{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:12:17Z","timestamp":1781532737487,"version":"3.54.5"},"reference-count":73,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:p>Orthopedic anesthesia necessitates the real-time integration of rapidly changing physiological states, specific interventions, and contextual narratives to avert hypotension, postoperative nausea and vomiting, and uncontrolled pain. We present Ortho PeriFT, a multimodal transformer that integrates perioperative prediction, therapeutic recommendations, and continuous monitoring with a calibrated uncertainty. The encoder was designed to align with clinical time scales by processing second-level waveform patches and minute-level numerical data, alongside medication and event tokens and extended clinical text, with optional prompts from preoperative imaging. Self-supervised pre-training on extensive clinical time series was followed by multitask fine-tuning for the primary endpoints. A constrained Decision Transformer suggests titrations of fluids, vasopressors, and anesthetic depth under guideline-aware action masks, with all outputs accompanied by conformal risk intervals to allow abstention when confidence is low. Across both internal and external cohorts, Ortho PeriFT enhanced discrimination and precision-recall for all primary outcomes compared to robust classical and neural baselines, reduced calibration error and negative log-likelihood, and maintained narrow uncertainty bands. Off-policy estimators indicate higher counterfactual utility than clinician behavior and behavior cloning while ensuring zero-guardrail violations. Streaming analyses demonstrated earlier warnings at matched false alarm rates, and performance generalized across orthopedic subtypes with stable calibration across demographic strata. Attribution maps and prototype trajectory retrieval offer case-based rationales that are aligned with clinical reasoning. These findings illustrate that a hierarchical, safety-aware, and interpretable transformer can provide accurate risk estimates, actionable therapeutic suggestions, and timely alerts for orthopedic anesthesia within a unified framework.<\/jats:p>","DOI":"10.3389\/fmed.2026.1836430","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T13:31:35Z","timestamp":1781530295000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging transformer-based artificial intelligence for enhanced anesthetic decision-making in orthopedic surgery"],"prefix":"10.3389","volume":"13","author":[{"given":"Yuanzhou","family":"Mao","sequence":"first","affiliation":[{"name":"Department of Anesthesiology, Sichuan Province Orthopedic Hospital","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Chengdu Studying Biotechnology Co., LTD","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peiyu","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Sichuan Province Orthopedic Hospital","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijun","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Sichuan Province Orthopedic Hospital","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liting","family":"Wang","sequence":"additional","affiliation":[{"name":"Chengdu Studying Biotechnology Co., LTD","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yalan","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Sichuan Province Orthopedic Hospital","place":["Chengdu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1186\/s12877-024-05431-1","article-title":"Association of preoperative cognitive frailty with postoperative complications in older patients under general anesthesia: a prospective cohort study","volume":"24","author":"Fang","year":"2024","journal-title":"BMC Geriatr"},{"key":"B2","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1097\/SA.0000000000000064","article-title":"Relationship between intraoperative mean arterial pressure and clinical outcomes after noncardiac surgery: toward an empirical definition of hypotension","volume":"58","author":"Walsh","year":"2014","journal-title":"Surv Anesthesiol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1097\/ALN.0000000000001432","article-title":"Relationship between intraoperative hypotension, defined by either reduction from baseline or absolute thresholds, and acute kidney and myocardial injury after noncardiac surgery","volume":"126","author":"Salmasi","year":"2017","journal-title":"Anesthesiology"},{"key":"B4","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.jpain.2015.12.008","article-title":"Management of Postoperative Pain: a clinical practice guideline from the American pain society, the American Society of Regional Anesthesia and Pain Medicine, and the American Society of Anesthesiologists' committee on regional anesthesia, executive committee, and administrative council","volume":"17","author":"Chou","year":"2016","journal-title":"J Pain"},{"key":"B5","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1097\/00000542-199909000-00022","article-title":"A simplified risk score for predicting postoperative nausea and vomiting: conclusions from cross-validations between two centers","volume":"91","author":"Apfel","year":"1999","journal-title":"Anesthesiology"},{"key":"B6","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1213\/ANE.0000000000004833","article-title":"Fourth consensus guidelines for the management of postoperative nausea and vomiting","volume":"131","author":"Gan","year":"2020","journal-title":"Anesthesia"},{"key":"B7","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1186\/s13054-022-04173-z","article-title":"Effective hemodynamic monitoring","volume":"26","author":"Pinsky","year":"2022","journal-title":"Crit Care"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e88","DOI":"10.1213\/ANE.0000000000003433","article-title":"Feasibility of fully automated hypnosis, analgesia, and fluid management using 2 independent closed-loop systems during major vascular surgery: a pilot study","volume":"128","author":"Joosten","year":"2019","journal-title":"Anesthesia"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1316931","DOI":"10.3389\/fdgth.2024.1316931","article-title":"Strengths-weaknesses-opportunities-threats analysis of artificial intelligence in anesthesiology and perioperative medicine","volume":"6","author":"Paiste","year":"2024","journal-title":"Front Digital Health"},{"key":"B10","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1080\/10705511.2023.2287967","article-title":"Dynamic structural equation models with missing data: Data requirements on N and T","volume":"31","author":"Fang","year":"2024","journal-title":"Struct Equat Model"},{"key":"B11","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/s41512-018-0045-2","article-title":"Dynamic models to predict health outcomes: current status and methodological challenges","volume":"2","author":"Jenkins","year":"2018","journal-title":"Diagnost Prognost Res"},{"key":"B12","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1002\/jrsm.1453","article-title":"Assessing context suitability (generalizability, external validity, applicability or transferability) of findings in evidence syntheses in healthcare\u2014An integrative review of methodological guidance","volume":"11","author":"Weise","year":"2020","journal-title":"Res Synth Methods"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1712.06957","article-title":"MURA: Large dataset for abnormality detection in musculoskeletal radiographs","author":"Rajpurkar","year":"2017","journal-title":"arXiv"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1433","DOI":"10.1016\/j.joca.2008.06.016","article-title":"The osteoarthritis initiative: report on the design rationale for the magnetic resonance imaging protocol for the knee","volume":"16","author":"Peterfy","year":"2008","journal-title":"Osteoarthrit Cartilage"},{"key":"B15","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.05150","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv"},{"key":"B17","first-page":"17283","article-title":"Big bird: transformers for longer sequences","author":"Zaheer","year":"2020","journal-title":"34th Conference on neural information processing systems (NeurIPS 2020)"},{"key":"B18","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s41597-022-01411-5","article-title":"VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients","volume":"9","author":"Lee","year":"2022","journal-title":"Sci Data"},{"key":"B19","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1038\/s41597-024-03517-4","article-title":"INSPIRE, a publicly available research dataset for perioperative medicine","volume":"11","author":"Lim","year":"2024","journal-title":"Sci Data"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooad084","article-title":"Medical Informatics Operating Room Vitals and Events Repository (MOVER): a public-access operating room database","author":"Samad","year":"2023","journal-title":"JAMIA Open"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-023-01945-2","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci Data"},{"key":"B22","unstructured":"HiRID\n            \n            \n              A High Time Resolution ICU\n              Dataset\n            \n          \n          \n          2020"},{"key":"B23","doi-asserted-by":"publisher","first-page":"e563","DOI":"10.1097\/CCM.0000000000004916","article-title":"Sharing ICU patient data responsibly under the society of critical care medicine\/European society of intensive care medicine joint data science collaboration: the Amsterdam university medical centers database (AmsterdamUMCdb) example","volume":"49","author":"Thoral","year":"2021","journal-title":"Crit Care Med"},{"key":"B24","unstructured":"VitalDB, A High Fidelity Multi Parameter Vital Signs Database in Surgical Patients, Version 1.0.0; 2022"},{"key":"B25","first-page":"15084","article-title":"Decision Transformer: Reinforcement Learning Via Sequence Modeling","volume-title":"NIPS'21: Proceedings of the 35th international conference on neural information processing systems.","author":"Chen","year":"2021"},{"key":"B26","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1561\/2200000101","article-title":"Conformal prediction: a gentle introduction","volume":"16","author":"Angelopoulos","year":"2023","journal-title":"Found Trends Mach Learn"},{"key":"B27","first-page":"1321","article-title":"On calibration of modern neural networks","author":"Guo","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"B28","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med Deci Mak"},{"key":"B29","article-title":"Doubly robust policy evaluation and learning","author":"Dud\u00edk","year":"2011","journal-title":"Proceedings of the 28th international conference on machine learning"},{"key":"B30","first-page":"2139","article-title":"Data-efficient off-policy policy evaluation for reinforcement learning","author":"Thomas","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"B31","unstructured":"INSPIRE\n              Dataset on PhysioNet\n            \n          \n          \n          2024"},{"key":"B32","unstructured":"MIMIC-IV\n              on PhysioNet\n            \n          \n          \n          2024"},{"key":"B33","doi-asserted-by":"publisher","first-page":"e0277957","DOI":"10.1371\/journal.pone.0277957","article-title":"Machine learning for prediction of postoperative nausea and vomiting in patients with intravenous patient-controlled analgesia","volume":"17","author":"Shim JG Ryu","year":"2022","journal-title":"PLoS ONE"},{"key":"B34","doi-asserted-by":"publisher","first-page":"6439","DOI":"10.1038\/s41598-023-33807-7","article-title":"Development and assessment of novel machine learning models to predict the probability of postoperative nausea and vomiting for patient-controlled analgesia","volume":"13","author":"Xie","year":"2023","journal-title":"Sci Rep"},{"key":"B35","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1186\/s12871-025-02987-2","article-title":"Predicting postoperative nausea and vomiting using machine learning: a model development and validation study","volume":"25","author":"Glebov","year":"2025","journal-title":"BMC Anesthesiol"},{"key":"B36","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1186\/s12874-024-02357-5","article-title":"Deep learning models for the prediction of acute postoperative pain in PACU for video-assisted thoracoscopic surgery","volume":"24","author":"Zhang","year":"2024","journal-title":"BMC Med Res Methodol"},{"key":"B37","doi-asserted-by":"publisher","first-page":"970281","DOI":"10.3389\/fdgth.2022.970281","article-title":"Fairness in the prediction of acute postoperative pain using machine learning models","volume":"4","author":"Davoudi","year":"2023","journal-title":"Front Digital Health"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1335","DOI":"10.1111\/anae.16429","article-title":"Carl\u00e9 N, Uhrbrand CG, Haroutounian S, Nikolajsen L. Prognostic clinical prediction models for acute post-surgical pain in adults: a systematic review","volume":"79","author":"Papadomanolakis-Pakis","year":"2024","journal-title":"Anaesthesia"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1016\/j.bja.2024.08.007","article-title":"Machine learning-augmented interventions in perioperative care: a systematic review and meta-analysis","volume":"133","author":"Mehta","year":"2024","journal-title":"Br J Anaesth"},{"key":"B40","doi-asserted-by":"publisher","first-page":"108326","DOI":"10.1016\/j.engappai.2024.108326","article-title":"Applications of artificial intelligence in Orthopaedic surgery: a systematic review and meta-analysis","volume":"133","author":"Geda","year":"2024","journal-title":"Eng Appl Artif Intell"},{"key":"B41","first-page":"5606","article-title":"Clocs: Contrastive learning of cardiac signals across space, time, and patients","author":"Kiyasseh","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"B42","doi-asserted-by":"publisher","first-page":"7155","DOI":"10.1038\/s41598-020-62922-y","article-title":"BEHRT: transformer for electronic health records","volume":"10","author":"Li","year":"2020","journal-title":"Sci Rep"},{"key":"B43","article-title":"H, Schlegel V, Sun Y","author":"Sun","year":"2025"},{"key":"B44","author":"Kottapalli","year":"2025","journal-title":"Foundation Models for Time Series: A Survey"},{"key":"B45","author":"Samad","year":"2023","journal-title":"MOVER: Medical Informatics Operating Room Vitals and Events Repository"},{"key":"B46","article-title":"HiRID-ICU-benchmark-a comprehensive machine learning benchmark on high-resolution ICU Data","author":"Y\u00e8che","year":"2021","journal-title":"In Thirty-fifth conference on neural information processing systems datasets and benchmarks track (round 1)"},{"key":"B47","unstructured":"2024"},{"key":"B48","unstructured":"2017"},{"key":"B49","unstructured":""},{"key":"B50","unstructured":"2025"},{"key":"B51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1159\/000339789","article-title":"KDIGO clinical practice guideline for acute kidney injury","volume":"2","author":"Khwaja","year":"2012","journal-title":"Kidney Int Suppl."},{"key":"B52","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"He","year":"2022"},{"key":"B53","first-page":"17283","author":"Zaheer","year":"2020","journal-title":"Big bird: Transformers for Longer Sequences"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.14795","article-title":"Perceiver IO: A general architecture for structured inputs & outputs","author":"Jaegle","year":"2021","journal-title":"arXiv"},{"key":"B55","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"B56","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","author":"Fujimoto","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"B57","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","author":"Kumar","year":"2020","journal-title":"34th conference on neural information processing systems (NeurIPS 2020)"},{"key":"B58","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1093\/biomet\/70.1.41","article-title":"The central role of the propensity score in observational studies for causal effects","volume":"70","author":"Rosenbaum","year":"1983","journal-title":"Biometrika"},{"key":"B59","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.acl-main.385","article-title":"Quantifying attention flow in transformers","author":"Abnar","year":"2020","journal-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics"},{"key":"B60","first-page":"3319","article-title":"Axiomatic attribution for deep networks","author":"Sundararajan","year":"2017","journal-title":"International conference on machine learning. Proceedings of the 34th international conference on machine learning"},{"key":"B61","first-page":"359","article-title":"Using dynamic time warping to find patterns in time series","author":"Berndt","year":"1994","journal-title":"Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining"},{"key":"B62","first-page":"785","article-title":"Xgboost: A scalable tree boosting system","author":"Chen","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining"},{"key":"B63","article-title":"LightGBM: a highly efficient gradient boosting decision tree","author":"Ke","year":"2017","journal-title":"Advances in neural information processing systems. 31st conference on neural information processing systems (NIPS 2017)"},{"key":"B64","doi-asserted-by":"publisher","first-page":"1724","DOI":"10.3115\/v1\/D14-1179","article-title":"Learning phrase representations using RNN encoder-decoder for statisticalmachine translation","author":"Cho","year":"2014","journal-title":"Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)"},{"key":"B65","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"B66","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1803.01271","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"arXiv"},{"key":"B67","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2012.06678","article-title":"Tabtransformer: Tabular data modeling using contextual embeddings","author":"Huang","year":"2020","journal-title":"arXiv"},{"key":"B68","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"},{"key":"B69","doi-asserted-by":"publisher","first-page":"72","DOI":"10.18653\/v1\/W19-1909","article-title":"Publicly available clinical BERT embeddings. Proceedings of the 2nd Clinical Natural Language Processing Workshop","author":"Alsentzer","year":"2019","journal-title":"arXiv"},{"key":"B70","doi-asserted-by":"crossref","DOI":"10.1145\/1143844.1143874","article-title":"The relationship between Precision-Recall and ROC curves","author":"Davis","year":"2006","journal-title":"Proceedings of the 23rd International Conference on Machine Learning"},{"key":"B71","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1126\/science.aax2342","article-title":"Dissecting racial bias in an algorithm used to manage the health of populations","volume":"366","author":"Obermeyer","year":"2019","journal-title":"Science"},{"key":"B72","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1145\/3287560.3287596","article-title":"Model cards for model reporting","author":"Mitchell","year":"2019","journal-title":"Proceedings of the Conference on Fairness, Accountability, and Transparency"},{"key":"B73","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1186\/s13063-020-04951-6","article-title":"Reporting guidelines for clinical trials of artificial intelligence interventions: the SPIRIT-AI and CONSORT-AI guidelines","volume":"22","author":"Ibrahim","year":"2021","journal-title":"Trials"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1836430\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T13:31:49Z","timestamp":1781530309000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1836430\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":73,"alternative-id":["10.3389\/fmed.2026.1836430"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1836430","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,15]]},"article-number":"1836430"}}