{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T21:15:40Z","timestamp":1776892540018,"version":"3.51.2"},"reference-count":21,"publisher":"BMJ","issue":"5","content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Br J Ophthalmol"],"accepted":{"date-parts":[[2025,10,26]]},"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:sec>\n                    <jats:title>Background\/aims<\/jats:title>\n                    <jats:p>This study aimed to develop a multimodal artificial intelligence (AI) system that integrates fundus imaging and patient questionnaire data to achieve clinician-level diagnostic accuracy for diagnosing retinal detachment (RD).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Ultra-widefield fundus images and comprehensive patient questionnaires were collected from patients with RD and healthy controls at Tsukazaki Hospital. A multimodal model was developed using the Contrastive Language\u2013Image Pretraining framework to classify RD cases, alongside separate image-only and questionnaire-only models for comparison. Per-image and per-subject analyses were conducted to assess model performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The multimodal model outperformed single-modal models in per-image and per-subject assessments. It achieved accuracy, recall and F1 scores of 0.899\u00b10.054, 0.902\u00b10.043 and 0.902\u00b10.048 in the per-image analysis and 0.893\u00b10.071, 0.949\u00b10.044 and 0.873\u00b10.074 in the per-subject analysis, respectively. The AI model\u2019s overall diagnostic accuracy was slightly lower than that of human clinicians; however, it exhibited a higher recall rate, indicating improved detection of true RD cases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Integrating fundus imaging with patient questionnaire data significantly improves AI-based RD diagnosis. Future research needs to focus on expanding the dataset and refining the questionnaire design to further improve model performance.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bjo-2025-327506","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T08:55:20Z","timestamp":1762505720000},"page":"586-591","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal artificial intelligence for retinal detachment diagnosis using fundus imaging and patient questionnaires"],"prefix":"10.1136","volume":"110","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8745-8214","authenticated-orcid":false,"given":"Naoyuki","family":"Yonemaru","sequence":"first","affiliation":[{"name":"Technology Laboratory, Cresco Ltd, Minato-ku, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hitoshi","family":"Tabuchi","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Tsukazaki Hosital, Himeji, Hyogo, Japan"},{"name":"Department of Technology and Design Thinking for Medicine, Hiroshima University, Hiroshima, Hiroshima, Japan"},{"name":"Department of Ophthalmology, Hyogo Medical University, Nishinomiya, Hyogo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hodaka","family":"Deguchi","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Tsukazaki Hosital, Himeji, Hyogo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuto","family":"Omi","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Tsukazaki Hosital, Himeji, Hyogo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mao","family":"Tanabe","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Tsukazaki Hosital, Himeji, Hyogo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naofumi","family":"Ishitobi","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Tsukazaki Hosital, Himeji, Hyogo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisashi","family":"Maruyama","sequence":"additional","affiliation":[{"name":"Technology Laboratory, Cresco Ltd, Minato-ku, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuji","family":"Ayatsuka","sequence":"additional","affiliation":[{"name":"Technology Laboratory, Cresco Ltd, Minato-ku, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2025,11,6]]},"reference":[{"key":"2026042202150746000_110.5.586.1","first-page":"1691","article-title":"Evaluation and management of suspected retinal detachment","volume":"69","author":"Gariano","year":"2004","journal-title":"Am Fam Physician"},{"key":"2026042202150746000_110.5.586.2","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1111\/aos.13016","article-title":"What made you wait so long? Delays in presentation of retinal detachment: knowledge is related to an attached macula","volume":"94","author":"Eijk","year":"2016","journal-title":"Acta Ophthalmol"},{"key":"2026042202150746000_110.5.586.3","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1038\/s41433-020-01154-w","article-title":"Urgency of retinal detachment repair: is it time to re-think our priorities?","volume":"35","author":"Grabowska","year":"2021","journal-title":"Eye (Lond)"},{"key":"2026042202150746000_110.5.586.4","doi-asserted-by":"crossref","first-page":"2369","DOI":"10.2147\/OPTH.S460454","article-title":"Telemedicine at a University Ophthalmology Practice During the Beginning of the COVID-19 Pandemic","volume":"18","author":"Oganov","year":"2024","journal-title":"Clin Ophthalmol"},{"key":"2026042202150746000_110.5.586.5","doi-asserted-by":"crossref","DOI":"10.3390\/jcm12093161","article-title":"Evaluating the Efficacy of Teleophthalmology in Delivering Ophthalmic Care to Underserved Populations: A Literature Review","volume":"12","author":"Dolar-Szczasny","year":"2023","journal-title":"J Clin Med"},{"key":"2026042202150746000_110.5.586.6","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.ophtha.2023.09.018","article-title":"Ophthalmology Workforce Projections in the United States, 2020 to 2035","volume":"131","author":"Berkowitz","year":"2024","journal-title":"Ophthalmology"},{"key":"2026042202150746000_110.5.586.7","doi-asserted-by":"crossref","DOI":"10.1186\/s12960-015-0085-4","article-title":"Future requirements for and supply of ophthalmologists for an aging population in Singapore","volume":"13","author":"Ansah","year":"2015","journal-title":"Hum Resour Health"},{"key":"2026042202150746000_110.5.586.8","doi-asserted-by":"crossref","DOI":"10.1038\/s42003-019-0730-x","article-title":"Deep learning for detecting retinal detachment and discerning macular status using ultra-widefield fundus images","volume":"3","author":"Li","year":"2020","journal-title":"Commun Biol"},{"key":"2026042202150746000_110.5.586.9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1167\/tvst.13.4.1","article-title":"Deep Learning-Based Automated Detection of Retinal Breaks and Detachments on Fundus Photography","volume":"13","author":"Christ","year":"2024","journal-title":"Trans Vis Sci Tech"},{"key":"2026042202150746000_110.5.586.10","doi-asserted-by":"crossref","first-page":"1326004","DOI":"10.3389\/fmed.2024.1326004","article-title":"Artificial intelligence-assisted management of retinal detachment from ultra-widefield fundus images based on weakly-supervised approach","volume":"11","author":"Li","year":"2024","journal-title":"Front Med"},{"key":"2026042202150746000_110.5.586.11","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1167\/tvst.13.5.17","article-title":"Prediction of Visual Outcome After Rhegmatogenous Retinal Detachment Surgery Using Artificial Intelligence Techniques","volume":"13","author":"Guo","year":"2024","journal-title":"Trans Vis Sci Tech"},{"key":"2026042202150746000_110.5.586.12","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1038\/s41433-023-02779-3","article-title":"Posterior vitreous detachment and retinal tear - a prospective study of community referrals","volume":"38","author":"Nixon","year":"2024","journal-title":"Eye (Lond)"},{"key":"2026042202150746000_110.5.586.13","unstructured":"Radford A , Kim JW , Hallacy C , et al . Learning transferable visual models from natural language supervision. ArXiv 2021. Available: https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"2026042202150746000_110.5.586.14","unstructured":"Zhao Z , Liu Y , Wu H , et al . CLIP in medical imaging: a survey. ArXiv 2023. Available: https:\/\/arxiv.org\/abs\/2312.07353"},{"key":"2026042202150746000_110.5.586.15","doi-asserted-by":"crossref","unstructured":"Baliah S , Maani FA , Sanjeev S , et al . Exploring the transfer learning capabilities of clip in domain generalization for diabetic retinopathy. In: Cao X , Xu X , Rekik I , et al , eds. Machine learning in medical imaging: 14th International workshop, MLMI 2023, held in conjunction with MICCAI 2023. Cham: Springer, 2023: 444\u201353.","DOI":"10.1007\/978-3-031-45673-2_44"},{"key":"2026042202150746000_110.5.586.16","doi-asserted-by":"crossref","unstructured":"Du J , Guo J , Zhang W , et al . RET-clip: a retinal image foundation model pre-trained with clinical diagnostic reports. ArXiv 2024. Available: https:\/\/arxiv.org\/abs\/2405.14137","DOI":"10.1007\/978-3-031-72390-2_66"},{"key":"2026042202150746000_110.5.586.17","unstructured":"OpenAI. 2025. Available: https:\/\/openai.com\/index\/introducing-gpt-5"},{"key":"2026042202150746000_110.5.586.18","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-025-01772-2","article-title":"A multimodal visual-language foundation model for computational ophthalmology","volume":"8","author":"Shi","year":"2025","journal-title":"NPJ Digit Med"},{"key":"2026042202150746000_110.5.586.19","unstructured":"Shi D , Zhang W , Chen X , et al . EyeFound: a multimodal generalist foundation model for ophthalmic imaging. ArXiv 2024. Available: https:\/\/arxiv.org\/abs\/2405.11338"},{"key":"2026042202150746000_110.5.586.20","doi-asserted-by":"crossref","DOI":"10.3390\/s25144492","article-title":"Multi-Modal AI for Multi-Label Retinal Disease Prediction Using OCT and Fundus Images: A Hybrid Approach","volume":"25","author":"Zedadra","year":"2025","journal-title":"Sensors (Basel)"},{"key":"2026042202150746000_110.5.586.21","doi-asserted-by":"crossref","unstructured":"Tabuchi H , Yonemaru N , Deguchi H , et al . Multimodal dataset for retinal detachment diagnosis: ultra-widefield fundus images and patient questionnaires from Tsukazaki hospital (2020\u20132024). Zenodo; 2025. Available: https:\/\/zenodo.org\/records\/17156390","DOI":"10.1136\/bjo-2025-327506"}],"container-title":["British Journal of Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bjo-2025-327506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T09:16:43Z","timestamp":1776849403000},"score":1,"resource":{"primary":{"URL":"https:\/\/bjo.bmj.com\/lookup\/doi\/10.1136\/bjo-2025-327506"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,6]]},"references-count":21,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,4,22]]},"published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1136\/bjo-2025-327506"],"URL":"https:\/\/doi.org\/10.1136\/bjo-2025-327506","relation":{},"ISSN":["0007-1161","1468-2079"],"issn-type":[{"value":"0007-1161","type":"print"},{"value":"1468-2079","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,6]]}}}