{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T05:59:01Z","timestamp":1792735141880,"version":"4.5.0"},"reference-count":28,"publisher":"BMJ","issue":"2","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"unspecified","delay-in-days":51,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["#K23AG071945"],"award-info":[{"award-number":["#K23AG071945"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["bmjph"],"accepted":{"date-parts":[[2026,4,30]]},"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>This study assesses the utility of integrating multimodal preoperative electronic health records (EHRs), including unstructured medical notes, for early postoperative delirium prediction. We aim to demonstrate the feasibility of this data integration to facilitate future expansion of the methodology towards risk stratification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Transformer-based models were trained and evaluated using EHR data (2013\u20132021) from the Indiana Network for Patient Care for patients undergoing major surgeries such as laparotomies, bowel resections and cardiac procedures. Delirium was assessed retrospectively using (1) International Classification of Diseases, 10th revision codes and (2) clinician\/nurse assessments from both structured and unstructured documentation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>From an initial cohort of 35\u2009128 control patients, postoperative delirium was identified in 3872 (assessment 1) and 15\u2009351 (assessment 2) cases. Prevalent background comorbidities included pre-existing conditions such as hypertension, diabetes, hypothyroidism and chronic pulmonary disease. Following data balancing, our late fusion multimodal transformer model achieved an area under the receiver operating characteristic curve of 0.80. The model demonstrated increased sensitivity to patients with high disease burden, highlighting the potential of advanced architectures for using unstructured clinical data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Using up to 4 years of preoperative EHR data offers the significant advantage of earlier risk identification, facilitating enhanced preoperative surgical patient care. By successfully unlocking the nuanced clinical signals within preoperative unstructured data, this study provides a robust foundation for incorporating medical notes into early postoperative delirium prediction.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjph-2025-003375","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T15:45:14Z","timestamp":1779464714000},"page":"e003375","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["Early prediction of postoperative delirium in major surgery patients using multimodal preoperative EHR and medical notes: a retrospective cohort study in the Indiana network for patient care"],"prefix":"10.1136","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0198-0871","authenticated-orcid":false,"given":"Lena","family":"Ara","sequence":"first","affiliation":[{"name":"Elmore Family School of Electrical and Computer Engineering, Purdue University, Indianapolis, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5401-0368","authenticated-orcid":false,"given":"Zina","family":"Ben Miled","sequence":"additional","affiliation":[{"name":"Phillip M. Drayer Department of Electrical and Computer Engineering, Lamar University, Beaumont, Texas, USA"},{"name":"Indiana University School of Medicine, Indianapolis, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Malaz","family":"Boustani","sequence":"additional","affiliation":[{"name":"Indiana University School of Medicine, Indianapolis, Indiana, USA"},{"name":"Regenstrief Institute Inc, Indianapolis, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0295-3457","authenticated-orcid":false,"given":"Sanjay","family":"Mohanty","sequence":"additional","affiliation":[{"name":"Indiana University School of Medicine, Indianapolis, Indiana, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,5,22]]},"reference":[{"key":"2026052208450842000_4.2.e003375.1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(13)60688-1"},{"key":"2026052208450842000_4.2.e003375.2","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2017-019223","article-title":"Systematic review of prediction models for delirium in the older adult inpatient","volume":"8","author":"Lindroth","year":"2018","journal-title":"BMJ Open"},{"key":"2026052208450842000_4.2.e003375.3","doi-asserted-by":"crossref","first-page":"1373","DOI":"10.1001\/jamaneurol.2020.2273","article-title":"Association of Delirium With Long-term Cognitive Decline: A Meta-analysis","volume":"77","author":"Goldberg","year":"2020","journal-title":"JAMA Neurol"},{"key":"2026052208450842000_4.2.e003375.4","article-title":"ICU Delirium-Prediction Models: A Systematic Review","volume":"2","author":"Ruppert","year":"2020","journal-title":"Crit Care Explor"},{"key":"2026052208450842000_4.2.e003375.5","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1016\/j.jaclp.2020.12.005","article-title":"Development and External Validation of a Delirium Prediction Model for Hospitalized Patients With Coronavirus Disease 2019","volume":"62","author":"Castro","year":"2021","journal-title":"J Acad Consult Liaison Psychiatry"},{"key":"2026052208450842000_4.2.e003375.6","doi-asserted-by":"crossref","first-page":"11503","DOI":"10.1038\/s41598-024-61627-w","article-title":"Machine learning-based model to predict delirium in patients with advanced cancer treated with palliative care: a multicenter, patient-based registry cohort","volume":"14","author":"Kim","year":"2024","journal-title":"Sci Rep"},{"key":"2026052208450842000_4.2.e003375.7","doi-asserted-by":"crossref","first-page":"1292","DOI":"10.1093\/jamia\/ocac058","article-title":"Use of unstructured text in prognostic clinical prediction models: a systematic review","volume":"29","author":"Seinen","year":"2022","journal-title":"J Am Med Inform Assoc"},{"key":"2026052208450842000_4.2.e003375.8","doi-asserted-by":"crossref","unstructured":"Devlin J , Chang MW , Lee K , et al . BERT: pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North; Minneapolis, Minnesota, 2019:4171\u201386. doi:10.18653\/v1\/N19-1423 Available: http:\/\/aclweb.org\/anthology\/N19-1","DOI":"10.18653\/v1\/N19-1423"},{"key":"2026052208450842000_4.2.e003375.9","doi-asserted-by":"crossref","unstructured":"Grinsztajn L , Oyallon E , Varoquaux G . Why do tree-based models still outperform deep learning on typical tabular data. In: Advances in Neural Information Processing Systems. New Orleans, LA: Curran Associates, Inc, 2022: 507\u201320.","DOI":"10.52202\/068431-0037"},{"key":"2026052208450842000_4.2.e003375.10","unstructured":"Somepalli G , Goldblum M , Schwarzschild A , et al . SAINT: Improved neural networks for tabular data via row attention and contrastive pre-training. arXiv 2021. doi:10.48550\/arXiv.2106.01342"},{"key":"2026052208450842000_4.2.e003375.11","doi-asserted-by":"crossref","first-page":"6679","DOI":"10.1609\/aaai.v35i8.16826","article-title":"TabNet: Attentive Interpretable Tabular Learning","volume":"35","author":"Arik","year":"2021","journal-title":"AAAI"},{"key":"2026052208450842000_4.2.e003375.12","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1038\/s41551-023-01045-x","article-title":"A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics","volume":"7","author":"Zhou","year":"2023","journal-title":"Nat Biomed Eng"},{"key":"2026052208450842000_4.2.e003375.13","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"2026052208450842000_4.2.e003375.14","unstructured":"Fang L , Chen Q , Wei CH , et al . Bioformer: an efficient transformer language model for biomedical text mining. arXiv 2023. Available: https:\/\/arxiv.org\/abs\/2302.01588"},{"key":"2026052208450842000_4.2.e003375.15","doi-asserted-by":"publisher","DOI":"10.1377\/hlthaff.24.5.1214"},{"key":"2026052208450842000_4.2.e003375.16","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa113"},{"key":"2026052208450842000_4.2.e003375.17","doi-asserted-by":"publisher","DOI":"10.1002\/pds.4226"},{"key":"2026052208450842000_4.2.e003375.18","doi-asserted-by":"publisher","DOI":"10.1097\/00005650-199801000-00004"},{"key":"2026052208450842000_4.2.e003375.19","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9681(87)90171-8"},{"key":"2026052208450842000_4.2.e003375.20","unstructured":"Doyle DJ , Hendrix JM , Garmon EH . American Society of Anesthesiologists Classification. Treasure Island (FL): StatPearls Publishing, 2023."},{"key":"2026052208450842000_4.2.e003375.21","doi-asserted-by":"crossref","unstructured":"Jiao X , Yin Y , Shang L , et al . TinyBERT: distilling BERT for natural language understanding. arXiv 2019. doi:10.48550\/arXiv.1909.10351","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"2026052208450842000_4.2.e003375.22","unstructured":"Lundberg SM , Lee SI . A unified approach to interpreting model predictions. Adv Neural Inf Process Syst 2017. doi:10.48550\/arXiv.1705.07874"},{"key":"2026052208450842000_4.2.e003375.23","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-113-12-941"},{"key":"2026052208450842000_4.2.e003375.24","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1038\/s41572-020-00223-4","article-title":"Delirium","volume":"6","author":"Wilson","year":"2020","journal-title":"Nat Rev Dis Primers"},{"key":"2026052208450842000_4.2.e003375.25","doi-asserted-by":"publisher","DOI":"10.1038\/s41582-022-00698-7"},{"key":"2026052208450842000_4.2.e003375.26","doi-asserted-by":"crossref","unstructured":"Warner B , Chaffin A , Clavi\u00e9 B , et al . Smarter, better, faster, longer: A modern bidirectional encoder for fast, memory efficient, and long context finetuning and inference. arXiv 2024. doi:10.18653\/v1\/2025.acl-long.127","DOI":"10.18653\/v1\/2025.acl-long.127"},{"key":"2026052208450842000_4.2.e003375.27","doi-asserted-by":"crossref","unstructured":"Rahman W , Hasan MK , Lee S , et al . Integrating multimodal information in large pretrained transformers. Proc 58th Annu Meet Assoc Comput Linguist; 2020 doi:10.18653\/v1\/2020.acl-main.214 Available: https:\/\/www.aclweb.org\/anthology\/2020.acl-main","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"2026052208450842000_4.2.e003375.28","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"}],"container-title":["BMJ Public Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjph-2025-003375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T15:45:16Z","timestamp":1779464716000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjpublichealth.bmj.com\/lookup\/doi\/10.1136\/bmjph-2025-003375"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":28,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,5,22]]},"published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1136\/bmjph-2025-003375"],"URL":"https:\/\/doi.org\/10.1136\/bmjph-2025-003375","relation":{},"ISSN":["2753-4294"],"issn-type":[{"value":"2753-4294","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}