{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T14:16:24Z","timestamp":1788444984138,"version":"build-2803163510"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T00:00:00Z","timestamp":1787184000000},"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>Machine learning prediction models consistently outperform conventional clinical scoring tools across perioperative outcomes, yet remain largely unadopted at the bedside. This narrative review examines explainable artificial intelligence (XAI) as a bridge between algorithmic performance and clinical translation, drawing on a targeted search of PubMed and Embase (January 2018 to March 2026). Five prediction domains are synthesized: perioperative hypotension, postoperative complications, difficult airway management, depth-of-anesthesia monitoring, and regional anesthesia and pain management. SHAP (SHapley Additive exPlanations) has emerged as the dominant XAI method, identifying modifiable intraoperative targets. Attention mechanisms and GradCAM provide complementary interpretability for time-series and imaging-based models. Critical gaps persist: most delirium prediction models include no XAI analysis; no standardized evaluation framework exists, and no prospective trial has demonstrated that XAI-enhanced recommendations improve patient outcomes. Addressing these gaps is a research priority if XAI is to fulfill its potential as a facilitator of perioperative AI adoption.<\/jats:p>","DOI":"10.3389\/fmed.2026.1928394","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T11:24:26Z","timestamp":1787225066000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable artificial intelligence in anesthesiology prediction models: bridging the gap from black-box algorithms to clinical decision support"],"prefix":"10.3389","volume":"13","author":[{"given":"Yan","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Anesthesiology, Qingdao Municipal Hospital","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuoyan","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Qingdao Municipal Hospital","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Qingdao Municipal Hospital","place":["Qingdao, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,20]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"e62853","DOI":"10.2196\/62853","article-title":"A risk prediction model (CMC-AKIX) for postoperative acute kidney injury using machine learning: algorithm development and validation","volume":"27","author":"Min","year":"2025","journal-title":"J Med Internet Res"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1016\/j.bja.2024.07.027","article-title":"Machine learning-augmented interventions in perioperative medicine: a systematic review and meta-analysis","volume":"133","author":"Mehta","year":"2024","journal-title":"Br J Anaesth"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1097\/ACO.0000000000001479","article-title":"Roadmap for artificial intelligence in pain medicine","volume":"38","author":"Adams","year":"2025","journal-title":"Curr Opin Anaesthesiol"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"925","DOI":"10.1016\/j.bja.2024.07.015","article-title":"Machine learning and preoperative risk prediction: the machines are coming","volume":"133","author":"Shelley","year":"2024","journal-title":"Br J Anaesth"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1186\/s12911-025-02930-y","article-title":"Machine learning-based prediction of post-induction hypotension: identifying risk factors and enhancing anesthesia management","volume":"25","author":"Chen","year":"2025","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e0231172","DOI":"10.1371\/journal.pone.0231172","article-title":"Development of a prediction model for hypotension after induction of anesthesia using machine learning","volume":"15","author":"Kang","year":"2020","journal-title":"PLoS One"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1007\/s10877-025-01295-x","article-title":"Developing a machine learning-based prediction model for postinduction hypotension","volume":"39","author":"Katsin","year":"2025","journal-title":"J Clin Monit Comput"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1186\/s12967-024-05481-4","article-title":"Predictive ability of hypotension prediction index and machine learning methods in intraoperative hypotension: a systematic review and meta-analysis","volume":"22","author":"Mohammadi","year":"2024","journal-title":"J Transl Med"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1016\/j.bja.2024.02.025","article-title":"Utilising intraoperative respiratory dynamic features for developing and validating an explainable machine learning model for postoperative pulmonary complications","volume":"132","author":"Li","year":"2024","journal-title":"Br J Anaesth"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"2170","DOI":"10.1097\/CM9.0000000000003447","article-title":"Development and multicenter validation of a machine learning model for postoperative pulmonary complications after neurosurgery","volume":"138","author":"Xu","year":"2025","journal-title":"Chin Med J"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"940","DOI":"10.1186\/s12888-025-07401-2","article-title":"Machine learning-based prediction models for postoperative delirium: a systematic review and meta-analysis","volume":"25","author":"Tu","year":"2025","journal-title":"BMC Psychiatry"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1002\/acn3.70029","article-title":"Development of a disease model for postoperative delirium prediction with biomarkers and SHAP analysis","volume":"12","author":"Wan","year":"2025","journal-title":"Ann Clin Transl Neurol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1186\/s12933-025-02644-5","article-title":"Stress Hyperglycemia ratio and machine learning model for prediction of all-cause mortality in patients undergoing cardiac surgery","volume":"24","author":"Pei","year":"2025","journal-title":"Cardiovasc Diabetol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"101589","DOI":"10.1016\/j.accpm.2025.101589","article-title":"Artificial intelligence for difficult airway prediction: a systematic review and meta-analysis","volume":"44","author":"Abosamak","year":"2025","journal-title":"Anaesth Crit Care Pain Med"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1213\/ANE.0000000000006789","article-title":"Future of artificial intelligence for difficult airway management","volume":"140","author":"De Rosa","year":"2025","journal-title":"Anesth Analg"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1606","DOI":"10.1016\/j.bja.2025.12.052","article-title":"Artificial intelligence in airway management: a narrative review","volume":"136","author":"Sorbello","year":"2026","journal-title":"Br J Anaesth"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"102569","DOI":"10.1016\/j.artmed.2023.102569","article-title":"Development of a bispectral index score prediction model based on an interpretable deep learning algorithm","volume":"143","author":"Hwang","year":"2023","journal-title":"Artif Intell Med"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"e55046","DOI":"10.2196\/55046","article-title":"Supervised explainable machine learning for post-liver transplant pulmonary complications","volume":"27","author":"Ding","year":"2025","journal-title":"J Med Internet Res"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1111\/anae.16315","article-title":"Artificial intelligence in peri-operative prediction model research: are we there yet?","volume":"79","author":"Shah","year":"2024","journal-title":"Anaesthesia"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1186\/s12911-025-02986-w","article-title":"Anesthesia depth prediction from drug infusion history using hybrid AI","volume":"25","author":"Wang","year":"2025","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/s12264-024-01345-6","article-title":"Accurate machine learning-based EEG depth monitoring for anesthesia","volume":"41","author":"Tu","year":"2025","journal-title":"Neurosci Bull"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1007\/s10877-025-01301-2","article-title":"Quantitative electroencephalogram and machine learning to predict expired sevoflurane concentration in infants","volume":"39","author":"Kumar","year":"2025","journal-title":"J Clin Monit Comput"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"e078378","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"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"e63601","DOI":"10.2196\/63601","article-title":"Predicting agitation-sedation levels in intensive care unit patients: development of an ensemble model","volume":"13","author":"Dai","year":"2025","journal-title":"JMIR Med Inform"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1186\/s12871-023-02118-9","article-title":"The prognostic value of intraoperative HRV during Anesthesia in patients presenting for non-cardiac surgery","volume":"23","author":"Niu","year":"2023","journal-title":"BMC Anesthesiol"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/s12874-022-01540-w","article-title":"Comparative analysis of explainable machine learning prediction models for hospital mortality","volume":"22","author":"Stenwig","year":"2022","journal-title":"BMC Med Res Methodol"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"17965","DOI":"10.1038\/s41598-025-20584-8","article-title":"Development and validation of a risk prediction model for postoperative pulmonary complications in 44,740 patients","volume":"15","author":"Cong","year":"2025","journal-title":"Sci Rep"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"101567","DOI":"10.1016\/j.accpm.2025.101567","article-title":"Reshaping anesthesia with artificial intelligence","volume":"44","author":"Dost","year":"2025","journal-title":"Anesth Crit Care Pain Med"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1145\/2939672.2939778","article-title":"\"Why should I trust you?\": explaining the predictions of any classifier","author":"Ribeiro","year":"2016","journal-title":"Proc 22nd ACM SIGKDD Int Conf Knowl Discov Data Min"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"3543","DOI":"10.18653\/v1\/N19-1357","article-title":"Attention is not explanation","author":"Jain","year":"2019","journal-title":"Proc 2019 Conf North Am Chapter Assoc Comput Linguist"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1056\/NEJMsa1410639","article-title":"Driving pressure and survival in the acute respiratory distress syndrome","volume":"372","author":"Amato","year":"2015","journal-title":"N Engl J Med"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1528","DOI":"10.1111\/anae.16733","article-title":"Guidance for reporting artificial intelligence technology evaluations for ultrasound scanning in regional anaesthesia","volume":"80","author":"Zhang","year":"2025","journal-title":"Anaesthesia"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1497","DOI":"10.1016\/j.bja.2024.12.040","article-title":"Evaluation of AI-based nerve segmentation on ultrasound: relevance of standard metrics in the clinical setting","volume":"134","author":"Delvaux","year":"2025","journal-title":"Br J Anaesth"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1016\/j.bja.2025.05.052","article-title":"Artificial intelligence-based nerve segmentation: standardised methodology needed for ultrasound-guided regional anaesthesia","volume":"135","author":"Delvaux","year":"2025","journal-title":"Br J Anaesth"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1016\/j.jopan.2025.10.003","article-title":"The intelligent needle: the role of artificial intelligence in ultrasound-guided regional anesthesia","volume":"41","author":"Dost","year":"2026","journal-title":"J Perianesth Nurs"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2147\/JMDH.S572550","article-title":"Explainable machine learning for prediction of early postoperative nausea and vomiting after general anesthesia","volume":"19","author":"Chang","year":"2026","journal-title":"J Multidiscip Healthc"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"e97747","DOI":"10.7759\/cureus.97747","article-title":"A systematic literature review of precision anesthesia through machine learning: automated drug titration and real-time physiologic optimization","volume":"17","author":"Zarei","year":"2025","journal-title":"Cureus"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1016\/j.anclin.2025.02.003","article-title":"Artificial intelligence for regional anesthesia and pain management","volume":"43","author":"Schroeder","year":"2025","journal-title":"Anesthesiol Clin"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"4765","DOI":"10.5555\/3295222.3295230","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1928394\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T13:43:36Z","timestamp":1788443016000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1928394\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,20]]},"references-count":39,"alternative-id":["10.3389\/fmed.2026.1928394"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1928394","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,20]]},"article-number":"1928394"}}