{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T14:01:25Z","timestamp":1790776885207,"version":"4.1.0"},"reference-count":27,"publisher":"BMJ","issue":"9","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"unspecified","delay-in-days":29,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2026,9,8]]},"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Diabetic retinopathy (DR) is one of the leading causes of visual impairment among working-age adults worldwide. Existing artificial intelligence (AI) studies have mainly focused on automated diagnosis and grading of DR or diabetic macular oedema while relatively few studies have investigated long-term prediction of visual outcomes. In clinical practice, patients and clinicians are more concerned about whether future visual decline will occur rather than merely identifying the current presence of DR. This study aims to develop and validate a real-world prognostic model integrating AI-derived imaging scores, ophthalmic examinations and systemic clinical variables to predict 3-year visual decline in patients with diabetes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and analysis<\/jats:title>\n                    <jats:p>This retrospective longitudinal cohort study will use routinely collected ophthalmic imaging and clinical data from Peking University Third Hospital for model development and internal validation, with independent external validation planned using data from Ningbo Eye Hospital, Wenzhou Medical University. The development cohort will cover the period from 1 January 2018 to 1 May 2026. Eligible eyes will have baseline colour fundus photography (CFP) and\/or optical coherence tomography (OCT), baseline best-corrected visual acuity and at least one follow-up visual acuity record within 3 years after the index date. CFP-enhanced analyses will include eyes with eligible CFP, OCT-enhanced analyses will include eyes with eligible OCT and multimodal analyses will require eligible paired CFP and OCT. The primary outcome will be time to first visual decline within 3 years, defined as an increase in logarithm of the minimum angle of resolution (logMAR) best-corrected visual acuity of \u22650.2 from baseline in the same eye. Sustained visual decline, requiring confirmation of a \u22650.2-logMAR deterioration at a subsequent eligible visit, will be evaluated as a key secondary outcome. AI-derived imaging scores will be generated using prespecified modality-specific and multimodal retinal image models. Separate CFP and OCT models will generate continuous CFP-derived and OCT-derived imaging scores, while a prespecified multimodal model jointly integrating paired CFP and OCT information will generate a single continuous multimodal imaging score. These imaging scores will be incorporated separately into prespecified AI-enhanced prognostic models together with demographic, systemic and ophthalmic predictors. Cox regression, penalised Cox regression and exploratory machine learning survival models will be developed and internally validated and the final prognostic model will be externally evaluated in an independent cohort from Ningbo Eye Hospital. Performance will be evaluated using discrimination, calibration, Brier score and decision curve analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Ethics and dissemination<\/jats:title>\n                    <jats:p>This study has received ethical approval from the Ethics Committee of Peking University Third Hospital (approval number: IRB00006761-M20260399). All data will be de-identified before analysis. The findings of this study will be disseminated through peer-reviewed publications and conferences.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2026-123521","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T13:36:48Z","timestamp":1790775408000},"page":"e123521","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Development and validation of an AI-enhanced prediction model for 3-year visual decline in patients with diabetes using ophthalmic imaging: protocol for a real-world longitudinal cohort study"],"prefix":"10.1136","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8967-2250","authenticated-orcid":false,"given":"Yexian","family":"Yu","sequence":"first","affiliation":[{"name":"School of Biomedical Engineering, Hainan University, Sanya, Hainan, China"},{"name":"Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing, China"},{"name":"Key Laboratory of Epidemiology of Major Diseases (Peking University), Ministry of Education, Beijing, China"},{"name":"Hainan Boao Lecheng International Medical Tourism Pilot Zone Administration, Hainan Real-World Data Research Institute, Lecheng, Hainan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiarui","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Peking University Third Hospital, Beijing, China"},{"name":"Beijing Key Laboratory of Restoration of Damaged Ocular Nerve, Peking University Third Hospital, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9452-6622","authenticated-orcid":false,"given":"Yanyan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ningbo Key Laboratory of Medical Research on Blinding Eye Diseases, Ningbo Eye Institute, Wenzhou Medical University, Ningbo Eye Hospital, Ningbo, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaodong","family":"Ma","sequence":"additional","affiliation":[{"name":"Laboratory of Advanced Theranostic Materials and Technology, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Hong","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Peking University Third Hospital, Beijing, China"},{"name":"Beijing Key Laboratory of Restoration of Damaged Ocular Nerve, Peking University Third Hospital, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Nan","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, Hainan University, Sanya, Hainan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4334-6805","authenticated-orcid":false,"given":"Feng","family":"Sun","sequence":"additional","affiliation":[{"name":"Key Laboratory of Epidemiology of Major Diseases (Peking University), Ministry of Education, Beijing, China"},{"name":"Hainan Boao Lecheng International Medical Tourism Pilot Zone Administration, Hainan Real-World Data Research Institute, Lecheng, Hainan, China"},{"name":"Department of Ophthalmology, Peking University Third Hospital, Beijing, China"},{"name":"Department of Epidemiology and Biostatistics, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"key":"2026093006351924000_16.9.e123521.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2021.04.027"},{"key":"2026093006351924000_16.9.e123521.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2024.12.020"},{"key":"2026093006351924000_16.9.e123521.3","doi-asserted-by":"crossref","first-page":"1309","DOI":"10.1001\/jamaophthalmol.2014.2350","article-title":"Disorganization of the retinal inner layers as a predictor of visual acuity in eyes with center-involved diabetic macular edema","volume":"132","author":"Sun","year":"2014","journal-title":"JAMA Ophthalmol"},{"key":"2026093006351924000_16.9.e123521.4","doi-asserted-by":"crossref","first-page":"S252","DOI":"10.2337\/dc25-S012","article-title":"12. Retinopathy, Neuropathy, and Foot Care: Standards of Care in Diabetes\u20142025","volume":"48","year":"2025","journal-title":"Diabetes Care"},{"key":"2026093006351924000_16.9.e123521.5","doi-asserted-by":"publisher","DOI":"10.2337\/dc11-1909"},{"key":"2026093006351924000_16.9.e123521.6","doi-asserted-by":"crossref","DOI":"10.1186\/s40942-023-00473-w","article-title":"OCT biomarkers as predictors of visual improvement in diabetic macular edema eyes receiving dexamethasone implants","volume":"9","author":"Visioli","year":"2023","journal-title":"Int J Retina Vitreous"},{"key":"2026093006351924000_16.9.e123521.7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2007.12.004"},{"key":"2026093006351924000_16.9.e123521.8","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"2026093006351924000_16.9.e123521.9","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-021-23458-5","article-title":"A deep learning system for detecting diabetic retinopathy across the disease spectrum","volume":"12","author":"Dai","year":"2021","journal-title":"Nat Commun"},{"key":"2026093006351924000_16.9.e123521.10","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02702-z"},{"key":"2026093006351924000_16.9.e123521.11","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2024-084574"},{"key":"2026093006351924000_16.9.e123521.12","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"2026093006351924000_16.9.e123521.13","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2022-071058"},{"key":"2026093006351924000_16.9.e123521.14","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2024-082505"},{"key":"2026093006351924000_16.9.e123521.15","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.18152"},{"key":"2026093006351924000_16.9.e123521.16","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1038\/s43856-024-00590-z","article-title":"Predicting 1, 2 and 3 year emergent referable diabetic retinopathy and maculopathy using deep learning","volume":"4","author":"Nderitu","year":"2024","journal-title":"Commun Med"},{"key":"2026093006351924000_16.9.e123521.17","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-019-13922-8","article-title":"Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning","volume":"11","author":"Varadarajan","year":"2020","journal-title":"Nat Commun"},{"key":"2026093006351924000_16.9.e123521.18","doi-asserted-by":"crossref","DOI":"10.3389\/fmed.2025.1741146","article-title":"Early prediction of diabetic retinopathy using a multimodal deep learning framework integrating fundus and OCT imaging","volume":"12","author":"Emara","year":"2026","journal-title":"Frontiers in Medicine."},{"key":"2026093006351924000_16.9.e123521.19","doi-asserted-by":"crossref","unstructured":"Steyerberg EW . Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating. 2nd edn. Cham: Springer, 2019.","DOI":"10.1007\/978-3-030-16399-0"},{"key":"2026093006351924000_16.9.e123521.20","doi-asserted-by":"crossref","unstructured":"Harrell FE . Regression Modeling Strategies: With Applications to Linear Models, Logistic and Ordinal Regression, and Survival Analysis. 2nd edn. Cham: Springer, 2015.","DOI":"10.1007\/978-3-319-19425-7"},{"key":"2026093006351924000_16.9.e123521.21","doi-asserted-by":"crossref","DOI":"10.1186\/s12916-019-1466-7","article-title":"Calibration: the Achilles heel of predictive analytics","volume":"17","author":"Van Calster","year":"2019","journal-title":"BMC Med"},{"key":"2026093006351924000_16.9.e123521.22","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X06295361"},{"key":"2026093006351924000_16.9.e123521.23","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.b2393","article-title":"Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls","volume":"338","author":"Sterne","year":"2009","journal-title":"BMJ"},{"key":"2026093006351924000_16.9.e123521.24","doi-asserted-by":"crossref","unstructured":"Rubin DB . Multiple Imputation for Nonresponse in Surveys. New York: WILEY, 1987.","DOI":"10.1002\/9780470316696"},{"key":"2026093006351924000_16.9.e123521.25","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.m441","article-title":"Calculating the sample size required for developing a clinical prediction model","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"},{"key":"2026093006351924000_16.9.e123521.26","doi-asserted-by":"publisher","DOI":"10.1002\/sim.7992"},{"key":"2026093006351924000_16.9.e123521.27","doi-asserted-by":"publisher","DOI":"10.1136\/bmjophth-2025-002238"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2026-123521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T13:36:51Z","timestamp":1790775411000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2026-123521"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":27,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,30]]},"published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1136\/bmjopen-2026-123521"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2026-123521","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}