Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Review Article
  • Published:

Current uses of artificial intelligence in the analysis of biofluid markers involved in corneal and ocular surface diseases: a systematic review

Eye volume 37, pages 2007–2019 (2023)Cite this article

Subjects

Abstract

Corneal and ocular surface diseases (OSDs) carry significant psychosocial and economic burden worldwide. We set out to review the literature on the application of artificial intelligence (AI) and bioinformatics for analysis of biofluid biomarkers in corneal and OSDs and evaluate their utility in clinical decision making. MEDLINE, EMBASE, Cochrane and Web of Science were systematically queried for articles using AI or bioinformatics methodology in corneal and OSDs and examining biofluids from inception to August 2021. In total, 10,264 articles were screened, and 23 articles consisting of 1058 individuals were included. Using various AI/bioinformatics tools, changes in certain tear film cytokines that are proinflammatory such as increased expression of apolipoprotein, haptoglobin, annexin 1, S100A8, S100A9, Glutathione S-transferase, and decreased expression of supportive tear film components such as lipocalin-1, prolactin inducible protein, lysozyme C, lactotransferrin, cystatin S, and mammaglobin-b, proline rich protein, were found to be correlated with pathogenesis and/or treatment outcomes of dry eye, keratoconus, meibomian gland dysfunction, and Sjögren’s. Overall, most AI/bioinformatics tools were used to classify biofluids into diseases subgroups, distinguish between OSD, identify risk factors, or make predictions about treatment response, and/or prognosis. To conclude, AI models such as artificial neural networks, hierarchical clustering, random forest, etc., in conjunction with proteomic or metabolomic profiling using bioinformatics tools such as Gene Ontology or Kyoto Encylopedia of Genes and Genomes pathway analysis, were found to inform biomarker discovery, distinguish between OSDs, help define subgroups with OSDs and make predictions about treatment response in a clinical setting.

摘要

角膜和眼表疾病 (OSDs) 在世界范围内带来了严重的心理和经济负担。我们对人工智能 (AI) 和生物信息学分析角膜和眼表疾病中生物流体标志物的相关文献进行了综述, 评估其在临床决策中的实用性。 本文对MEDLINE、EMBASE、Cochrane和Web of Science数据库进行系统筛选, 找到从建库到2021年8月期间将人工智能或生物信息学方法应用于角膜和眼表疾病并检查了生物体液的文章。共筛选10264篇文献, 纳入23篇, 共1058位受试者。 使用各种人工智能/生物信息学工具发现某些促炎性泪膜细胞因子的表达变化, 例如载脂蛋白、结合珠蛋白、膜联蛋白1、S100A8、S100A9和谷胱甘肽S-转移酶的表达增加, 支持性泪膜成分如脂质运载蛋白-1、催乳素诱导蛋白、溶菌酶C、乳转铁蛋白、胱抑素S的表达减少, 乳球蛋白-B和脯氨酸富集类蛋白等与干眼症、圆锥角膜、睑板腺功能障碍和干燥综合征的发病机制和/或治疗结果相关。总之, 大部分人工智能/生物信息学工具可根据生物液体将疾病亚群进行分类, 从而区分眼表疾病, 识别风险因素或对治疗反应和/或预后进行预测。 总的来说, 人工智能模型如人工神经网络, 分层聚类, 随机森林等, 在进行蛋白质组或代谢组分析中使用的生物信息学工具, 如基因本体论或京都基因和基因组路径分析百科全书, 可以为生物标志物的发现提供信息, 区分眼表疾病, 帮助定义眼表疾病亚群, 并在临床环境中预测治疗反应。

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: PRISMA flowchart diagram for study identification and selection.

Similar content being viewed by others

References

  1. von Thun und Hohenstein-Blaul N, Funke S, Grus FH. Tears as a source of biomarkers for ocular and systemic diseases. Exp Eye Res. 2013;117:126–37.

    Article  Google Scholar 

  2. Zhou L, Beuerman RW. Tear analysis in ocular surface diseases. Progr Retinal Eye Res. 2012;31:527–50.

    Article  CAS  Google Scholar 

  3. Wang MTM, Muntz A, Wolffsohn JS, Craig JP. Association between dry eye disease, self-perceived health status, and self-reported psychological stress burden. Clin Exp Optom. 2021;104:835–40.

    Article  PubMed  Google Scholar 

  4. Yu J, Asche CV, Fairchild CJ. The economic burden of dry eye disease in the United States: A decision tree analysis. Cornea. 2011;30:379–87.

    Article  PubMed  Google Scholar 

  5. Chan C, Ziai S, Myageri V, Burns JG, Prokopich CL. Economic burden and loss of quality of life from dry eye disease in Canada. BMJ Open Ophthalmol. 2021;6:e000709.

    Article  PubMed  PubMed Central  Google Scholar 

  6. Yang W, Luo Y, Wu S, Niu X, Yan Y, Qiao C, et al. Estimated annual economic burden of dry eye disease based on a multi-center analysis in china: a retrospective study. Front Med (Lausanne). 2021;8:771352.

    Article  PubMed  Google Scholar 

  7. de Almeida Borges D, Alborghetti MR, Franco Paes Leme A, Ramos Domingues R, Duarte B, Veiga M, et al. Tear proteomic profile in three distinct ocular surface diseases: keratoconus, pterygium, and dry eye related to graft-versus-host disease. Clin Proteomics [Internet]. 2020;17:1–16.

    Google Scholar 

  8. Ji YW, Kim HM, Ryu SY, Oh JW, Yeo A, Choi CY, et al. Changes in human tear proteome following topical treatment of dry eye disease: Cyclosporine a versus diquafosol tetrasodium. Invest Ophthalmol Vis Sci. 2019;60:5035–44.

    Article  CAS  PubMed  Google Scholar 

  9. Menegay M, Lee DM, Tabbara KF, Cafaro TA, Urrets-Zavalía JA, Serra HM, et al. Proteomic analysis of climatic keratopathy droplets. Invest Ophthalmol Vis Sci. 2008;49:2829–37.

    Article  PubMed  Google Scholar 

  10. Jiang Y, Yang C, Zheng Y, Liu Y, Chen Y. A set of global metabolomic biomarker candidates to predict the risk of dry eye disease. Front Cell Dev Biol. 2020;8:344.

    Article  PubMed  PubMed Central  Google Scholar 

  11. Wojakowska A, Pietrowska M, Widlak P, Dobrowolski D, Wylegała E, Tarnawska D. Metabolomic signature discriminates normal human cornea from Keratoconus—A pilot GC/MS study. Molecules. 2020;25:2933.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. González N, Iloro I, Soria J, Duran JA, Santamaría A, Elortza F, et al. Human tear peptide/protein profiling study of ocular surface diseases by SPE-MALDI-TOF mass spectrometry analyses. EuPA Open Proteom. 2014;3:206–15.

    Article  Google Scholar 

  13. Soria J, Villarrubia A, Merayo-Lloves J, Elortza F, Azkargorta M, de Toledo JA, et al. Label-free LC–MS/MS quantitative analysis of aqueous humor from keratoconic and normal eyes. Mol Vis. 2015;21:451–60.

    CAS  PubMed  PubMed Central  Google Scholar 

  14. Keskinbora K, Güven F. Artificial intelligence and ophthalmology. Turk J Ophthalmol. 2020;50:37–43.

    Article  PubMed  PubMed Central  Google Scholar 

  15. Schmidt-Erfurth U, Sadeghipour A, Gerendas BS, Waldstein SM, Bogunović H. Artificial intelligence in retina. Prog Retin Eye Res. 2018;67:1–29.

    Article  PubMed  Google Scholar 

  16. Yu LR, Stewart NA, Veenstra TD. Chapter 8 - Proteomics: The Deciphering of the Functional Genome. In: Ginsburg GS, Willard HFBTE of G and PM, editors. San Diego: Academic Press; 2010:89–96

  17. Larrañaga P, Calvo B, Santana R, Bielza C, Galdiano J, Inza I, et al. Machine learning in bioinformatics. Brief Bioinform. 2006;7:86–112.

    Article  PubMed  Google Scholar 

  18. Cryan LM, O’Brien C. Proteomics as a research tool in clinical and experimental ophthalmology. Proteomics Clin Appl. 2008;2:762–75.

    Article  CAS  PubMed  Google Scholar 

  19. Schmidt A, Forne I, Imhof A. Bioinformatic analysis of proteomics data. BMC Syst Biol. 2014;8(Suppl 2):S3–S3. 2014/03/13

    Article  PubMed  PubMed Central  Google Scholar 

  20. Tan SZ, Begley P, Mullard G, Hollywood KA, Bishop PN. Introduction to metabolomics and its applications in ophthalmology. Eye (Basingstoke). 2016;30:773–83.

    CAS  Google Scholar 

  21. Hopkins JJ, Keane PA, Balaskas K. Delivering personalized medicine in retinal care: From artificial intelligence algorithms to clinical application. Curr Opin Ophthalmol. 2020;31:329–36.

    Article  Google Scholar 

  22. Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;372:n71.

    Article  PubMed  PubMed Central  Google Scholar 

  23. Munn Z, Moola S, Riitano D, Lisy K. The development of a critical appraisal tool for use in systematic reviews addressing questions of prevalence. Int J Health Policy Manag. 2014;3:123–8.

    Article  PubMed  PubMed Central  Google Scholar 

  24. Valesan LF, Da-Cas CD, Réus JC, Denardin ACS, Garanhani RR, Bonotto D, et al. Prevalence of temporomandibular joint disorders: a systematic review and meta-analysis. Clin Oral Investig. 2021;25:441–53.

    Article  PubMed  Google Scholar 

  25. Liang JT, Huang J, Chen TC, Hung JS. The Toldt fascia: A historic review and surgical implications in complete mesocolic excision for colon cancer. Asian J Surg. 2019;42:1–5.

    Article  PubMed  Google Scholar 

  26. Srinivasan S, Thangavelu M, Zhang L, Green KB, Nichols KK. iTRAQ quantitative proteomics in the analysis of tears in dry eye patients. Invest Ophthalmol Vis Sci. 2012;53:5052–9.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  27. Huang Z, Du CX, Pan XD. The use of in-strip digestion for fast proteomic analysis on tear fluid from dry eye patients. PLoS One. 2018;13:e0200702.

    Article  PubMed  PubMed Central  Google Scholar 

  28. Yawata N, Awate S, Liu YC, Yuan S, Woon K, Siak J, et al. Kinetics of tear fluid proteins after endothelial keratoplasty and predictive factors for recovery from corneal haze. J Clin Med. 2020;9:1–14.

    Google Scholar 

  29. Linghu D, Guo L, Zhao Y, Liu Z, Zhao M, Huang L, et al. iTRAQ-based quantitative proteomic analysis and bioinformatics study of proteins in pterygia. 2018;1600094:7–8.

  30. Aqrawi LA, Galtung HK, Vestad B, Øvstebø R, Thiede B, Rusthen S, et al. Identification of potential saliva and tear biomarkers in primary Sjögren’s syndrome, utilising the extraction of extracellular vesicles and proteomics analysis. Arthritis Res Ther. 2017;19:1–15.

    Article  Google Scholar 

  31. Grus FH, Podust VN, Bruns K, Lackner K, Fu S, Dalmasso EA, et al. SELDI-TOF-MS ProteinChip array profiling of tears from patients with dry eye. Invest Ophthalmol Vis Sci. 2005;46:863–76.

    Article  PubMed  Google Scholar 

  32. Tong L, Zhou L, Beuerman R, Simonyi S, Hollander DA, Stern ME. Effects of punctal occlusion on global tear proteins in patients with dry eye. Ocular Surface. 2017;15:736–41.

    Article  PubMed  Google Scholar 

  33. Zou X, Wang S, Zhang P, Lu L, Zou H. Quantitative proteomics and weighted correlation network analysis of tear samples in adults and children with diabetes and dry eye. Transl Vis Sci Technol. 2020;9:1–15.

    Article  Google Scholar 

  34. Soria J, Durán JA, Etxebarria J, Merayo J, González N, Reigada R, et al. Tear proteome and protein network analyses reveal a novel pentamarker panel for tear film characterization in dry eye and meibomian gland dysfunction. J Proteomics. 2013;78:94–112.

    Article  CAS  PubMed  Google Scholar 

  35. Fodor M, Vitályos G, Losonczy G, Hassan Z, Pásztor D, Gogolák P, et al. Tear mediators NGF along with IL-13 predict keratoconus progression. Ocul Immunol Inflamm. 2021;29:1090–101.

    Article  CAS  PubMed  Google Scholar 

  36. Fodor M, Gogolák P, Rajnavölgyi É, Berta A, Kardos L, Módis L, et al. Long-term kinetics of cytokine responses in human tears after penetrating keratoplasty. J Interferon Cytokine Res. 2009;29:375–9.

    Article  CAS  PubMed  Google Scholar 

  37. Kim SW, Lee J, Lee B, Rhim T. Proteomic analysis in pterygium; upregulated protein expression of ALDH3A1, PDIA3, and PRDX2. Mol Vis. 2014;20:1192–202.

    CAS  PubMed  PubMed Central  Google Scholar 

  38. Sembler-Møller ML, Belstrøm D, Locht H, Pedersen AML. Proteomics of saliva, plasma, and salivary gland tissue in Sjögren’s syndrome and non-Sjögren patients identify novel biomarker candidates. J Proteomics. 2020;225:103877.

    Article  PubMed  Google Scholar 

  39. O’leary OE, Schoetzau A, Amruthalingam L, Geber-Hollbach N, Plattner K, Jenoe P, et al. Tear proteomic predictive biomarker model for ocular graft versus host disease classification. Transl Vis Sci Technol. 2020;9:1–15.

    Google Scholar 

  40. Piyacomn Y, Kasetsuwan N, Reinprayoon U, Satitpitakul V, Tesapirat L. Efficacy and safety of intense pulsed light in patients with meibomian gland dysfunction-a randomized, double-masked, sham-controlled clinical trial. Cornea. 2020;39:325–32.

    Article  PubMed  Google Scholar 

  41. Leonardi A, Palmigiano A, Mazzola EA, Messina A, Milazzo EMS, Bortolotti M, et al. Identification of human tear fluid biomarkers in vernal keratoconjunctivitis using iTRAQ quantitative proteomics. Allergy: Eur J Allergy Clin Immunol. 2014;69:254–60.

    Article  CAS  Google Scholar 

  42. Sembler-Møller ML, Belstrøm D, Locht H, Pedersen AML. Proteomics of saliva, plasma, and salivary gland tissue in Sjögren’s syndrome and non-Sjögren patients identify novel biomarker candidates. J Proteomics. 2020;225:103877.

    Article  PubMed  Google Scholar 

  43. Inamoto Y, Valdés-Sanz N, Ogawa Y, Alves M, Berchicci L, Galvin J, et al. Ocular graft-versus-host disease after hematopoietic cell transplantation: Expert review from the Late Effects and Quality of Life Working Committee of the CIBMTR and Transplant Complications Working Party of the EBMT. Bone Marrow Transpl. 2019;54:662–73.

    Article  Google Scholar 

  44. Yam GHF, Fuest M, Zhou L, Liu YC, Deng L, Chan ASY, et al. Differential epithelial and stromal protein profiles in cone and non-cone regions of keratoconus corneas. Sci Rep. 2019;9:1–17.

    Article  CAS  Google Scholar 

  45. Sharif R, Bak-Nielsen S, Sejersen H, Ding K, Hjortdal J, Karamichos D. Prolactin-induced protein is a novel biomarker for keratoconus. Exp Eye Res. 2019;179:55–63.

    Article  CAS  PubMed  Google Scholar 

  46. Soria J, Acera A, Merayo-Lloves J, Durán JA, González N, Rodriguez S, et al. Tear proteome analysis in ocular surface diseases using label-free LC-MS/MS and multiplexed-microarray biomarker validation. Sci Rep. 2017;7:17478.

    Article  PubMed  PubMed Central  Google Scholar 

  47. Karimpour-Fard A, Elaine Epperson L, Hunter LE. A survey of computational tools for downstream analysis of proteomic and other omic datasets. Hum Genomics. 2015;9:28.

    Article  PubMed  PubMed Central  Google Scholar 

  48. Lancashire LJ, Lemetre C, Ball GR. An introduction to artificial neural networks in bioinformatics—Application to complex microarray and mass spectrometry datasets in cancer studies. Briefings in Bioinformatics. 2009;10:315–29.

    Article  CAS  PubMed  Google Scholar 

  49. González N, Iloro I, Durán JA, Elortza F, Suárez T. Evaluation of inter-day and inter-individual variability of tear peptide/protein profiles by MALDI-TOF MS analyses. Mol Vis. 2012;18:1572–82.

    PubMed  PubMed Central  Google Scholar 

  50. Vizcaíno JA, Foster JM, Martens L. Proteomics data repositories: Providing a safe haven for your data and acting as a springboard for further research. J Proteomics. 2010;73:2136.

    Article  PubMed  PubMed Central  Google Scholar 

  51. Khatri P, Drǎghici S. Ontological analysis of gene expression data: Current tools, limitations, and open problems. Bioinformatics. 2005;21:3587–95.

    Article  CAS  PubMed  Google Scholar 

  52. Green-Church KB, Nichols KK, Kleinholz NM, Zhang L, Nichols JJ. Investigation of the human tear film proteome using multiple proteomic approaches. Mol Vis. 2008;14:456–70.

    CAS  PubMed  PubMed Central  Google Scholar 

  53. Grus FH, Sabuncuo P, Augustin AJ. Analysis of tear protein patterns of dry-eye patients using fluorescent staining dyes and two-dimensional quantification algorithms. Electrophoresis. 2001;22:1845–50.

    Article  CAS  PubMed  Google Scholar 

  54. Edorh NA, el Maftouhi A, Djerada Z, Arndt C, Denoyer A. New model to better diagnose dry eye disease integrating OCT corneal epithelial mapping. Br J Ophthalmol. 2021;106:1488–95.

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

This study was in-part funded by a Fighting Blindness Canada research grant awarded to Dr. Tina Felfeli. The authors would like to acknowledge Arshpreet Bassi, Shaily Brahmbhatt, Priyanka Singh, Ishita Aggarwal, Amy Basilious, Jasmine Bhatti, and Karthik Manickavachagam, who participated in article screening.

Author information

Authors and Affiliations

  1. Schulich School of Medicine and Dentistry, Western University, London, ON, Canada

    Daiana Roxana Pur & Saffire H. Krance

  2. School of Medicine, Queen’s University, Kingston, ON, Canada

    Aidan Pucchio

  3. Toronto Health Economics and Technology Assessment Collaborative, Toronto, ON, Canada

    Rafael N. Miranda & Tina Felfeli

  4. The Institute of Health Policy, Management and Evaluation (IHPME), Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada

    Rafael N. Miranda & Tina Felfeli

  5. Department of Ophthalmology and Visual Sciences, University of Toronto, Toronto, ON, Canada

    Tina Felfeli

Authors
  1. Daiana Roxana Pur
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Saffire H. Krance
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Aidan Pucchio
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Rafael N. Miranda
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Tina Felfeli
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

TF, RNM: conceptualization, supervision, methodology, writing, review and editing of manuscript. DRP: conceptualization, data collection, analysis and interpretation of results, draft manuscript preparation. SHK, methodology, data collection. AP, data collection, analysis and interpretation of the results. All authors reviewed the results, and approved the final version of the manuscript.

Corresponding author

Correspondence to Tina Felfeli.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix A

Search strategy used to survey databases.

Appendix B

Assessment of risk of bias and quality of included studies based on criteria from Joanna Briggs Institute Critical Appraisal Tools.

Supplementary information

Search strategy used to survey databases.

41433_2022_2307_MOESM2_ESM.docx

Assessment of risk of bias and quality of included studies based on criteria from Joanna Briggs Institute Critical Appraisal Tools

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Pur, D.R., Krance, S.H., Pucchio, A. et al. Current uses of artificial intelligence in the analysis of biofluid markers involved in corneal and ocular surface diseases: a systematic review. Eye 37, 2007–2019 (2023). https://doi.org/10.1038/s41433-022-02307-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41433-022-02307-9

This article is cited by

Search

Advanced search

Quick links