2.1 临床预测因素

2.1.1 基线视力与治疗前特征

基线视力是预测治疗应答的重要临床因素。多项研究证实，基线视力较差的患者往往能获得更大的视力改善。这可能与视力改善的“天花板效应”有关。更重要的是，首次注射后1个月时的视力变化被证实是预测12个月时视力结局的最强指标，提示早期视力应答可作为预测长期疗效的重要参考。

DME病程与治疗应答相关，病程较短的患者对抗VEGF治疗反应更好。Panozzo等提出的ESASO DME分型系统将DME分为早期、进展期、晚期和萎缩期，研究发现早期DME患者对治疗的反应显著优于晚期患者。

2.1.2 血糖控制状态

血糖控制水平与治疗应答密切相关。多项研究显示，糖化血红蛋白（HbA1c）水平较高的患者对抗VEGF治疗应答较差。高血糖状态下炎症因子水平升高、VEGF表达上调、血-视网膜屏障损伤更严重。然而，也有研究未发现HbA1c与治疗应答的相关性，提示血糖控制可能仅是影响疗效的众多因素之一。

2.2 OCT生物标志物的预测价值

2.2.1 中央视网膜厚度

中央视网膜厚度（CRT）或黄斑中心凹视网膜厚度（CMT）是最常用的OCT参数。基线CMT较高的患者对抗VEGF治疗反应更好，CMT下降幅度更大。更重要的是，首针后1个月时CMT下降百分比被证实能够有效区分出在3个月及1年时应答不佳的患者。Shah等的研究显示，首次注射后1个月CMT下降≥20%的患者，加载期后应答不佳率仅为18%，而CMT下降<20%的患者应答不佳率高达62%。Maeda等的研究也证实，首次注射后1个月的CMT下降百分比与第三次注射后的CMT下降百分比显著相关。

2.2.2 高反射点

高反射点（HRF）是反映视网膜炎症状态的重要OCT生物标志物。研究发现，HRF在抗VEGF治疗后显著减少，可作为评估抗炎效果的指标。基线HRF数量与治疗应答相关，HRF数量多的患者应答较差。Yoshitake等发现HRF的减少与视力改善相关，但HRF的消退可能需要较长时间（6个月以上）。这些发现提示，对于HRF较多的患者，可能需要更强或更持久的抗炎治疗。

2.2.3视网膜内层结构紊乱

视网膜内层结构紊乱（DRIL）反映视网膜内层神经元结构的破坏，是预测视力预后的强有力负面指标。DRIL的存在往往预示着更差的视力结局和对治疗的不敏感。Radwan等的研究发现，DRIL的改善与视力恢复相关，但改善程度有限，即使在水肿消退后也难以完全恢复。Okudan等的研究显示，DRIL在抗VEGF治疗后3个月内无明显变化，提示DRIL反映的是相对不可逆的结构损伤。因此，对于存在DRIL的患者，早期干预至关重要。

2.2.4 椭圆体带/外界膜完整性

椭圆体带（EZ）和外界膜（ELM）的完整性直接反映光感受器细胞的健康状态。多项研究证实，EZ/ELM的损伤与预后不良相关。Gerendas等的研究显示，基线EZ完整性是预测抗VEGF治疗后视力结局的重要指标，EZ完整的患者治疗后视力改善更显著。由于EZ/ELM损伤在治疗后改善有限，早期识别并干预对于保护光感受器功能至关重要。

2.2.5视网膜下积液

视网膜下积液（SRF）在DME中的发生率约为15%-30%。关于SRF对治疗应答的影响，研究结果尚不一致。部分研究显示SRF的存在与更好的功能和解剖学结局相关，可能与SRF反映的是急性血管渗漏有关。但也有研究未发现SRF与治疗应答的相关性。这种差异可能与SRF的持续时间、高度及是否伴有其他OCT特征有关，需进一步研究阐明。

2.3 外周血炎症指标的预测价值

2.3.1 中性粒细胞/淋巴细胞比值

中性粒细胞/淋巴细胞比值（NLR）是反映全身炎症状态的简便指标。Hu等的研究发现，基线NLR≥2.27与较差的视力结局相关。Katic等的研究显示，NLR在非应答组显著升高，预测早期应答的AUC为0.778。Yalinbas等的研究发现，NLR≥2.0对预测DME患者早期抗VEGF药物治疗反应具有一定的临床价值。

2.3.2 血小板/淋巴细胞比值

血小板/淋巴细胞比值（PLR）也是常用的炎症指标。Ergin等的研究显示，PLR在非应答组显著升高，并与早期功能改善相关。Katic等的研究显示，PLR预测早期抗VEGF治疗应答的AUC为0.719。多因素分析显示，PLR是早期功能应答的独立预测因素。

2.3.3 系统性免疫炎症指数

系统性免疫炎症指数（SII）是结合中性粒细胞、血小板和淋巴细胞的综合指标。Ergin等的研究显示，SII在非应答组显著升高，对早期解剖学应答具有良好的预测价值（AUC=0.788）。多变量模型（SII+基线CMT+IRF）预测早期解剖应答的AUC可达0.911。Zhou等的研究发现，SII与DME患者HRF数量显著相关，进一步证实了炎症反应在HRF形成中的作用。

2.4 人工智能预测模型的发展

2.4.1传统机器学习方法

传统机器学习方法在DME治疗应答预测中已显示出良好效果。Tamilselvi等的系统综述纳入50项研究，机器学习模型预测治疗应答的最高灵敏度达92%。Cao等基于OCT影像组学特征构建的随机森林模型预测抗VEGF治疗应答的AUC达0.923。

2.4.2 深度学习模型

深度学习技术在OCT图像分析中取得了显著进展。APTOS2021大数据竞赛首次探索了治疗前分层预测DME疗效，提供了包含2000名患者数万张OCT图像的公开数据集，最佳模型的AUC达80.06%。Roberts等利用深度学习方法自动量化OCT图像中的视网膜内积液和视网膜下积液，发现积液体积与视力结局相关。Al-Qazlan等的Meta分析显示，AI模型预测抗VEGF治疗应答的合并灵敏度为86.4%，特异度为77.6%，汇总AUC为0.89。

2.4.3 多模态整合预测

由于DME的发病机制涉及多种因素，整合多模态数据的预测模型逐渐成为研究热点。Yanxia等构建了包含外周血炎症指标和OCT生物标志物的诺模图，预测抗VEGF治疗应答的AUC达0.866。Atik等整合OCT图像和临床数据，构建的深度学习模型预测DME治疗应答的AUC达0.81。这些研究提示，多模态预测模型较单一指标具有更高的预测效能。

3 小结

DME患者抗VEGF治疗应答的异质性已成为制约精准治疗的关键瓶颈。深入理解应答异质性的病理生理机制，建立可靠的早期预测方法，对于实现个体化治疗、改善患者预后具有重要意义。目前，临床预测因素、OCT生物标志物、外周血炎症指标及人工智能预测模型均展现出良好的预测价值，但单一指标难以全面反映疾病的复杂性。未来，随着多模态数据整合技术的发展，以及可解释性人工智能的应用，早期识别应答不佳者、制定个体化治疗策略将逐步成为现实，为DME患者带来更大的临床获益。

参考文献：

  1. [1] Varma R, Bressler N M, Doan Q V, et al. Prevalence of and risk factors for diabetic macular edema in the United States[J]. JAMA ophthalmology,2014,132(11):1334-1340.
  2. [2] Wells J A, Glassman A R, Ayala A R, et al. Aflibercept, bevacizumab, or ranibizumab for diabetic macular edema[J]. New England journal of medicine,2015,372(13):1193-1203.
  3. [3] Bressler N M, Beaulieu W T, Glassman A R, et al. Persistent macular thickening following intravitreous aflibercept, bevacizumab, or ranibizumab for central-involved diabetic macular edema with vision impairment: A secondary analysis of a randomized clinical trial[J]. JAMA ophthalmology,2018,136(03):257-269.
  4. [4] Zhang J, Zhang J, Zhang C, et al. Diabetic macular edema: current understanding, molecular mechanisms and therapeutic implications[J]. Cells,2022,11(21):3362.
  5. [5] Chang Y C, Huang Y T, Hsu A Y, et al. Optical coherence tomography biomarkers in predicting treatment outcomes of diabetic macular edema after ranibizumab injections[J]. Medicina,2023,59(03):629.
  6. [6] Visioli G, Alisi L, Mastrogiuseppe E, et al. OCT biomarkers as predictors of visual improvement in diabetic macular edema eyes receiving dexamethasone implants[J]. International journal of retina and vitreous,2023,9(01):35.
  7. [7] Katic K, Katic J, Kumric M, et al. The predictors of early treatment effectiveness of intravitreal bevacizumab application in patients with diabetic macular edema[J]. Diagnostics,2024,14(09):992.
  8. [8] Schmidt-Erfurth U, Reiter G S, Riedl S, et al. AI-based monitoring of retinal fluid in disease activity and under therapy[J]. Progress in retinal and eye research,2022,86:100972.
  9. [9] Romero-Aroca P, Baget-Bernaldiz M, Pareja-Rios A, et al. Diabetic macular edema pathophysiology: Vasogenic versus inflammatory[J]. Journal of diabetes research,2016,2016:2156273.
  10. [10] Sohn H J, Han D H, Kim I T, et al. Changes in aqueous concentrations of various cytokines after intravitreal triamcinolone versus bevacizumab for diabetic macular edema[J]. American journal of ophthalmology,2011,152(04):686-694.
  11. [11] Vujosevic S, Simo R. Local and systemic inflammatory biomarkers of diabetic retinopathy: An integrative approach[J]. Investigative ophthalmology & visual science,2017,58(06): BIO68-BIO75.
  12. [12] Kovoor E, Chauhan S K, Hajrasouliha A. Role of inflammatory cells in pathophysiology and management of diabetic retinopathy[J]. Survey of ophthalmology,2022,67(06):1563-1573.
  13. [13] Das A, McGuire P G, Rangasamy S. Diabetic macular edema: pathophysiology and novel therapeutic targets[J]. Ophthalmology,2015,122(07):1375-1394.
  14. [14] Miller K, Fortun J A. Diabetic macular edema: current understanding, pharmacologic treatment options, and developing therapies[J]. Asia-Pacific journal of ophthalmology,2018,7(01):28-35.
  15. [15] Rübsam A, Parikh S, Fort P E. Role of inflammation in diabetic retinopathy[J]. International journal of molecular sciences,2018,19(03):942.
  16. [16] Veloso C E, Brocchi D N, Singh R P, et al. Vitreomacular interface after anti-VEGF injections in diabetic macular edema[J]. International journal of retina and vitreous,2021,7(01):1-7.
  17. [17] Yoon D, Rusu I, Barbazetto I. Reduced treatment burden in diabetic macular edema using treat-and-extend regimen with intravitreal aflibercept[J]. Clinical ophthalmology,2019（13）:1697-1703.
  18. [18] Gunduz K, Bakri S J. Management of refractory diabetic macular edema[J]. Expert opinion on pharmacotherapy,2021,22(08):1021-1031.
  19. [19] Shah A R, Yonekawa Y, Todorich B, et al. Prediction of anti-VEGF response in diabetic macular edema after1 injection[J]. Journal of vitreoretinal diseases,2017,1(03):169-174.
  20. [20] Hong E H, Yeom H, Yu H S, et al. Genome-wide association study of the response of patients with diabetic macular edema to intravitreal anti-VEGF injection[J]. Scientific reports,2022,12(01):22527.
  21. [21] Ristić B, et al. Genetic polymorphisms and response to anti-VEGF therapy in diabetic macular edema: a systematic review[J]. International journal of molecular sciences,2023,24(05):4825.
  22. [22] Camacho P, Ribeiro E, Pereira B, et al. DNA methyltransferase expression (DNMT1, DNMT3a and DNMT3b) as a potential biomarker for anti-VEGF diabetic macular edema response[J]. European journal of ophthalmology,2023,33(06):2267-2274.
  23. [23] Bressler S B, Odia I, Glassman A R, et al. Changes in diabetic retinopathy severity when treating diabetic macular edema with ranibizumab: DRCR.net Protocol I5-year report[J]. Retina,2018,38(10):1896-1904.
  24. [24] Gonzalez V H, Campbell J, Holekamp N M, et al. Early and long-term responses to anti-vascular endothelial growth factor therapy in diabetic macular edema: analysis of Protocol I data[J]. American journal of ophthalmology,2016,172:72-79.
  25. [25] Gurung R L, FitzGerald L M, Liu E, et al. Predictive factors for treatment outcomes with intravitreal anti-vascular endothelial growth factor injections in diabetic macular edema in clinical practice[J]. International journal of retina and vitreous,2023,9(01):23.
  26. [26] Panozzo G, Cicinelli M V, Augustin A J, et al. An optical coherence tomography-based grading of diabetic maculopathy proposed by an international expert panel: The European school for advanced studies in ophthalmology classification[J]. European journal of ophthalmology,2020,30(01):8-18.
  27. [27] Bressler N M, Beaulieu W T, Maguire M G, et al. Early response to anti-VEGF treatment and long-term outcomes in diabetic macular edema: Protocol T study results[J]. JAMA Ophthalmology,2018,136(04):383-389.
  28. [28] Maeda S, Sugimoto M, Tenma Y, et al. Response to initial anti-vascular endothelial growth factor for diabetic macular edema is significantly correlated with response to third consecutive monthly injection[J]. Journal of clinical medicine,2022,11(21):6416.
  29. [29] Sophie R L. Early retinal thickness reduction predicts long-term visual outcomes in diabetic macular edema[J]. Ophthalmology,2015,122(03):579-586.
  30. [30] Santos A R, Gomes S C, Figueira J, et al. Degree of decrease in central retinal thickness predicts visual acuity response to intravitreal ranibizumab in diabetic macular edema[J]. Ophthalmologica,2014,231(01):16-22.
  31. [31] Vujosevic S, Bini S, Midena G, et al. Hyperreflective intraretinal spots in diabetics without and with nonproliferative diabetic retinopathy: an in vivo study using spectral domain OCT[J]. Journal of diabetes research,2013,2013:491835.
  32. [32] Schreur V, Altay L, van Asten F, et al. Hyperreflective foci on optical coherence tomography associate with treatment outcome for anti-VEGF in patients with diabetic macular edema[J]. Plos one,2018,13(10): e0206482.
  33. [33] Yoshitake T, Murakami T, Suzuma K, et al. Hyperreflective foci in the outer retinal layers as a predictor of the functional efficacy of ranibizumab for diabetic macular edema[J]. Scientific reports,2020,10(01):873.
  34. [34] Sun J K, Lin M, Lammer J, et al. Disorganization of the retinal inner layers as a predictor of visual acuity in eyes with center-involved diabetic macular edema[J]. JAMA ophthalmology,2014,132(11):1309-1316.
  35. [35] Radwan S H, Soliman A Z, Tokarev J, et al. Association of disorganization of retinal inner layers with vision after resolution of center-involved diabetic macular edema[J]. JAMA ophthalmology,2015,133(07):820-825.
  36. [36] Okudan S, Acar Duyan S, Erdem A, et al. Optical coherence tomography biomarkers predict the long-term restorative effect of early anti-VEGF treatment on diabetic macular edema[J]. Life,2025,15(02):269.
  37. [37] Murakami T, Suzuma K, Uji A, et al. Association between characteristics of foveal cystoid spaces and short-term responsiveness to ranibizumab for diabetic macular edema[J]. Japanese journal of ophthalmology,2018,62(03):292-301.
  38. [38] Wirth M A, Wons J, Freiberg F J, et al. Impact of long-term intravitreal anti-vascular endothelial growth factor on preexisting microstructural alterations in diabetic macular edema[J]. Retina,2018,38(09):1824-1829.
  39. [39] Gerendas B S, Prager S, Deak G, et al. Predictive imaging biomarkers relevant for functional and anatomical outcomes during ranibizumab therapy of diabetic macular oedema[J]. British journal of ophthalmology,2018,102(02):195-203.
  40. [40] Bonfiglio V, Reibaldi M, Pizzo A, et al. Dexamethasone for unresponsive diabetic macular oedema: optical coherence tomography biomarkers[J]. Acta ophthalmologica,2019,97(04):540-544.
  41. [41] Seo K H, Yu S Y, Kim M, et al. Visual and morphologic outcomes of intravitreal ranibizumab for diabetic macular edema based on optical coherence tomography patterns[J]. Retina,2016,36(03):588-595.
  42. [42] Hu Y, Cheng Y, Xu X, et al. Pretreatment neutrophil-to-lymphocyte ratio predicts prognosis in patients with diabetic macular edema treated with ranibizumab[J]. BMC ophthalmology,2019,19(01):194.
  43. [43] Yalinbas Yeter D, Eroglu S, Sariakali B, et al. The usefulness of monocyte-to-high density lipoprotein and neutrophil-to-lymphocyte ratio in diabetic macular edema prediction and early anti-VEGF treatment response[J]. Ocular immunology and inflammation,2022,30(04):901-906.
  44. [44] Ergin E, Dascalu A M, Stana D, et al. Predictive role of complete blood count-derived inflammation indices and optical coherence tomography biomarkers for early response to intravitreal anti-VEGF in diabetic macular edema[J]. Biomedicines,2025,13(06):1308.
  45. [45] Zhou J, Song S, Zhang Y, et al. OCT-based biomarkers are associated with systemic inflammation in patients with treatment-naive diabetic macular edema[J]. Ophthalmology and therapy,2022,11(06):2153-2167.
  46. [46] Tamilselvi S, Suchetha M, Ratra D, et al. Evaluating anti-VEGF responses in diabetic macular edema: a systematic review with AI-powered treatment insights[J]. Indian journal of ophthalmology,2025,73(06):797-806.
  47. [47] Cao J, You K, Jin K, et al. Prediction of response to anti-vascular endothelial growth factor treatment in diabetic macular oedema using an optical coherence tomography-based machine learning method[J]. Acta ophthalmologica,2021,99(01): e19-e27.
  48. [48] Zhang W, Chotcomwongse P, Li Y, et al. Predicting diabetic macular edema treatment responses using OCT: dataset and methods of APTOS competition[J]. Medical image analysis,2026，109:103942.
  49. [49] Roberts P K, Vogl W D, Gerendas B S, et al. Quantification of fluid resolution and visual acuity gain in patients with diabetic macular edema using deep learning: a post hoc analysis of a randomized clinical trial[J]. JAMA ophthalmology,2020,138(09):945-953.
  50. [50] Al-Qazlan F. Diagnostic accuracy of artificial intelligence in predicting anti-VEGF treatment response in diabetic macular edema: a systematic review and meta-analysis[J]. Journal of clinical medicine,2025,14(22):8177.
  51. [51] Yanxia C. A nomogram based on peripheral blood inflammatory indices and optical coherence tomography biomarkers for early prediction of anti-VEGF response in diabetic macular edema[J]. Clinical and experimental optometry,2025,108(04):1-10.
  52. [52] Atik M E, Kocak I, Sayin N, et al. Integration of optical coherence tomography images and real-life clinical data for deep learning modeling: a unified approach in prognostication of diabetic macular edema[J]. Journal of biophotonics,2025,18(02): e202400315.
联系我们
人工客服，稿件咨询
投稿
扫码添加微信
客服
置顶