{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:27:30Z","timestamp":1792790850381,"version":"4.5.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T00:00:00Z","timestamp":1704412800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T00:00:00Z","timestamp":1704412800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000009","name":"Foundation for the National Institutes of Health","doi-asserted-by":"publisher","award":["5 K23 EY032204-02"],"award-info":[{"award-number":["5 K23 EY032204-02"]}],"id":[{"id":"10.13039\/100000009","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>To develop and evaluate the performance of a deep learning model (DLM) that predicts eyes at high risk of surgical intervention for uncontrolled glaucoma\u00a0based on multimodal data from an initial ophthalmology visit. Longitudinal, observational, retrospective study. 4898 unique eyes from 4038 adult glaucoma or glaucoma-suspect patients who underwent surgery for uncontrolled glaucoma (trabeculectomy, tube shunt, xen, or diode surgery) between 2013 and 2021, or did not undergo glaucoma surgery but had 3 or more ophthalmology visits. We constructed a DLM to predict the occurrence of glaucoma surgery within various time horizons from a baseline visit. Model inputs included spatially oriented visual field (VF) and optical coherence tomography (OCT) data as well as clinical and demographic features. Separate DLMs with the same architecture were trained to predict the occurrence of surgery within 3\u00a0months, within 3\u20136\u00a0months, within 6\u00a0months\u20131\u00a0year, within 1\u20132\u00a0years, within 2\u20133\u00a0years, within 3\u20134\u00a0years, and within 4\u20135\u00a0years from the baseline visit. Included eyes were randomly split into 60%, 20%, and 20% for training, validation, and testing. DLM performance was measured using area under the receiver operating characteristic curve (AUC) and precision-recall curve (PRC). Shapley additive explanations (SHAP) were utilized to assess the importance of different features. Model prediction of surgery for uncontrolled glaucoma within 3\u00a0months had the best AUC of 0.92 (95% CI 0.88, 0.96). DLMs achieved clinically useful AUC values (&gt;\u20090.8) for all models that predicted the occurrence of surgery within 3\u00a0years. According to SHAP analysis, all 7 models placed intraocular pressure (IOP) within the five most important features in predicting the occurrence of glaucoma surgery. Mean deviation (MD) and average retinal nerve fiber layer (RNFL) thickness were listed among the top 5 most important features by 6 of the 7 models. DLMs can successfully identify eyes requiring surgery for uncontrolled glaucoma within specific time horizons. Predictive performance decreases as the time horizon for forecasting surgery increases. Implementing prediction models in a clinical setting may help identify patients that should be referred to a glaucoma specialist for surgical evaluation.<\/jats:p>","DOI":"10.1038\/s41598-023-50597-0","type":"journal-article","created":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T11:03:32Z","timestamp":1704452612000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Deep learning-based identification of eyes at risk for glaucoma surgery"],"prefix":"10.1038","volume":"14","author":[{"given":"Ruolin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Bradley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"Herbert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaihua","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pradeep","family":"Ramulu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katharina","family":"Breininger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathias","family":"Unberath","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jithin","family":"Yohannan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,5]]},"reference":[{"issue":"6","key":"50597_CR1","doi-asserted-by":"publisher","first-page":"e339","DOI":"10.1016\/S2214-109X(13)70113-X","volume":"1","author":"RRA Bourne","year":"2013","unstructured":"Bourne, R. R. A. et al. Causes of vision loss worldwide, 1990\u20132010: A systematic analysis. Lancet Glob. Health. 1(6), e339-349. https:\/\/doi.org\/10.1016\/S2214-109X(13)70113-X (2013).","journal-title":"Lancet Glob. Health."},{"issue":"11","key":"50597_CR2","doi-asserted-by":"publisher","first-page":"2081","DOI":"10.1016\/j.ophtha.2014.05.013","volume":"121","author":"YC Tham","year":"2014","unstructured":"Tham, Y. C. et al. Global prevalence of glaucoma and projections of glaucoma burden through 2040: A systematic review and meta-analysis. Ophthalmology. 121(11), 2081\u20132090. https:\/\/doi.org\/10.1016\/j.ophtha.2014.05.013 (2014).","journal-title":"Ophthalmology."},{"issue":"12","key":"50597_CR3","doi-asserted-by":"publisher","first-page":"e1221","DOI":"10.1016\/S2214-109X(17)30393-5","volume":"5","author":"SR Flaxman","year":"2017","unstructured":"Flaxman, S. R. et al. Global causes of blindness and distance vision impairment 1990\u20132020: A systematic review and meta-analysis. Lancet Glob. Health. 5(12), e1221\u2013e1234. https:\/\/doi.org\/10.1016\/S2214-109X(17)30393-5 (2017).","journal-title":"Lancet Glob. Health."},{"issue":"7","key":"50597_CR4","doi-asserted-by":"publisher","first-page":"4135","DOI":"10.1167\/iovs.14-14643","volume":"55","author":"BC Chauhan","year":"2014","unstructured":"Chauhan, B. C. et al. Rates of glaucomatous visual field change in a large clinical population. Investig. Ophthalmol. Vis. Sci. 55(7), 4135\u20134143. https:\/\/doi.org\/10.1167\/iovs.14-14643 (2014).","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"issue":"4","key":"50597_CR5","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1136\/bjophthalmol-2019-314336","volume":"104","author":"S Resnikoff","year":"2020","unstructured":"Resnikoff, S. et al. Estimated number of ophthalmologists worldwide (International Council of Ophthalmology update): Will we meet the needs?. Br. J. Ophthalmol. 104(4), 588\u2013592. https:\/\/doi.org\/10.1136\/bjophthalmol-2019-314336 (2020).","journal-title":"Br. J. Ophthalmol."},{"issue":"4","key":"50597_CR6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0249856","volume":"16","author":"SR Shuldiner","year":"2021","unstructured":"Shuldiner, S. R. et al. Predicting eyes at risk for rapid glaucoma progression based on an initial visual field test using machine learning. PLoS ONE. 16(4), e0249856. https:\/\/doi.org\/10.1371\/journal.pone.0249856 (2021).","journal-title":"PLoS ONE."},{"key":"50597_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ogla.2023.03.005","author":"P Herbert","year":"2023","unstructured":"Herbert, P. et al. Forecasting risk of future rapid glaucoma worsening using early visual field, optical coherence tomography, and clinical data. Ophthalmol. Glaucoma. https:\/\/doi.org\/10.1016\/j.ogla.2023.03.005 (2023).","journal-title":"Ophthalmol. Glaucoma."},{"key":"50597_CR8","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.ajo.2021.06.025","volume":"233","author":"K Shon","year":"2022","unstructured":"Shon, K., Sung, K. R. & Shin, J. W. Can artificial intelligence predict glaucomatous visual field progression? A spatial-ordinal convolutional neural network model. Am. J. Ophthalmol. 233, 124\u2013134. https:\/\/doi.org\/10.1016\/j.ajo.2021.06.025 (2022).","journal-title":"Am. J. Ophthalmol."},{"key":"50597_CR9","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.ajo.2021.01.008","volume":"227","author":"SL Baxter","year":"2021","unstructured":"Baxter, S. L. et al. Predictive analytics for glaucoma using data from the all of US research program. Am. J. Ophthalmol. 227, 74\u201386. https:\/\/doi.org\/10.1016\/j.ajo.2021.01.008 (2021).","journal-title":"Am. J. Ophthalmol."},{"issue":"7","key":"50597_CR10","doi-asserted-by":"publisher","first-page":"984","DOI":"10.1016\/j.ophtha.2018.01.007","volume":"125","author":"W Zheng","year":"2018","unstructured":"Zheng, W. et al. Systemic medication associations with presumed advanced or uncontrolled primary open-angle glaucoma. Ophthalmology. 125(7), 984\u2013993. https:\/\/doi.org\/10.1016\/j.ophtha.2018.01.007 (2018).","journal-title":"Ophthalmology."},{"issue":"11","key":"50597_CR11","doi-asserted-by":"publisher","first-page":"1612","DOI":"10.1016\/j.ophtha.2017.04.035","volume":"124","author":"J Yohannan","year":"2017","unstructured":"Yohannan, J. et al. Evidence-based criteria for assessment of visual field reliability. Ophthalmology. 124(11), 1612\u20131620. https:\/\/doi.org\/10.1016\/j.ophtha.2017.04.035 (2017).","journal-title":"Ophthalmology."},{"key":"50597_CR12","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.ajo.2019.07.005","volume":"208","author":"SL Baxter","year":"2019","unstructured":"Baxter, S. L., Marks, C., Kuo, T. T., Ohno-Machado, L. & Weinreb, R. N. Machine learning-based predictive modeling of surgical intervention in glaucoma using systemic data from electronic health records. Am. J. Ophthalmol. 208, 30\u201340. https:\/\/doi.org\/10.1016\/j.ajo.2019.07.005 (2019).","journal-title":"Am. J. Ophthalmol."},{"key":"50597_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.xops.2022.100127","author":"SY Wang","year":"2022","unstructured":"Wang, S. Y., Tseng, B. & Hernandez-Boussard, T. Deep learning approaches for predicting glaucoma progression using electronic health records and natural language processing. Ophthalmol. Sci. https:\/\/doi.org\/10.1016\/j.xops.2022.100127 (2022).","journal-title":"Ophthalmol. Sci."},{"issue":"9","key":"50597_CR14","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1097\/JTO.0b013e3181ec173d","volume":"5","author":"JN Mandrekar","year":"2010","unstructured":"Mandrekar, J. N. Receiver operating characteristic curve in diagnostic test assessment. J. Thorac. Oncol. Off. Publ. Int. Assoc. Study Lung Cancer. 5(9), 1315\u20131316. https:\/\/doi.org\/10.1097\/JTO.0b013e3181ec173d (2010).","journal-title":"J. Thorac. Oncol. Off. Publ. Int. Assoc. Study Lung Cancer."},{"key":"50597_CR15","unstructured":"Lundberg, S. & Lee, S. I. A Unified Approach to Interpreting Model Predictions. (2017) (Accessed 8 June 2023) http:\/\/arxiv.org\/abs\/1705.07874."},{"issue":"2","key":"50597_CR16","doi-asserted-by":"publisher","first-page":"99","DOI":"10.4274\/tjo.galenos.2019.78000","volume":"50","author":"A Bayer","year":"2020","unstructured":"Bayer, A. & Akman, A. Artifacts and anatomic variations in optical coherence tomography. Turk. J. Ophthalmol. 50(2), 99\u2013106. https:\/\/doi.org\/10.4274\/tjo.galenos.2019.78000 (2020).","journal-title":"Turk. J. Ophthalmol."},{"issue":"11","key":"50597_CR17","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1097\/IJG.0000000000001374","volume":"28","author":"MS Sung","year":"2019","unstructured":"Sung, M. S., Heo, H. & Park, S. W. Structure-function relationship in advanced glaucoma after reaching the RNFL floor. J. Glaucoma. 28(11), 1006\u20131011. https:\/\/doi.org\/10.1097\/IJG.0000000000001374 (2019).","journal-title":"J. Glaucoma."},{"key":"50597_CR18","unstructured":"Dosovitskiy, A. et al. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. (2021). (Accessed 27 Dec 2022) http:\/\/arxiv.org\/abs\/2010.11929."},{"issue":"1","key":"50597_CR19","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C. & Khoshgoftaar, T. M. A survey on image data augmentation for deep learning. J. Big Data. 6(1), 60. https:\/\/doi.org\/10.1186\/s40537-019-0197-0 (2019).","journal-title":"J. Big Data."},{"key":"50597_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2023.116985","volume":"116","author":"H Zhang","year":"2023","unstructured":"Zhang, H., Tang, J., Wu, P., Li, H. & Zeng, N. A novel attention-based enhancement framework for face mask detection in complicated scenarios. Signal Process Image Commun. 116, 116985. https:\/\/doi.org\/10.1016\/j.image.2023.116985 (2023).","journal-title":"Signal Process Image Commun."},{"key":"50597_CR21","doi-asserted-by":"publisher","unstructured":"Attention-based VGG-16 model for COVID-19 chest X-ray image classification|SpringerLink. (Accessed 1 Oct 2023) https:\/\/doi.org\/10.1007\/s10489-020-02055-x.","DOI":"10.1007\/s10489-020-02055-x"},{"key":"50597_CR22","unstructured":"A Large-Scale Database and a CNN Model for Attention-Based Glaucoma Detection|IEEE Journals & Magazine|IEEE Xplore. (Accessed 29 Sept 2023) https:\/\/ieeexplore.ieee.org\/document\/8756196."},{"issue":"1","key":"50597_CR23","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1186\/s12938-021-00877-5","volume":"20","author":"X Xu","year":"2021","unstructured":"Xu, X. et al. Automatic glaucoma detection based on transfer induced attention network. Biomed. Eng. OnLine. 20(1), 39. https:\/\/doi.org\/10.1186\/s12938-021-00877-5 (2021).","journal-title":"Biomed. Eng. OnLine."},{"issue":"1","key":"50597_CR24","doi-asserted-by":"publisher","first-page":"1603","DOI":"10.3233\/JIFS-230659","volume":"45","author":"M Murugesan","year":"2023","unstructured":"Murugesan, M., JeyaliLaseetha, T. S., Sundaram, S. & Kandasamy, H. Glaucoma disease detection using stacked attention U-Net and deep convolutional neural network. J. Intell. Fuzzy Syst. Appl. Eng. Technol. 45(1), 1603\u20131616. https:\/\/doi.org\/10.3233\/JIFS-230659 (2023).","journal-title":"J. Intell. Fuzzy Syst. Appl. Eng. Technol."},{"key":"50597_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106874","volume":"158","author":"M Liu","year":"2023","unstructured":"Liu, M. et al. AA-WGAN: Attention augmented Wasserstein generative adversarial network with application to fundus retinal vessel segmentation. Comput. Biol. Med. 158, 106874. https:\/\/doi.org\/10.1016\/j.compbiomed.2023.106874 (2023).","journal-title":"Comput. Biol. Med."},{"key":"50597_CR26","doi-asserted-by":"publisher","unstructured":"Liu, Z. et al. Swin transformer: Hierarchical vision transformer using shifted windows. In 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 9992\u201310002 (IEEE, 2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"50597_CR27","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/3454167","author":"A Hussain","year":"2022","unstructured":"Hussain, A., Hussain, T., Ullah, W., Baik, S. W. & Ding, B. Y. Vision transformer and deep sequence learning for human activity recognition in surveillance videos. Comput. Intell. Neurosci. https:\/\/doi.org\/10.1155\/2022\/3454167 (2022).","journal-title":"Comput. Intell. Neurosci."},{"issue":"3","key":"50597_CR28","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong, E. R., DeLong, D. M. & Clarke-Pearson, D. L. Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach. Biometrics. 44(3), 837\u2013845 (1988).","journal-title":"Biometrics."},{"key":"50597_CR29","doi-asserted-by":"crossref","unstructured":"Regression Shrinkage and Selection Via the Lasso | Journal of the Royal Statistical Society Series B: Statistical Methodology | Oxford Academic. (Accessed 1 Oct 2023) https:\/\/academic.oup.com\/jrsssb\/article\/58\/1\/267\/7027929.","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"50597_CR30","doi-asserted-by":"publisher","unstructured":"Tikhonov Regularization and Total Least Squares | SIAM Journal on Matrix Analysis and Applications. (Accessed 1 Oct 2023) https:\/\/doi.org\/10.1137\/S0895479897326432.","DOI":"10.1137\/S0895479897326432"},{"key":"50597_CR31","unstructured":"EarlyStopping\u2014PyTorch-Ignite v0.4.12 Documentation (Accessed 6 Oct 2023) https:\/\/pytorch.org\/ignite\/generated\/ignite.handlers.early_stopping.EarlyStopping.html."},{"key":"50597_CR32","unstructured":"sklearn.model_selection.GridSearchCV\u2014scikit-learn 1.3.1 documentation. (Accessed 6 Oct 2023) https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.model_selection.GridSearchCV.html."},{"issue":"6","key":"50597_CR33","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1186\/cc3000","volume":"8","author":"V Bewick","year":"2004","unstructured":"Bewick, V., Cheek, L. & Ball, J. Statistics review 13: Receiver operating characteristic curves. Crit. Care. 8(6), 508\u2013512. https:\/\/doi.org\/10.1186\/cc3000 (2004).","journal-title":"Crit. Care."},{"issue":"3","key":"50597_CR34","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1002\/bimj.200710415","volume":"50","author":"MD Ruopp","year":"2008","unstructured":"Ruopp, M. D., Perkins, N. J., Whitcomb, B. W. & Schisterman, E. F. Youden index and optimal cut-point estimated from observations affected by a lower limit of detection. Biom J. 50(3), 419\u2013430. https:\/\/doi.org\/10.1002\/bimj.200710415 (2008).","journal-title":"Biom J."},{"key":"50597_CR35","doi-asserted-by":"publisher","unstructured":"17. A Value for n-Person Games. (Accessed 6 Oct 2023) https:\/\/doi.org\/10.1515\/9781400881970-018\/html.","DOI":"10.1515\/9781400881970-018\/html"},{"issue":"6","key":"50597_CR36","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1016\/j.ophtha.2008.03.031","volume":"115","author":"DS Minckler","year":"2008","unstructured":"Minckler, D. S. et al. Aqueous shunts in glaucoma: A report by the American Academy of Ophthalmology. Ophthalmology. 115(6), 1089\u20131098. https:\/\/doi.org\/10.1016\/j.ophtha.2008.03.031 (2008).","journal-title":"Ophthalmology."},{"issue":"8","key":"50597_CR37","doi-asserted-by":"publisher","first-page":"1011","DOI":"10.1001\/archophthalmol.2011.182","volume":"129","author":"BA Francis","year":"2011","unstructured":"Francis, B. A. et al. Vision loss and recovery after trabeculectomy: Risk and associated risk factors. Arch. Ophthalmol. 129(8), 1011\u20131017. https:\/\/doi.org\/10.1001\/archophthalmol.2011.182 (2011).","journal-title":"Arch. Ophthalmol."},{"issue":"9","key":"50597_CR38","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1097\/IJG.0000000000001906","volume":"30","author":"J Yohannan","year":"2021","unstructured":"Yohannan, J., Boland, M. V. & Ramulu, P. The association between intraocular pressure and visual field worsening in treated glaucoma patients. J. Glaucoma. 30(9), 759\u2013768. https:\/\/doi.org\/10.1097\/IJG.0000000000001906 (2021).","journal-title":"J. Glaucoma."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-50597-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-50597-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-50597-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T11:11:25Z","timestamp":1704453085000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-50597-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,5]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["50597"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-50597-0","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,5]]},"assertion":[{"value":"7 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"599"}}