{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T20:05:22Z","timestamp":1789157122945,"version":"build-2803163510"},"reference-count":57,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T00:00:00Z","timestamp":1699920000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01LM013426"],"award-info":[{"award-number":["R01LM013426"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R21LM013937"],"award-info":[{"award-number":["R21LM013937"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R21EY031443"],"award-info":[{"award-number":["R21EY031443"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["T15LM007088"],"award-info":[{"award-number":["T15LM007088"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P30EY10572"],"award-info":[{"award-number":["P30EY10572"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000053","name":"National Eye Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100001818","name":"Research to Prevent Blindness","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100001818","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,1,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Surgical outcome prediction is challenging but necessary for postoperative management. Current machine learning models utilize pre- and post-op data, excluding intraoperative information in surgical notes. Current models also usually predict binary outcomes even when surgeries have multiple outcomes that require different postoperative management. This study addresses these gaps by incorporating intraoperative information into multimodal models for multiclass glaucoma surgery outcome prediction.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and methods<\/jats:title>\n                  <jats:p>We developed and evaluated multimodal deep learning models for multiclass glaucoma trabeculectomy surgery outcomes using both structured EHR data and free-text operative notes. We compare those to baseline models that use structured EHR data exclusively, or neural network models that leverage only operative notes.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The multimodal neural network had the highest performance with a macro AUROC of 0.750 and F1 score of 0.583. It outperformed the baseline machine learning model with structured EHR data alone (macro AUROC of 0.712 and F1 score of 0.486). Additionally, the multimodal model achieved the highest recall (0.692) for hypotony surgical failure, while the surgical success group had the highest precision (0.884) and F1 score (0.775).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>This study shows that operative notes are an important source of predictive information. The multimodal predictive model combining perioperative notes and structured pre- and post-op EHR data outperformed other models. Multiclass surgical outcome prediction can provide valuable insights for clinical decision-making.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>Our results show the potential of deep learning models to enhance clinical decision-making for postoperative management. They can be applied to other specialties to improve surgical outcome predictions.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocad213","type":"journal-article","created":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T09:24:41Z","timestamp":1700040281000},"page":"456-464","source":"Crossref","is-referenced-by-count":26,"title":["Prediction of multiclass surgical outcomes in glaucoma using multimodal deep learning based on free-text operative notes and structured EHR data"],"prefix":"10.1093","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2226-4619","authenticated-orcid":false,"given":"Wei-Chun","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Medical Informatics & Clinical Epidemiology, Oregon Health & Science University , 3181 S.W. Sam Jackson Park Rd , Portland, OR, 97239, United States"},{"name":"Department of Ophthalmology, Casey Eye Institute, Oregon Health & Science University , 545 SW Campus Dr , Portland, OR, 97239, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aiyin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Casey Eye Institute, Oregon Health & Science University , 545 SW Campus Dr , Portland, OR, 97239, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xubo","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Medical Informatics & Clinical Epidemiology, Oregon Health & Science University , 3181 S.W. Sam Jackson Park Rd , Portland, OR, 97239, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0365-909X","authenticated-orcid":false,"given":"Nicole G","family":"Weiskopf","sequence":"additional","affiliation":[{"name":"Department of Medical Informatics & Clinical Epidemiology, Oregon Health & Science University , 3181 S.W. Sam Jackson Park Rd , Portland, OR, 97239, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8172-7636","authenticated-orcid":false,"given":"Michael F","family":"Chiang","sequence":"additional","affiliation":[{"name":"National Eye Institute, National Institutes of Health , 31 Center Dr MSC 2510 , Bethesda, MD, 20892, United States"},{"name":"National Library of Medicine, National Institutes of Health , 8600 Rockville Pike , Bethesda, MD, 20894, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1724-1858","authenticated-orcid":false,"given":"Michelle R","family":"Hribar","sequence":"additional","affiliation":[{"name":"Department of Medical Informatics & Clinical Epidemiology, Oregon Health & Science University , 3181 S.W. Sam Jackson Park Rd , Portland, OR, 97239, United States"},{"name":"Department of Ophthalmology, Casey Eye Institute, Oregon Health & Science University , 545 SW Campus Dr , Portland, OR, 97239, United States"},{"name":"National Eye Institute, National Institutes of Health , 31 Center Dr MSC 2510 , Bethesda, MD, 20892, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,11,14]]},"reference":[{"issue":"1","key":"2024011907285481400_ocad213-B1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1197\/jamia.M2273","article-title":"Toward a national framework for the secondary use of health data: an American Medical Informatics Association White Paper","volume":"14","author":"Safran","year":"2007","journal-title":"J Am Med Inform Assoc"},{"key":"2024011907285481400_ocad213-B2","author":"Charles","year":"2013"},{"issue":"6","key":"2024011907285481400_ocad213-B3","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1111\/joim.12119","article-title":"Electronic health records: new opportunities for clinical research","volume":"274","author":"Coorevits","year":"2013","journal-title":"J Intern Med"},{"issue":"8","key":"2024011907285481400_ocad213-B4","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1111\/jop.13013","article-title":"Improvement of oral cancer screening quality and reach: the promise of artificial intelligence","volume":"49","author":"Kar","year":"2020","journal-title":"J Oral Pathol Med"},{"key":"2024011907285481400_ocad213-B5","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.canlet.2019.12.007","article-title":"Artificial intelligence in cancer diagnosis and prognosis: opportunities and challenges","volume":"471","author":"Huang","year":"2020","journal-title":"Cancer Lett"},{"issue":"1","key":"2024011907285481400_ocad213-B6","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1055\/s-0039-1677903","article-title":"Artificial intelligence in clinical decision support: challenges for evaluating AI and practical implications","volume":"28","author":"Magrabi","year":"2019","journal-title":"Yearb Med Inform"},{"key":"2024011907285481400_ocad213-B7","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1109\/RBME.2020.3007816","article-title":"Machine learning for clinical outcome prediction","volume":"14","author":"Shamout","year":"2021","journal-title":"IEEE Rev Biomed Eng"},{"issue":"12","key":"2024011907285481400_ocad213-B8","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1097\/BRS.0000000000002442","article-title":"Examining the ability of artificial neural networks machine learning models to accurately predict complications following posterior lumbar spine fusion","volume":"43","author":"Kim","year":"2018","journal-title":"Spine (Phila Pa 1976)"},{"issue":"6","key":"2024011907285481400_ocad213-B9","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1016\/j.jspd.2018.03.003","article-title":"Predicting surgical complications in patients undergoing elective adult spinal deformity procedures using machine learning","volume":"6","author":"Kim","year":"2018","journal-title":"Spine Deform"},{"issue":"6","key":"2024011907285481400_ocad213-B10","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1016\/j.bja.2019.07.030","article-title":"An automated machine learning-based model predicts postoperative mortality using readily-extractable preoperative electronic health record data","volume":"123","author":"Hill","year":"2019","journal-title":"Br J Anaesth"},{"issue":"4","key":"2024011907285481400_ocad213-B11","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1097\/ALN.0000000000002186","article-title":"Development and validation of a deep neural network model for prediction of postoperative in-hospital mortality","volume":"129","author":"Lee","year":"2018","journal-title":"Anesthesiology"},{"key":"2024011907285481400_ocad213-B12","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.jss.2021.02.045","article-title":"Machine learning and surgical outcomes prediction: a systematic review","volume":"264","author":"Elfanagely","year":"2021","journal-title":"J Surg Res"},{"issue":"2","key":"2024011907285481400_ocad213-B13","doi-asserted-by":"crossref","first-page":"544","DOI":"10.3390\/s21020544","article-title":"Prediction of postoperative complications for patients of end stage renal disease","volume":"21","author":"Jeong","year":"2021","journal-title":"Sensors"},{"issue":"4","key":"2024011907285481400_ocad213-B14","doi-asserted-by":"crossref","first-page":"e0215133","DOI":"10.1371\/journal.pone.0215133","article-title":"Using a machine learning approach to predict outcome after surgery for degenerative cervical myelopathy","volume":"14","author":"Merali","year":"2019","journal-title":"PLoS One"},{"issue":"11","key":"2024011907285481400_ocad213-B15","doi-asserted-by":"crossref","first-page":"3701","DOI":"10.1007\/s00417-022-05738-y","article-title":"Machine learning predicting myopic regression after corneal refractive surgery using preoperative data and fundus photography","volume":"260","author":"Kim","year":"2022","journal-title":"Graefes Arch Clin Exp Ophthalmol"},{"issue":"79-80","key":"2024011907285481400_ocad213-B16","first-page":"73","article-title":"Post-operative management of trabeculectomy in the first three months","volume":"25","author":"Murdoch","year":"2012","journal-title":"Commun Eye Health"},{"issue":"Suppl 1","key":"2024011907285481400_ocad213-B17","doi-asserted-by":"crossref","first-page":"S131","DOI":"10.4103\/0301-4738.73689","article-title":"Management of complications in glaucoma surgery","volume":"59","author":"Vijaya","year":"2011","journal-title":"Indian J Ophthalmol"},{"issue":"2","key":"2024011907285481400_ocad213-B18","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1097\/BRS.0000000000004511","article-title":"Predicting bone health using machine learning in patients undergoing spinal reconstruction surgery","volume":"48","author":"Shen","year":"2023","journal-title":"Spine (Phila Pa 1976)"},{"key":"2024011907285481400_ocad213-B19","doi-asserted-by":"crossref","first-page":"615987","DOI":"10.1155\/2014\/615987","article-title":"Postoperative arrhythmias after cardiac surgery: incidence, risk factors, and therapeutic management","volume":"2014","author":"Peretto","year":"2014","journal-title":"Cardiol Res Pract"},{"issue":"1","key":"2024011907285481400_ocad213-B20","doi-asserted-by":"crossref","first-page":"2473","DOI":"10.1038\/s41598-022-06438-7","article-title":"Evaluation of machine learning algorithms for trabeculectomy outcome prediction in patients with glaucoma","volume":"12","author":"Banna","year":"2022","journal-title":"Sci Rep"},{"key":"2024011907285481400_ocad213-B21","doi-asserted-by":"crossref","first-page":"1898","DOI":"10.12688\/f1000research.12904.1","article-title":"Predictive value of early postoperative IOP and bleb morphology in mitomycin-C augmented trabeculectomy","volume":"6","author":"Esfandiari","year":"2017","journal-title":"F1000Res"},{"issue":"1","key":"2024011907285481400_ocad213-B22","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1186\/s12886-015-0007-1","article-title":"Pre-operative intraocular pressure does not influence outcome of trabeculectomy surgery: a retrospective cohort study","volume":"15","author":"Nesaratnam","year":"2015","journal-title":"BMC Ophthalmol"},{"issue":"11","key":"2024011907285481400_ocad213-B23","first-page":"e11686","article-title":"Epidemiology of glaucoma: the past, present, and predictions for the future","volume":"12","author":"Allison","year":"2020","journal-title":"Cureus"},{"issue":"5","key":"2024011907285481400_ocad213-B24","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1016\/j.ajo.2009.06.018","article-title":"Three-year follow-up of the tube versus trabeculectomy study","volume":"148","author":"Gedde","year":"2009","journal-title":"Am J Ophthalmol"},{"key":"2024011907285481400_ocad213-B25","doi-asserted-by":"crossref","first-page":"114135","DOI":"10.1016\/j.psychres.2021.114135","article-title":"Detecting formal thought disorder by deep contextualized word representations","volume":"304","author":"Sarzynska-Wawer","year":"2021","journal-title":"Psychiatry Res"},{"issue":"12","key":"2024011907285481400_ocad213-B26","doi-asserted-by":"crossref","first-page":"1935","DOI":"10.1093\/jamia\/ocaa189","article-title":"Clinical concept extraction using transformers","volume":"27","author":"Yang","year":"2020","journal-title":"J Am Med Inform Assoc"},{"key":"2024011907285481400_ocad213-B27","first-page":"2","author":"Devlin","year":"2019"},{"key":"2024011907285481400_ocad213-B28","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.jbi.2017.11.011","article-title":"Clinical information extraction applications: a literature review","volume":"77","author":"Wang","year":"2018","journal-title":"J Biomed Inform"},{"key":"2024011907285481400_ocad213-B29","first-page":"773","article-title":"Extraction of active medications and adherence using natural language processing for glaucoma patients","volume":"2021","author":"Lin","year":"2021","journal-title":"AMIA Annu Symp Proc"},{"key":"2024011907285481400_ocad213-B30","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.knosys.2016.05.016","article-title":"A semantic web based framework for the interoperability and exploitation of clinical models and EHR data","volume":"105","author":"del Carmen Legaz-Garc\u00eda","year":"2016","journal-title":"Knowl Based Syst"},{"key":"2024011907285481400_ocad213-B31","first-page":"352","article-title":"Research on text classification based on CNN and LSTM","volume":"2019","author":"Luan","year":"2019","journal-title":"IEEE ICAICA"},{"key":"2024011907285481400_ocad213-B32","first-page":"2611","article-title":"The hateful memes challenge: detecting hate speech in multimodal memes","volume":"33","author":"Kiela","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"2024011907285481400_ocad213-B33","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1186\/s12911-020-01297-6","article-title":"Combining structured and unstructured data for predictive models: a deep learning approach","volume":"20","author":"Zhang","year":"2020","journal-title":"BMC Med Inform Decis Mak"},{"key":"2024011907285481400_ocad213-B34","first-page":"238","article-title":"Combining structured and unstructured data for predicting risk of readmission for heart failure patients","volume":"264","author":"Mahajan","year":"2019","journal-title":"MedInfo"},{"key":"2024011907285481400_ocad213-B35","first-page":"72","author":"Alsentzer"},{"issue":"9","key":"2024011907285481400_ocad213-B36","doi-asserted-by":"crossref","first-page":"e6486","DOI":"10.1002\/cpe.6486","article-title":"Text classification using improved bidirectional transformer","volume":"34","author":"Tezgider","year":"2022","journal-title":"Concurr Comput Pract Exp"},{"issue":"1","key":"2024011907285481400_ocad213-B37","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1076\/opep.5.1.41.1499","article-title":"Standardized measurement of visual acuity","volume":"5","author":"Ricci","year":"1998","journal-title":"Ophthal Epidemiol"},{"key":"2024011907285481400_ocad213-B38","author":"Mikolov"},{"key":"2024011907285481400_ocad213-B39","author":"\u0158eh\u016f\u0159ek","year":"2011"},{"key":"2024011907285481400_ocad213-B40","author":"Rong"},{"key":"2024011907285481400_ocad213-B41","volume-title":"Python 3 Reference Manual","author":"Van Rossum","year":"2009"},{"key":"2024011907285481400_ocad213-B42","first-page":"8024","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024011907285481400_ocad213-B43","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2024011907285481400_ocad213-B44","author":"Wolf"},{"issue":"2","key":"2024011907285481400_ocad213-B45","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s11749-016-0481-7","article-title":"A random forest guided tour","volume":"25","author":"Biau","year":"2016","journal-title":"Test"},{"key":"2024011907285481400_ocad213-B46","first-page":"707","article-title":"Improving text classification with transformer","volume":"2021","author":"Soyalp","year":"2021","journal-title":"IEEE UBMK"},{"issue":"1","key":"2024011907285481400_ocad213-B47","doi-asserted-by":"crossref","first-page":"9289","DOI":"10.1038\/s41598-020-62971-3","article-title":"Deep learning for improved risk prediction in surgical outcomes","volume":"10","author":"Jalali","year":"2020","journal-title":"Sci Rep"},{"key":"2024011907285481400_ocad213-B48","author":"Liu"},{"issue":"8","key":"2024011907285481400_ocad213-B49","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nat Med"},{"key":"2024011907285481400_ocad213-B50","first-page":"172","author":"Singhal"},{"issue":"5","key":"2024011907285481400_ocad213-B51","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1177\/01410768231173123","article-title":"Large language models will not replace healthcare professionals: curbing popular fears and hype","volume":"116","author":"Thirunavukarasu","year":"2023","journal-title":"J R Soc Med"},{"key":"2024011907285481400_ocad213-B52","author":"Shaheen"},{"issue":"9","key":"2024011907285481400_ocad213-B53","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1097\/IJG.0b013e318285ff44","article-title":"Can intraoperative intraocular pressure during primary trabeculectomy predict early postoperative pressure?","volume":"23","author":"Rong","year":"2014","journal-title":"J Glaucoma"},{"issue":"2","key":"2024011907285481400_ocad213-B54","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1097\/00061198-200604000-00004","article-title":"Prospective evaluation of preoperative factors associated with successful mitomycin C needling of failed filtration blebs","volume":"15","author":"Guti\u00e9rrez-Ortiz","year":"2006","journal-title":"J Glaucoma"},{"key":"2024011907285481400_ocad213-B55","first-page":"6","article-title":"Text data augmentation using generative adversarial networks \u2013 a systematic review","volume":"1","author":"Silva","year":"2023","journal-title":"J Comput Appl Linguist"},{"issue":"12","key":"2024011907285481400_ocad213-B56","doi-asserted-by":"crossref","first-page":"e0000168","DOI":"10.1371\/journal.pdig.0000168","article-title":"Predicting dementia from spontaneous speech using large language models","volume":"1","author":"Agbavor","year":"2022","journal-title":"PLoS Digit Health"},{"key":"2024011907285481400_ocad213-B57","author":"Wu"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/2\/456\/56209406\/ocad213.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/2\/456\/56209406\/ocad213.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T07:31:33Z","timestamp":1705649493000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/31\/2\/456\/7420544"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,14]]},"references-count":57,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,11,14]]},"published-print":{"date-parts":[[2024,1,18]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocad213","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,2,1]]},"published":{"date-parts":[[2023,11,14]]}}}