Abstract
High myopia can lead to cataract, glaucoma, retinal detachment, choroidal neovascularisation, and macular degeneration, causing irreversible vision loss. Imaging detects these complications, but population screening is limited by equipment, and specialist availability. Here we show that a machine learning model using routine blood test results identifies people at increased risk of complications related to high myopia during standard health examinations. We develop the model in a multicentre study of 10,661 participants and validate it in two independent cohorts. The model shows high accuracy across centres (area under the receiver operating characteristic curve=0.9010-0.9649) and flags individuals who receive a clinical diagnosis in a hospital-based prospective follow-up study of 5,067 participants. In a community screening study of 311,254 adults, the model increases the yield of detected complications among those referred for ophthalmic assessment (positive predictive value = 74%). This scalable blood-based approach supports opportunistic screening and earlier referral in primary care and community settings.
Similar content being viewed by others
Data availability
The de-identified data of the discovery cohort and validation cohort in this study have been deposited in the Source data file. The corresponding acronyms for these cohorts are listed in Tables S1 and S2, respectively. Access to comprehensive, individual-level clinical data is restricted to protect participant privacy and comply with the conditions of informed consent. The individual-level clinical data may be made available upon request to the corresponding author, accompanied by a study protocol and evidence of ethical approval. All requests will be reviewed by the corresponding author (Meiyan Li) in consultation with the cohort leadership and relevant study committees, and a response is typically provided within 12 weeks. Approved users will be required to sign a Data Use Agreement specifying that the data are to be used solely for the approved project and that any resulting publications must acknowledge the data source. The data will be made available only for scientific research purposes. Once access has been granted, the data will remain available for six months. The data generated in this study are provided in the Supplementary Information/Source Data file. Source data are provided with this paper.
Code availability
The analysis code was written in Python (version 3.11) and relies on standard open-source libraries (NumPy, Pandas, scikit-learn, XGBoost), used in compliance with their MIT and BSD licences. All reused components retain their original license and attribution. The analysis codes are available on GitHub at (https://github.com/fudanRenjun/high-myopia/tree/master) archived with Zenodo66 under https://doi.org/10.5281/zenodo.18382509.
References
Flitcroft, D. I. et al. IMI - defining and classifying myopia: a proposed set of standards for clinical and epidemiologic studies. Invest. Ophthalmol. Vis. Sci. 60, M20–M30 (2019).
Morgan, I. G., Ohno-Matsui, K. & Saw, S.-M. Myopia. Lancet 379, 1739–1748 (2012).
Zhang, X. et al. Optic neuropathy in high myopia: glaucoma or high myopia or both?. Prog. Retin. Eye Res. 99, 101246 (2024).
Flitcroft, D. I. The complex interactions of retinal, optical and environmental factors in myopia aetiology. Prog. Retin. Eye Res. 31, 622–660 (2012).
Kanthan, G. L., Mitchell, P., Rochtchina, E., Cumming, R. G. & Wang, J. J. Myopia and the long-term incidence of cataract and cataract surgery: the Blue Mountains Eye Study. Clin. Exp. Ophthalmol. 42, 347–353 (2014).
Haarman, A. E. G. et al. The complications of myopia: a review and meta-analysis. Invest. Ophthalmol. Vis. Sci. 61, 49 (2020).
Wang, Y. X. et al. High myopia as risk factor for the 10-year incidence of open-angle glaucoma in the Beijing Eye Study. Br. J. Ophthalmol. 107, 935–940 (2023).
Du, Y. et al. Complications of high myopia: an update from clinical manifestations to underlying mechanisms. Adv. Ophthalmol. Pract. Res. 4, 156–163 (2024).
Foo, L. L. et al. Predictors of myopic macular degeneration in a 12-year longitudinal study of Singapore adults with myopia. Br. J. Ophthalmol. 107, 1363–1368 (2023).
Zheng, F. et al. Quantitative OCT angiography of the retinal microvasculature and choriocapillaris in highly myopic eyes with myopic macular degeneration. Br. J. Ophthalmol. 106, 681–688 (2022).
Liu, H. et al. Economic evaluation of combined population-based screening for multiple blindness-causing eye diseases in China: a cost-effectiveness analysis. Lancet Glob. Health 11, e456–e465 (2023).
Fricke, T. R. et al. Global prevalence of visual impairment associated with myopic macular degeneration and temporal trends from 2000 through 2050: systematic review, meta-analysis and modelling. Br. J. Ophthalmol. 102, 855–862 (2018).
World Health Organization. World report on vision. Geneva: World Health Organization; 2019. Available from: https://www.who.int/publications/i/item/9789241516570
Cheung, N. et al. Prevalence and associations of retinal emboli with ethnicity, stroke, and renal disease in a multiethnic Asian population: the Singapore Epidemiology of Eye Disease Study. JAMA Ophthalmol. 135, 1023–1028 (2017).
Igarashi-Yokoi, T. et al. Prognostic factors for axial length elongation and posterior staphyloma in adults with high myopia: a Japanese Observational Study. Am. J. Ophthalmol. 225, 76–85 (2021).
Chen, Y. et al. Acceptability, applicability, and cost-utility of artificial-intelligence-powered low-cost portable fundus camera for diabetic retinopathy screening in primary health care settings. Diab. Res. Clin. Pract. 223, 112161 (2025).
Ahn, S. J. & Kim, Y. H. Clinical applications and future directions of smartphone fundus imaging. Diagnostics 14, 1395 (2024).
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).
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).
Perais, J. et al. Prognostic factors for the development and progression of proliferative diabetic retinopathy in people with diabetic retinopathy. Cochrane Database Syst. Rev. 2, CD013775 (2023).
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).
Horton, S. et al. The Top 25 laboratory tests by volume and revenue in five different countries. Am. J. Clin. Pathol. 151, 446–451 (2019).
Foy, B. H. et al. Haematological setpoints are a stable and patient-specific deep phenotype. Nature 637, 430–438 (2025).
Lundberg, S. M. et al. From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2, 56–67 (2020).
Bossi, E. et al. Revolutionizing blood collection: innovations, applications, and the potential of microsampling technologies for monitoring metabolites and lipids. Metabolites 14, 46 (2024).
Gause, W. C., Wynn, T. A. & Allen, J. E. Type 2 immunity and wound healing: evolutionary refinement of adaptive immunity by helminths. Nat. Rev. Immunol. 13, 607–614 (2013).
Rosenberg, H. F., Dyer, K. D. & Foster, P. S. Eosinophils: changing perspectives in health and disease. Nat. Rev. Immunol. 13, 9–22 (2013).
Nishiguchi, K. M. et al. C9-R95X polymorphism in patients with neovascular age-related macular degeneration. Invest. Ophthalmol. Vis. Sci. 53, 508–512 (2012).
Leung, D. Y. M. et al. Dupilumab inhibits vascular leakage of blood proteins into atopic dermatitis skin. J. Allergy Clin. Immunol. Pract. 11, 1421–1428 (2023).
Gao, L., Jiang, W., Liu, H., Chen, Z. & Lin, Y. Receptor-selective interleukin-4 mutein attenuates laser-induced choroidal neovascularization through the regulation of macrophage polarization in mice. Exp. Ther. Med. 22, 1367 (2021).
Ames, B. N., Cathcart, R., Schwiers, E. & Hochstein, P. Uric acid provides an antioxidant defense in humans against oxidant- and radical-caused aging and cancer: a hypothesis. Proc. Natl. Acad. Sci. USA 78, 6858–6862 (1981).
van Leeuwen, E. M. et al. A new perspective on lipid research in age-related macular degeneration. Prog. Retin Eye Res. 67, 56–86 (2018).
Li, B., Goss, D., Miller, J. W., Lin, J. B. & Vavvas, D. G. Systemic dyslipidemia in age-related macular degeneration: an updated systematic review and meta-analysis. Ophthalmol. Sci. 4, 100341 (2024).
Ma, Y., Li, S., Shao, M., Cao, W. & Sun, X. Platelet parameters and their relationships with the thickness of the retinal nerve fiber layer and ganglion cell complex in primary open-angle glaucoma. Front. Neurol. 13, 867465 (2022).
Qiu, J. et al. Development and validation of a multimodal multitask vision foundation model for generalist ophthalmic artificial intelligence. NEJM AI https://doi.org/10.1056/AIoa2300221 (2024).
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).
Wang, J. et al. Artificial intelligence-enhanced retinal imaging as a biomarker for systemic diseases. Theranostics 15, 3223–3233 (2025).
Xiao, W. et al. Screening and identifying hepatobiliary diseases through deep learning using ocular images: a prospective, multicentre study. Lancet Digit. Health 3, e88–e97 (2021).
Mitani, A. et al. Detection of anaemia from retinal fundus images via deep learning. Nat. Biomed. Eng. 4, 18–27 (2020).
Joo, Y. S. et al. Non-invasive chronic kidney disease risk stratification tool derived from retina-based deep learning and clinical factors. NPJ Digit. Med. 6, 114 (2023).
Cheung, C. Y. et al. A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre. Nat. Biomed. Eng. 5, 498–508 (2021).
Zhang, L. et al. Prediction of hypertension, hyperglycemia and dyslipidemia from retinal fundus photographs via deep learning: a cross-sectional study of chronic diseases in central China. PLoS ONE 15, e0233166 (2020).
Rajalakshmi, R., Prathiba, V., Arulmalar, S. & Usha, M. Review of retinal cameras for global coverage of diabetic retinopathy screening. Eye 35, 162–172 (2021).
Peng, Y. et al. Eye care use among rural adults in China: the Handan Eye Study. Ophthalmic Epidemiol. 20, 274–280 (2013).
Liang, Y. B. et al. Refractive errors in a rural Chinese adult population the Handan eye study. Ophthalmology 116, 2119–2127 (2009).
Li, S. et al. A noninvasive machine learning model using a complete blood count for screening of primary vitreoretinal lymphoma. Nat. Commun. 16, 10667 (2025).
Li, S. et al. Metabolomics identifies and validates serum androstenedione as novel biomarker for diagnosing primary angle closure glaucoma and predicting the visual field progression. eLife 12, RP91407 (2024).
Li, S. et al. Serum metabolite biomarkers for the early diagnosis and monitoring of age-related macular degeneration. J. Adv. Res. S2090-1232, 00434–X (2024).
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).
Arndt, C. et al. Increased intravitreal glucose in rhegmatogenous retinal detachment. Eye 37, 638–643 (2023).
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).
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).
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).
Shao, M., Li, Y., Teng, J., Li, S. & Cao, W. Association between serum lipid levels and patients with primary angle-closure glaucoma in china: a cross sectional, case-control study. Front. Med.) 8, 618970 (2021).
Shao, M. et al. Association between serum complement C3 levels and age-related cataract. Invest. Ophthalmol. Vis. Sci. 58, 4934–4939 (2017).
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).
Li, B. et al. Predictive role of the peripheral blood inflammation indices neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and systemic immunoinflammatory index (SII) for age-related cataract risk. PLoS ONE 19, e0313503 (2024).
Wang, Y. et al. The association between the lipids levels in blood and risk of age-related macular degeneration. Nutrients 8, 663 (2016).
Pinna, A. et al. Complete blood cell count-derived inflammation biomarkers in men with age-related macular degeneration. Ocul. Immunol. Inflamm. 27, 932–936 (2019).
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).
Grandini, M., Bagli, E. & Visani, G. Metrics for multi-class classification: an overview. Preprint at https://doi.org/10.48550/arXiv.2008.05756 (2020).
Hanley, J. A. & McNeil, B. J. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143, 29–36 (1982).
Kerr, K. F., Brown, M. D., Zhu, K. & Janes, H. Assessing the clinical impact of risk prediction models with decision curves: guidance for correct interpretation and appropriate use. J. Clin. Oncol. 34, 2534–2540 (2016).
Steyerberg, E. W. et al. Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiology 21, 128–138 (2010).
Hu, J. et al. Identification and validation of an explainable prediction model of acute kidney injury with prognostic implications in critically ill children: a prospective multicenter cohort study. EClinicalMedicine 68, 102409 (2024).
fudanRenjun. fudanRenjun/high-myopia: high-myopia. Zenodo https://doi.org/10.5281/zenodo.18382509 (2026).
Acknowledgements
This work was supported by the National Key Research and Development Program of China (2024YFC2510805, X.T.Z.), Shanghai Municipal Health Commission (2023ZZ02019, X.T.Z.), and the National Natural Science Foundation of China (82302582, S.J.L.). The sponsors or funding organisations played no role in the design or execution of this research. We gratefully acknowledge the Putuo District Central Hospital of Shanghai University for providing the sample data used in this study.
Author information
Authors and Affiliations
Contributions
W.J.C., X.T.Z, M.Y.L. and S.J.L. conceptualised and designed this study. S.J.L., Y.Z.L., J.N.W., F.L.W., X.X.W., M.Y.Z., H.G.H., Y.X.S. and J.R. performed most experiments. W.J.C., X.T.Z. and M.Y.L. performed partial experiments. S.J.L., J.N.W., F.L.W. and J.R. finished the acquisition and analysis of data. S.J.L., J.R., F.L.W. and J.N.W. prepared figures and performed the statistical analysis. S.J.L. wrote the original draft. W.J.C., X.T.Z, M.Y.L. and S.J.L. reviewed and supervised the manuscript. All the authors have read and approved the final manuscript.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Peer review
Peer review information
Nature Communications thanks Mengtian Kang, Carla Lança and the other anonymous reviewer(s) for their contribution to the peer review of this work. A peer review file is available.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Source data
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Li, S., Ren, J., Wang, F. et al. Routine blood tests and machine learning identify complications in high myopia. Nat Commun (2026). https://doi.org/10.1038/s41467-026-70891-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41467-026-70891-5
