人工智能在干眼管理中的应用进展

Advances in the application of artificial intelligence to dry eye disease management

摘要

人工智能(artificial intelligence, AI)是通过模拟人类思维与学习过程,实现数据分析与辅助决策的技术体系。干眼(dry eye disease, DED)是一种常见的慢性眼表疾病,传统诊疗过程依赖人工判断,存在主观性强、重复性差及效率低等不足。近年来,随着图像识别、深度学习与多模态数据融合等技术的发展,AI在医学领域的应用快速拓展,为DED的早期筛查、精准诊断、个体化治疗及长期随访提供了全新技术路径。本文以技术为导向,系统回顾了AI在DED临床管理各环节中的最新研究进展,深入分析当前面临的技术局限与临床应用瓶颈,重点阐述AI在提升诊断客观性与标准化水平、优化个体化治疗策略、构建智能化监测随访体系等方面的重要价值与应用前景。同时,本文对AI辅助DED管理的未来发展趋势进行展望,旨在为推进DED诊疗的智能化转型与精准医学实践提供参考。

Abstract

Artificial intelligence (AI) mimics human cognitive processes to facilitate data analysis and support decision-making. Dry eye disease (DED) is a common chronic disorder of the ocular surface, and conventional diagnosis and treatment rely on manual judgement, which is often subjective, unreliable, and inefficient. However, recent advances in image recognition, deep learning and multimodal data fusion have expanded the role of AI in medicine. This offers new approaches for the early screening, accurate diagnosis and personalised treatment of DED, as well as its long-term follow-up. This technology-focused review summarises recent advances in AI across all stages of DED clinical management. It analyses current technical limitations and implementation challenges, and highlights the value of AI in enhancing diagnostic objectivity, optimising individualised therapeutic strategies, and establishing intelligent monitoring systems. It also discusses future directions in AI-assisted DED management to guide the intelligent transformation of DED care and promote the practice of precision medicine.

关键词

人工智能 / 干眼 / 深度学习 / 机器学习 / 多模态数据

Key words

Artificial intelligence / Dry eye disease / Deep learning / Machine learning / Multimodal data

参考文献

[1] Tsubota K , Pflugfelder SC , Liu ZG , et al. Defining dry eye from a clinical perspective[J]. Int J Mol Sci, 2020, 21(23): 9271. doi: 10.3390/ijms21239271

[2] Sheppard J , Shen Lee B , Periman LM . Dry eye disease: identification and therapeutic strategies for primary care clinicians and clinical specialists[J]. Ann Med, 2023, 55(1): 241-252. doi: 10.1080/07853890.2022.2157477

[3] Stapleton F , Velez FG , Lau C , et al. Dry eye disease in the young: a narrative review[J]. Ocul Surf, 2024, 31: 11-20. doi: 10.1016/j.jtos.2023.12.001

[4] Britten-Jones AC , Wang MTM , Samuels I , et al. Epidemiology and risk factors of dry eye disease: considerations for clinical management[J]. Medicina, 2024, 60(9): 1458. doi: 10.3390/medicina60091458

[5] 邵毅, 胡瑾瑜, 应平 . 干眼炎症诊疗规范: 2023欧洲专家共识解读[J]. 眼科新进展, 2024, 44(2): 85-88. doi: 10.13389/j.cnki.rao.2024.0017

[6] SHAO Yi , HU Jinyu , YING Ping . Specification for diagnosis and treatment of inflammation in dry eye: interpretation of the European Expert Consensus 2023[J]. Recent Advances in Ophthalmology, 2024, 44(2): 85-88. doi: 10.13389/j.cnki.rao.2024.0017

[7] Storås AM , Strümke I , Riegler MA , et al. Artificial intelligence in dry eye disease[J]. Ocul Surf, 2022, 23: 74-86. doi: 10.1016/j.jtos.2021.11.004

[8] Mintz Y , Brodie R . Introduction to artificial intelligence in medicine[J]. Minim Invasive Ther Allied Technol, 2019, 28(2): 73-81. doi: 10.1080/13645706.2019.1575882

[9] 邵毅, 接英, 刘祖国, 等 . 人工智能在眼前节疾病诊断中的应用指南(2023)[J]. 国际眼科杂志, 2023, 23(9): 1421-1430. doi: 10.3980/j.issn.1672-5123.2023.9.02

[10] SHAO Yi , JIE Ying , LIU Zuguo , et al. Guidelines for the application of artificial intelligence in the diagnosis of anterior segment diseases (2023)[J]. International Eye Science, 2023, 23(9): 1421-1430. doi: 10.3980/j.issn.1672-5123.2023.9.02

[11] Larentzakis A , Lygeros N . Artificial Intelligence (AI) in medicine as a strategic valuable tool[J]. Pan Afr Med J, 2021, 38: 184. doi: 10.11604/pamj.2021.38.184.28197

[12] Hogarty DT , Mackey DA , Hewitt AW . Current state and future prospects of artificial intelligence in ophthalmology: a review[J]. Clin Exp Ophthalmol, 2019, 47(1): 128-139. doi: 10.1111/ceo.13381

[13] 韩雪, 丁婧娟, 陆淑婷, 等 . 人工智能在干眼诊断中的研究进展[J]. 国际眼科杂志, 2022, 22(12): 2063-2067. doi: 10.3980/j.issn.1672-5123.2022.12.25

[14] HAN Xue , DING Jingjuan , LU Shuting , et al. Application of artificial intelligence in the diagnosis of dry eye[J]. International Eye Science, 2022, 22(12): 2063-2067. doi: 10.3980/j.issn.1672-5123.2022.12.25

[15] 于薏, 周奕文, 杨燕宁 . 人工智能在眼表疾病中的应用现况[J]. 国际眼科杂志, 2022, 22(5): 726-730. doi: 10.3980/j.issn.1672-5123.2022.5.06

[16] YU Yi , ZHOU Yiwen , YANG Yanning . Application of artificial intelligence in ocular surface diseases[J]. International Eye Science, 2022, 22(5): 726-730. doi: 10.3980/j.issn.1672-5123.2022.5.06

[17] 钱金梅, 蔡岩 . 干眼患者泪液相关检测指标及技术的研究进展[J]. 国际眼科杂志, 2024, 24(9): 1448-1452. doi: 10.3980/j.issn.1672-5123.2024.9.18

[18] QIAN Jinmei , CAI Yan . Advances in tear-related indicators and techniques for patients with dry eye disease[J]. International Eye Science, 2024, 24(9): 1448-1452. doi: 10.3980/j.issn.1672-5123.2024.9.18

[19] Su TY , Liu ZY , Chen DY . Tear film break-up time measurement using deep convolutional neural networks for screening dry eye disease[J]. IEEE Sens J, 2018, 18(16): 6857-6862. doi: 10.1109/JSEN.2018.2850940

[20] Deng XY , Tian L , Liu ZY , et al. A deep learning approach for the quantification of lower tear Meniscus height[J]. Biomed Signal Process Control, 2021, 68: 102655. doi: 10.1016/j.bspc.2021.102655

[21] Wang SP , He X , He JZ , et al. A fully automatic estimation of tear Meniscus height using artificial intelligence[J]. Invest Ophthalmol Vis Sci, 2023, 64(13): 7. doi: 10.1167/iovs.64.13.7

[22] Vaccaro S , Borselli M , Scalia G , et al. A novel noninvasive screening tool for dry eye disease[J]. Diagnostics, 2024, 14(12): 1209. doi: 10.3390/diagnostics14121209

[23] Han YJ , Kim W , Park JS . Efficient eye-blinking detection on smartphones: a hybrid approach based on deep learning[J]. Mob Inf Syst, 2018, 2018(1): 6929762. doi: 10.1155/2018/6929762

[24] Zheng QX , Wang L , Wen H , et al. Impact of incomplete blinking analyzed using a deep learning model with the keratograph 5M in dry eye disease[J]. Transl Vis Sci Technol, 2022, 11(3): 38. doi: 10.1167/tvst.11.3.38

[25] Jo HC , Jeong H , Lee J , et al. Quantification of blood flow velocity in the human conjunctival microvessels using deep learning-based stabilization algorithm[J]. Sensors, 2021, 21(9): 3224. doi: 10.3390/s21093224

[26] «面向人工智能应用的干眼影像分类与标注方法流程及质量控制专家共识(2025)»专家组, 中国医药教育协会智能眼科分会 . 面向人工智能应用的干眼影像分类与标注方法、流程及质量控制专家共识(2025)[J]. 中华实验眼科杂志, 2025, 43(4): 289-300. doi: 10.3760/cma.j.cn115989-20250227-00055

[27] Expert Workgroup of Expert consensus on classification and annotation methods, processes and quality control for dry eye imaging in artificial intelligence applications (2025), Intelligent Ophthalmology Branch of China Medical Education Association . Expert consensus on classification and annotation methods, processes and quality control for dry eye imaging in artificial intelligence applications (2025)[J]. Chinese Journal of Experimental Ophthalmology, 2025, 43(4): 289-300. doi: 10.3760/cma.j.cn115989-20250227-00055

[28] Wang JY , Li SX , Yeh TN , et al. Quantifying meibomian gland morphology using artificial intelligence[J]. Optom Vis Sci, 2021, 98(9): 1094-1103. doi: 10.1097/opx.0000000000001767

[29] Yokoi N , Kusada N , Kato H , et al. Dry eye subtype classification using videokeratography and deep learning[J]. Diagnostics, 2023, 14(1): 52. doi: 10.3390/diagnostics14010052

[30] Shimizu E , Ishikawa T , Tanji M , et al. Artificial intelligence to estimate the tear film breakup time and diagnose dry eye disease[J]. Sci Rep, 2023, 13(1): 5822. doi: 10.1038/s41598-023-33021-5

[31] Setu MAK , Horstmann J , Schmidt S , et al. Deep learning-based automatic meibomian gland segmentation and morphology assessment in infrared meibography[J]. Sci Rep, 2021, 11(1): 7649. doi: 10.1038/s41598-021-87314-8

[32] Li L , Xiao K , Lai T , et al. Development and multi-center validation of an AI driven model for quantitative meibomian gland evaluation[J/OL]. Npj Digital Medicine, 2025, 8(1): 403. doi: 10.1038/s41746-025-01753-5

[33] Abdelmotaal H , Hazarbasanov R , Taneri S , et al. Detecting dry eye from ocular surface videos based on deep learning[J]. Ocul Surf, 2023, 28: 90-98. doi: 10.1016/j.jtos.2023.01.005

[34] Kim S , Park D , Shin Y , et al. Deep learning-based fully automated grading system for dry eye disease severity[J]. PLoS One, 2024, 19(3): e0299776. doi: 10.1371/journal.pone.0299776

[35] 韩亚波, 易全勇 . 人工智能在睑板腺功能障碍相关干眼中的应用现状及进展[J]. 中华实验眼科杂志, 2024, 42(2): 187-191. doi: 10.3760/cma.j.cn115989-20220821-00385

[36] HAN Yabo , YI Quanyong . Application status and progress of artificial intelligence in dry eye associated with meibomian gland dysfunction[J]. Chinese Journal of Experimental Ophthalmology, 2024, 42(2): 187-191. doi: 10.3760/cma.j.cn115989-20220821-00385

[37] Stapleton F , Alves M , Bunya VY , et al. TFOS DEWS II epidemiology report[J]. Ocul Surf, 2017, 15(3): 334-365. doi: 10.1016/j.jtos.2017.05.003

[38] Nair PP , Keskar M , Borghare PT , et al. Artificial intelligence in dry eye disease: a narrative review[J]. Cureus, 2024, 16(9): e70056. doi: 10.7759/cureus.70056

[39] Graham AD , Wang JY , Kothapalli T , et al. Artificial intelligence models utilize lifestyle factors to predict dry eye related outcomes[J]. Sci Rep, 2025, 15: 13378. doi: 10.1038/s41598-025-96778-x

[40] Wiedemann Peter , HUI Yannian . Artificial intelligence in ophthalmology[J]. International Eye Science, 2023, 23(9): 1417-1420. doi: 10.3980/j.issn.1672-5123.2023.9.01

[41] 李朝辉, 吴畏 . 重视人工智能在眼科领域的应用[J]. 解放军医学院学报, 2022, 43(10): 1010-1013. doi: 10.3969/j.issn.2095-5227.2022.10.002

[42] LI Zhaohui , WU Wei . Prospects of artificial intelligence in ophthalmology[J]. Academic Journal of Chinese Pla Medical School, 2022, 43(10): 1010-1013. doi: 10.3969/j.issn.2095-5227.2022.10.002

[43] Gong D , Li XM , Wan C , et al. Development and research status of intelligent ophthalmology in China[J]. Int J Ophthalmol, 2024, 17(12): 2308-2315. doi: 10.18240/ijo.2024.12.20

[44] Wang MH , Jiang XD , Zeng PJ , et al. Balancing accuracy and user satisfaction: the role of prompt engineering in AI-driven healthcare solutions[J]. Front Artif Intell, 2025, 8: 1517918. doi: 10.3389/frai.2025.1517918

[45] Li YH , Li YL , Wei MY , et al. Innovation and challenges of artificial intelligence technology in personalized healthcare[J]. Sci Rep, 2024, 14(1): 18994. doi: 10.1038/s41598-024-70073-7

[46] Ting DSJ , Foo VH , Yang LWY , et al. Artificial intelligence for anterior segment diseases: Emerging applications in ophthalmology[J]. Br J Ophthalmol, 2021, 105(2): 158-168. doi: 10.1136/bjophthalmol-2019-315651

[47] Hamet P , Tremblay J . Artificial intelligence in medicine[J]. Metabolism, 2017, 69: S36-S40. doi: 10.1016/j.metabol.2017.01.011

[48] 钱波, 李富江, 郑常乐, 等 . 医疗大模型发展现状与展望[J]. 数据采集与处理, 2025, 40(3): 562-584. doi: 10.16337/j.1004-9037.2025.03.002

[49] QIAN Bo , LI Fujiang , ZHENG Changle , et al. A review of development and future directions of medical foundation models[J]. Journal of Data Acquisition and Processing, 2025, 40(3): 562-584. doi: 10.16337/j.1004-9037.2025.03.002

基金资助

烟台市科技计划项目(2024JCYJ05)