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.

  • Article
  • Published:

Large-scale screening of blinding eye diseases from routine blood tests

Nature Health (2026)Cite this article

Subjects

Abstract

Blinding eye diseases pose a substantial global health burden, yet current screening strategies are limited by resource demands and poor accessibility, particularly in underserved settings. Leveraging the broad availability of routine blood testing, we developed a scalable and non-invasive machine learning-based multidisease eye screening (MES) framework to identify individuals at higher risk of major blinding eye diseases and prioritize referral for confirmatory ophthalmic evaluation. Using data from 93,839 participants and internally validated in 33,622 individuals, the MES test integrates a binary classifier to detect eye disease and a multiclass classifier to differentiate seven common blinding conditions. Performance was further evaluated in three independent external cohorts (n = 34,087), a prospective hospital-based cohort (n = 43,556) and a large population-based cohort (n = 498,095). Across validation datasets, the MES test achieved high diagnostic performance for detecting any eye disease, with an area under the curve of 0.9264–0.9561, positive predictive values of 0.9127–0.9260 and negative predictive values of 0.8075–0.8917. Subtype-level classification demonstrated a macroaveraged area under the curve of 0.889–0.900. In real-world clinical and community settings, the MES test yielded positive and negative predictive values of 0.959 and 0.960, and 0.931 and 0.991, respectively. Performance remained robust across age and comorbidity subgroups. These results support the potential of the MES framework as a scalable triage aid to identify individuals at higher risk and prioritize confirmatory ophthalmic assessment for major blinding eye diseases.

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

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

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

Fig. 1: Flowchart of study participant inclusion.
Fig. 2: Model development using all included indicators to distinguish patients with eye diseases from controls.
Fig. 3: Model development and validation after feature reduction using SHAP to distinguish patients with eye disease from controls.
Fig. 4: Model development and validation to distinguish seven types of eye disease.
Fig. 5: Performance of the MES test in the prospective hospital-based validation and community-based cross-sectional cohorts.

Data availability

Access to comprehensive, individual-level clinical data is restricted to protect sensitive human information and to comply with the terms of the informed consent. Requests for access to the de-identified data can be made to the corresponding author by providing a study protocol and ethical approval documentation. Requests for raw data will be reviewed by the corresponding author (S.L.), who will facilitate further communications with the cohort leaders and relevant ancillary study committees as appropriate. The corresponding author typically responds to such requests within 2–3 weeks. A Data Use Agreement will be established between the requesting party and the data holder, specifying that the data may only be used for the prespecified project described in the request and that any resulting paper must reference the data source. Once access has been granted, the data will remain available for 6 months. The data generated in this study are provided in the Supplementary Information and Source Data file. Source data are provided.

Code availability

The analysis code was written in Python (v.3.11) and relies on standard open-source libraries (NumPy, Pandas, scikit-learn), used in compliance with their Massachusetts Institute of Technology and Berkeley Software Distribution licences. All reused components retain their original licence and attribution. The analysis code is available on GitHub (https://github.com/fudanRenjun/EyeGuard7/tree/master) and has been archived with Zenodo at https://doi.org/10.5281/zenodo.18637593 (ref. 64).

References

  1. World Report on Vision (World Health Organization, 2019).

  2. Vision and Eye Screening Implementation Handbook (World Health Organization, 2024).

  3. Xu, T. et al. Prevalence and causes of vision loss in China from 1990 to 2019: findings from the Global Burden of Disease Study 2019. Lancet Public Health 5, e682–e691 (2020).

    Article  PubMed  Google Scholar 

  4. Dhablania, N. et al. Uncorrected refractive error in the African American Eye Disease Study. JAMA Ophthalmol. 142, 292–298 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  5. Fleckenstein, M., Schmitz-Valckenberg, S. & Chakravarthy, U. Age-related macular degeneration: a review. JAMA 331, 147–157 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Stein, J. D., Khawaja, A. P. & Weizer, J. S. Glaucoma in adults-screening, diagnosis, and management: a review. JAMA 325, 164–174 (2021).

    Article  PubMed  Google Scholar 

  7. Lin, J. B., Narayanan, R., Philippakis, E., Yonekawa, Y. & Apte, R. S. Retinal detachment. Nat. Rev. Dis. Primers 10, 18 (2024).

    Article  PubMed  Google Scholar 

  8. Chen, C., Singh, G., Madike, R. & Cugati, S. Central retinal artery occlusion: a stroke of the eye. Eye 38, 2319–2326 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  9. Mohamed, Q., Gillies, M. C. & Wong, T. Y. Management of diabetic retinopathy: a systematic review. JAMA 298, 902–916 (2007).

    Article  CAS  PubMed  Google Scholar 

  10. Burton, M. J. et al. The Lancet Global Health Commission on Global Eye Health: vision beyond 2020. Lancet Glob. Health 9, e489–e551 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Wen, X. et al. Clinlabomics: leveraging clinical laboratory data by data mining strategies. BMC Bioinformatics 23, 387 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  12. Podolsky, E. et al. Choosing which in-hospital laboratory tests to target for intervention: a scoping review. Clin. Chem. Lab. Med. 61, 388–401 (2023).

    Article  CAS  PubMed  Google Scholar 

  13. Cai, G. et al. Artificial intelligence-based models enabling accurate diagnosis of ovarian cancer using laboratory tests in China: a multicentre, retrospective cohort study. Lancet Digit. Health 6, e176–e186 (2024).

    Article  CAS  PubMed  Google Scholar 

  14. Connelly, K. et al. Associations of improvement in laboratory tests with clinical outcomes in patients with active systemic lupus erythematosus: a multinational longitudinal cohort study. Lancet Rheumatol. 4, e831–e841 (2022).

    Article  CAS  PubMed  Google Scholar 

  15. Hu, M. et al. Development and preliminary validation of a machine learning system for thyroid dysfunction diagnosis based on routine laboratory tests. Commun. Med. 2, 9 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  16. Zacharias, H. U. et al. A predictive model for progression of CKD to kidney failure based on routine laboratory tests. Am. J. Kidney Dis. 79, 217–230 (2022).

    Article  CAS  PubMed  Google Scholar 

  17. van der Geest, K. S. M., Sandovici, M., Brouwer, E. & Mackie, S. L. Diagnostic accuracy of symptoms, physical signs, and laboratory tests for giant cell arteritis: a systematic review and meta-analysis. JAMA Intern. Med. 180, 1295–1304 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  18. Li, S. et al. Development and validation of a routine blood parameters-based model for screening the occurrence of retinal detachment in high myopia in the context of PPPM. EPMA J. 14, 219–233 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. Li, S. et al. Association of systemic inflammation indices with visual field loss progression in patients with primary angle-closure glaucoma: potential biomarkers for 3P medical approaches. EPMA J. 12, 659–675 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  20. Shao, M. et al. Association between serum total bilirubin level and patients with primary open-angle glaucoma in China: a cross-sectional, case-control study. Oxid. Med. Cell Longev. 2023, 8206298 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

  21. Li, S. et al. Serum complement component 3, complement component 4 and complement component 1q levels predict progressive visual field loss in older women with primary angle closure glaucoma. Br. J. Ophthalmol. 107, 828–835 (2023).

    Article  PubMed  Google Scholar 

  22. Ma, Y. et al. Association between red blood cell distribution width and diabetic retinopathy: a 5-year retrospective case-control study. J. Ophthalmol. 2021, 6653969 (2021).

    PubMed  PubMed Central  Google Scholar 

  23. Li, S. et al. Association between serum lipids concentration and patients with age-related cataract in China: a cross-sectional, case-control study. BMJ Open 8, e021496 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

  24. Li, S. et al. Association between coagulation function and patients with primary angle closure glaucoma: a 5-year retrospective case-control study. BMJ Open 7, e016719 (2017).

    Article  PubMed  PubMed Central  Google Scholar 

  25. Liisborg, C., Nielsen, M. K., Hasselbalch, H. C. & Sørensen, T. L. Patients with myeloproliferative neoplasms and high levels of systemic inflammation develop age-related macular degeneration. eClinicalMedicine 26, 100526 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

  26. Vergroesen, J. E. et al. The inflammatory potential of diet is associated with the risk of age-related eye diseases. Clin. Nutr. 42, 2404–2413 (2023).

    Article  PubMed  Google Scholar 

  27. Zhang, A. et al. Neutrophil-to-lymphocyte ratio as a potential biomarker of neovascular glaucoma. Ocul. Immunol. Inflamm. 29, 417–424 (2021).

    Article  PubMed  Google Scholar 

  28. He, M. et al. Correlation between neutrophil-to-lymphocyte ratio and clinical manifestations and complications of retinitis pigmentosa. Acta Ophthalmol. 100, e278–e287 (2022).

    Article  CAS  PubMed  Google Scholar 

  29. Kiang, L. et al. Vitreous cytokine expression and a murine model suggest a key role of microglia in the inflammatory response to retinal detachment. Invest. Ophthalmol. Vis. Sci. 59, 3767–3778 (2018).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Long, Q., Ye, J., Li, Y., Wang, S. & Jiang, Y. C-reactive protein and complement components in patients with pathological myopia. Optom. Vis. Sci. 90, 501–506 (2013).

    Article  PubMed  Google Scholar 

  31. Baudouin, C., Kolko, M., Melik-Parsadaniantz, S. & Messmer, E. M. Inflammation in glaucoma: from the back to the front of the eye, and beyond. Prog. Retin. Eye Res. 83, 100916 (2021).

    Article  PubMed  Google Scholar 

  32. Datta, S., Cano, M., Ebrahimi, K., Wang, L. & Handa, J. T. The impact of oxidative stress and inflammation on RPE degeneration in non-neovascular AMD. Prog. Retin. Eye Res. 60, 201–218 (2017).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  33. Asbell, P. A. et al. Age-related cataract. Lancet 365, 599–609 (2005).

    Article  PubMed  Google Scholar 

  34. Babenko, B. et al. A deep learning model for novel systemic biomarkers in photographs of the external eye: a retrospective study. Lancet Digit. Health 5, e257–e264 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  35. Gao, Y. et al. Machine learning based early warning system enables accurate mortality risk prediction for COVID-19. Nat. Commun. 11, 5033 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  36. Tan, T. F. et al. Artificial intelligence and digital health in global eye health: opportunities and challenges. Lancet Glob. Health 11, e1432–e1443 (2023).

    Article  CAS  PubMed  Google Scholar 

  37. Chen, X. et al. FFA-GPT: an automated pipeline for fundus fluorescein angiography interpretation and question-answer. NPJ Digit. Med. 7, 111 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  38. Zhou, Y. et al. A foundation model for generalizable disease detection from retinal images. Nature 622, 156–163 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  39. Tabuchi, H. et al. Using artificial intelligence to improve human performance: efficient retinal disease detection training with synthetic images. Br. J. Ophthalmol. 108, 1430–1435 (2024).

    Article  PubMed  PubMed Central  Google Scholar 

  40. Li, S. et al. Association between 17-β-estradiol and interleukin-8 and visual field progression in postmenopausal women with primary angle closure glaucoma. Am. J. Ophthalmol. 217, 55–67 (2020).

    Article  CAS  PubMed  Google Scholar 

  41. Li, S. et al. Developing and validating a clinlabomics-based machine-learning model for early detection of retinal detachment in patients with high myopia. J. Transl. Med. 22, 405 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  42. Bossi, E. et al. Revolutionizing blood collection: innovations, applications, and the potential of microsampling technologies for monitoring metabolites and lipids. Metabolites 14, 46 (2024).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  43. Chuang, S.-H. & Chang, C.-H. Platelet-to-lymphocyte ratio and lymphocyte-to-monocyte ratio in glaucoma: a meta-analysis. Biomark. Med. 18, 39–49 (2024).

    Article  CAS  PubMed  Google Scholar 

  44. Han, D. & He, X. Screening for biomarkers in age-related macular degeneration. Heliyon 9, e16981 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  45. Arndt, C. et al. Increased intravitreal glucose in rhegmatogenous retinal detachment. Eye 37, 638–643 (2023).

    Article  CAS  PubMed  Google Scholar 

  46. AlDarrab, A., Al Jarallah, O. J. & Al Balawi, H. B. Association of diabetes, fasting glucose, and the risk of glaucoma: a systematic review and meta-analysis. Eur. Rev. Med. Pharmacol. Sci. 27, 2419–2427 (2023).

    CAS  PubMed  Google Scholar 

  47. Luo, S. et al. Quantitative proteomics analysis of human vitreous in rhegmatogenous retinal detachment associated with choroidal detachment by data-independent acquisition mass spectrometry. Mol. Cell. Biochem. 477, 1849–1863 (2022).

    Article  CAS  PubMed  Google Scholar 

  48. Kim, J. et al. Retinal vein occlusion is associated with low blood high-density lipoprotein cholesterol: a nationwide cohort study. Am. J. Ophthalmol. 205, 35–42 (2019).

    Article  CAS  PubMed  Google Scholar 

  49. Lee, B., Afshari, N. A. & Shaw, P. X. Oxidative stress and antioxidants in cataract development. Curr. Opin. Ophthalmol. 35, 57–63 (2024).

    Article  PubMed  Google Scholar 

  50. Mantopoulos, D. et al. Tauroursodeoxycholic acid (TUDCA) protects photoreceptors from cell death after experimental retinal detachment. PLoS ONE 6, e24245 (2011).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  51. Oveson, B. C. et al. Constituents of bile, bilirubin and TUDCA, protect against oxidative stress-induced retinal degeneration. J. Neurochem. 116, 144–153 (2011).

    Article  CAS  PubMed  Google Scholar 

  52. Drack, A. V. et al. TUDCA slows retinal degeneration in two different mouse models of retinitis pigmentosa and prevents obesity in Bardet–Biedl syndrome type 1 mice. Invest. Ophthalmol. Vis. Sci. 53, 100–106 (2012).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  53. Phillips, M. J. et al. Tauroursodeoxycholic acid preservation of photoreceptor structure and function in the rd10 mouse through postnatal day 30. Invest. Ophthalmol. Vis. Sci. 49, 2148–2155 (2008).

    Article  PubMed  PubMed Central  Google Scholar 

  54. Zhao, H. et al. Blood levels of glycated hemoglobin, D-dimer, and fibrinogen in diabetic retinopathy. Diabetes Metab. Syndr. Obes. 14, 2483–2488 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  55. Liu, Z., Perry, L. A. & Edwards, T. L. Association between platelet indices and retinal vein occlusion: a systematic review and meta-analysis. Retina 41, 238–248 (2021).

    Article  PubMed  Google Scholar 

  56. Wang, Y. et al. The association between the lipids levels in blood and risk of age-related macular degeneration. Nutrients 8, 663 (2016).

    Article  PubMed  PubMed Central  Google Scholar 

  57. Nezu, N. et al. Machine learning approach for intraocular disease prediction based on aqueous humor immune mediator profiles. Ophthalmology 128, 1197–1208 (2021).

    Article  PubMed  Google Scholar 

  58. Sugawara, R. et al. An approach to predict intraocular diseases by machine learning based on vitreous humor immune mediator profile. Invest. Ophthalmol. Vis. Sci. 66, 38 (2025).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  59. Heus, P. et al. Transparent reporting of multivariable prediction models in journal and conference abstracts: TRIPOD for abstracts. Ann. Intern. Med. (in the press).

  60. Ma, Y. et al. Association of serum complement C1q and C3 level with age-related macular degeneration in women. J. Inflamm. Res. 15, 285–294 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  61. Shao, M. et al. Association between serum complement C3 levels and age-related cataract. Invest. Ophthalmol. Vis. Sci. 58, 4934–4939 (2017).

    Article  CAS  PubMed  Google Scholar 

  62. Liu, Z. et al. Association between increased lipid profiles and risk of diabetic retinopathy in a population-based case-control study. J. Inflamm. Res. 15, 3433–3446 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  63. Berkelmans, G. F. N. et al. Population median imputation was noninferior to complex approaches for imputing missing values in cardiovascular prediction models in clinical practice. J. Clin. Epidemiol. 145, 70–80 (2022).

    Article  PubMed  Google Scholar 

  64. fudanRenjun. fudanRenjun/EyeGuard7: EyeGuard7. Zenodo https://doi.org/10.5281/zenodo.18637593 (2026).

Download references

Acknowledgements

This work was supported by the National Key Research and Development Program of China (no. 2024YFC2510805 to X.Z.), the Shanghai Municipal Health Commission (no. 2023ZZ02019 to X.Z.), the National Natural Science Foundation of China (no. 82302582 to S.L., no. 82371091 to M.L., no. 82572671 to S.G.) and Oriental Talent Plan (no. SSF828079 to M.L.). The sponsor or funding organization had no role in the design or conduct of this research.

Author information

Author notes

  1. These authors contributed equally: Shengjie Li, Jun Ren.

Authors and Affiliations

  1. Department of Clinical Laboratory, Eye & ENT Hospital, Fudan University, Shanghai, China

    Shengjie Li, Jun Ren, Jianing Wu, Yingzhu Li & Wenjun Cao

  2. Eye Institute and Department of Ophthalmology, Eye & ENT Hospital, Fudan University, Shanghai, China

    Shengjie Li, Wenjun Cao, Meiyan Li & Xingtao Zhou

  3. NHC Key laboratory of Myopia and Related Eye Diseases; Key Laboratory of Myopia and Related Eye Diseases, Chinese Academy of Medical Sciences, Shanghai, China

    Shengjie Li, Wenjun Cao, Meiyan Li & Xingtao Zhou

  4. Shanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, China

    Shengjie Li, Wenjun Cao, Meiyan Li & Xingtao Zhou

  5. Department of Clinical Laboratory, the First Affiliated Hospital of Anhui Medical University, Anhui, China

    Xuanxuan Wang

  6. Department of Clinical Laboratory, Anhui Wanbei Electricity Group General Hospital, Suzhou, China

    Mengyu Zhang & Henggui Hu

  7. Department of Clinical Laboratory, Shanghai Xuhui Central Hospital, Fudan University, Shanghai, China

    Yunxiao Song

  8. Department of Ophthalmology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China

    Shunxiang Gao

  9. National Clinical Research Center for Eye Diseases, Shanghai Key Laboratory of Ocular Fundus Diseases, Shanghai Engineering Center for Visual Science and Photomedicine, Shanghai, China

    Shunxiang Gao

Authors
  1. Shengjie Li
    View author publications

    Search author on:PubMed Google Scholar

  2. Jun Ren
    View author publications

    Search author on:PubMed Google Scholar

  3. Jianing Wu
    View author publications

    Search author on:PubMed Google Scholar

  4. Yingzhu Li
    View author publications

    Search author on:PubMed Google Scholar

  5. Xuanxuan Wang
    View author publications

    Search author on:PubMed Google Scholar

  6. Mengyu Zhang
    View author publications

    Search author on:PubMed Google Scholar

  7. Henggui Hu
    View author publications

    Search author on:PubMed Google Scholar

  8. Yunxiao Song
    View author publications

    Search author on:PubMed Google Scholar

  9. Shunxiang Gao
    View author publications

    Search author on:PubMed Google Scholar

  10. Wenjun Cao
    View author publications

    Search author on:PubMed Google Scholar

  11. Meiyan Li
    View author publications

    Search author on:PubMed Google Scholar

  12. Xingtao Zhou
    View author publications

    Search author on:PubMed Google Scholar

Contributions

W.C., X.Z., M.L. and S.L. conceptualized and designed the study. S.L., Y.L., J.W., S.G., X.W., M.Z., H.H., Y.S. and J.R. performed most of the experiments. W.C., S.G., X.Z. and M.L. performed parts of the experiments. S.L., J.W., Y.S. and J.R. acquired and analysed the data. S.L., J.R., M.L., Y.L. and J.W. prepared the figures and performed the statistical analysis. S.L. wrote the original paper draft. W.C., X.Z., M.L., S.G. and S.L. reviewed and edited the paper. All authors read and approved the final paper.

Corresponding authors

Correspondence to Shengjie Li, Shunxiang Gao, Wenjun Cao, Meiyan Li or Xingtao Zhou.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Health thanks Yoshihiko Usui and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Primary Handling Editor: Lorenzo Righetto, in collaboration with the Nature Health team.

Additional information

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

Supplementary information

Supplementary Information (download PDF )

Supplementary Figs. 1–9, Tables 1–42 and Methods.

Reporting Summary (download PDF )

Supplementary Table (download XLSX )

Supplementary Tables 1–42.

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

Li, S., Ren, J., Wu, J. et al. Large-scale screening of blinding eye diseases from routine blood tests. Nat. Health (2026). https://doi.org/10.1038/s44360-026-00101-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • DOI: https://doi.org/10.1038/s44360-026-00101-5

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing