{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:12:48Z","timestamp":1788307968668,"version":"build-2803163510"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:00:00Z","timestamp":1788307200000},"content-version":"vor","delay-in-days":72,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the Wu Jieping Medical Foundation","award":["320.6750.2024-15-72"],"award-info":[{"award-number":["320.6750.2024-15-72"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cardiovasc Diabetol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Postoperative hypotension (POH) is a common and serious complication in patients with type 2 diabetes mellitus (T2DM) undergoing non\u2011cardiac surgery, yet predictive tools tailored to this high\u2011risk population remain scarce.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This single\u2011center cohort study developed and validated a machine learning (ML) model to predict the risk of postoperative hypotension (POH) occurring during the post\u2011anaesthesia care unit (PACU) stay, defined as systolic blood pressure\u2009&lt;\u200990 mmHg after leaving the operating theatre and before transfer to the general ward, consistent with the Perioperative Quality Initiative (POQI) consensus. Data from 34,012 retrospective (2012\u20132022) and 10,528 prospective (2023\u20132025) T2DM patients undergoing non\u2011cardiac surgery were used. Following rigorous preprocessing and a four\u2011step feature selection, 13 predictors were retained. Fourteen ML models were trained and evaluated using area under the curve (AUC), sensitivity, specificity, and calibration. Model interpretability was enhanced using SHapley Additive exPlanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Random Forest achieved the best overall performance, with AUCs of 0.843 (95% CI 0.837\u20130.849) on training, 0.854 (95% CI 0.848\u20130.860) on internal validation, and 0.847 (95% CI 0.840\u20130.854) on prospective validation. External validation on an independent hospital cohort (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u20092156) yielded an AUC of 0.822 (95% CI 0.805\u20130.839), confirming generalisability. It demonstrated high sensitivity (0.932) and reliable calibration. SHAP analysis identified intraoperative blood loss, age, heart failure, obstructive sleep apnoea, and body mass index as the top predictors, providing transparent global and local explanations for individual risk.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An interpretable ML model based on routinely collected clinical data accurately predicts POH risk in T2DM patients after non\u2011cardiac surgery. The model combines strong discriminative performance with clinical explainability, suggesting its potential as a practical tool for preoperative risk stratification and personalized postoperative monitoring in T2DM patients within similar clinical settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12933-026-03256-3","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T01:35:01Z","timestamp":1782092101000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An interpretable machine learning model for predicting postoperative hypotension in type 2 diabetes mellitus undergoing non\u2011cardiac surgery"],"prefix":"10.1186","volume":"25","author":[{"given":"Yu","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guojiang","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyang","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"issue":"12","key":"3256_CR1","doi-asserted-by":"publisher","first-page":"1155","DOI":"10.1056\/NEJMoa2412006","volume":"392","author":"Y Bi","year":"2025","unstructured":"Bi Y, Li M, Liu Y, Li T, Lu J, Duan P, et al. Intensive blood-pressure control in patients with type 2 diabetes. N Engl J Med. 2025;392(12):1155\u201367.","journal-title":"N Engl J Med"},{"issue":"5","key":"3256_CR2","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1016\/j.bja.2019.01.019","volume":"122","author":"MD McEvoy","year":"2019","unstructured":"McEvoy MD, Gupta R, Koepke EJ, Feldheiser A, Michard F, Levett D, et al. Perioperative Quality Initiative consensus statement on postoperative blood pressure, risk and outcomes for elective surgery. Br J Anaesth. 2019;122(5):575\u201386.","journal-title":"Br J Anaesth"},{"key":"3256_CR3","doi-asserted-by":"publisher","first-page":"102955","DOI":"10.1016\/j.arr.2025.102955","volume":"113","author":"D Xenos","year":"2026","unstructured":"Xenos D, Mancinetti F, Mecocci P, Boccardi V. The muscle-brain axis in type 2 diabetes: molecular pathways linking sarcopenia and cognitive decline. Ageing Res Rev. 2026;113:102955.","journal-title":"Ageing Res Rev"},{"issue":"2","key":"3256_CR4","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1097\/ALN.0000000000001985","volume":"128","author":"DI Sessler","year":"2018","unstructured":"Sessler DI, Meyhoff CS, Zimmerman NM, Mao G, Leslie K, V\u00e1squez SM, et al. Period-dependent associations between hypotension during and for four days after noncardiac surgery and a composite of myocardial infarction and death: a substudy of the POISE-2 Trial. Anesthesiology. 2018;128(2):317\u201327.","journal-title":"Anesthesiology"},{"issue":"11","key":"3256_CR5","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.1001\/jama.297.11.1197","volume":"297","author":"PG Steg","year":"2007","unstructured":"Steg PG, Bhatt DL, Wilson PW, D\u2019Agostino R, Sr., Ohman EM, R\u00f6ther J, et al. One-year cardiovascular event rates in outpatients with atherothrombosis. JAMA. 2007;297(11):1197\u2013206.","journal-title":"JAMA"},{"issue":"17","key":"3256_CR6","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1056\/NEJMoa1001286","volume":"362","author":"WC Cushman","year":"2010","unstructured":"Cushman WC, Evans GW, Byington RP, Goff DC Jr., Grimm RH Jr., Cutler JA, et al. Effects of intensive blood-pressure control in type 2 diabetes mellitus. N Engl J Med. 2010;362(17):1575\u201385.","journal-title":"N Engl J Med"},{"issue":"2","key":"3256_CR7","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/j.bja.2023.02.029","volume":"131","author":"F Michard","year":"2023","unstructured":"Michard F, Futier E. Predicting intraoperative hypotension: from hope to hype and back to reality. Br J Anaesth. 2023;131(2):199\u2013201.","journal-title":"Br J Anaesth"},{"issue":"1","key":"3256_CR8","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1213\/ANE.0000000000007216","volume":"141","author":"R Mukkamala","year":"2025","unstructured":"Mukkamala R, Schnetz MP, Khanna AK, Mahajan A. Intraoperative hypotension prediction: current methods, controversies, and research outlook. Anesth Analg. 2025;141(1):61\u201373.","journal-title":"Anesth Analg"},{"issue":"1","key":"3256_CR9","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1186\/s12871-021-01496-2","volume":"21","author":"SY Chu","year":"2021","unstructured":"Chu SY, Li PW, Fan FF, Han XN, Liu L, Wang J, et al. Combining CHA(2)DS(2)-VASc score into RCRI for prediction perioperative cardiovascular outcomes in patients undergoing non-cardiac surgery: a retrospective pilot study. BMC Anesthesiol. 2021;21(1):276.","journal-title":"BMC Anesthesiol"},{"issue":"5","key":"3256_CR10","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1111\/jdi.70004","volume":"16","author":"PW Hsu","year":"2025","unstructured":"Hsu PW, Chen YR, Sheu WH. MetS-Z: A gender- and age-specific scoring system for predicting type 2 diabetes. J Diabetes Investig. 2025;16(5):907\u201316.","journal-title":"J Diabetes Investig"},{"issue":"5","key":"3256_CR11","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1016\/j.jemermed.2022.09.032","volume":"63","author":"RR Ehrman","year":"2022","unstructured":"Ehrman RR, Kline JA. Primer on logistic regression for emergency care researchers. J Emerg Med. 2022;63(5):683\u201391.","journal-title":"J Emerg Med"},{"issue":"4","key":"3256_CR12","doi-asserted-by":"publisher","first-page":"2080","DOI":"10.3758\/s13428-022-01880-x","volume":"55","author":"D Tu","year":"2023","unstructured":"Tu D, Chiu J, Ma W, Wang D, Cai Y, Ouyang X. A multiple logistic regression-based (MLR-B) Q-matrix validation method for cognitive diagnosis models: a confirmatory approach. Behav Res Methods. 2023;55(4):2080\u201392.","journal-title":"Behav Res Methods"},{"key":"3256_CR13","doi-asserted-by":"publisher","first-page":"e082104","DOI":"10.1136\/bmj-2024-082104","volume":"388","author":"J Han","year":"2025","unstructured":"Han J, Zhai W, Wu Z, Zhang Z, Wang T, Ren M, et al. Care guided by tissue oxygenation and haemodynamic monitoring in off-pump coronary artery bypass grafting (Bottomline-CS): assessor blind, single centre, randomised controlled trial. BMJ. 2025;388:e082104.","journal-title":"BMJ"},{"issue":"1","key":"3256_CR14","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1038\/s41580-021-00407-0","volume":"23","author":"JG Greener","year":"2022","unstructured":"Greener JG, Kandathil SM, Moffat L, Jones DT. A guide to machine learning for biologists. Nat Rev Mol Cell Biol. 2022;23(1):40\u201355.","journal-title":"Nat Rev Mol Cell Biol"},{"issue":"11","key":"3256_CR15","doi-asserted-by":"publisher","first-page":"1052","DOI":"10.1001\/jama.2020.0592","volume":"323","author":"M Wijnberge","year":"2020","unstructured":"Wijnberge M, Geerts BF, Hol L, Lemmers N, Mulder MP, Berge P, et al. Effect of a machine learning-derived early warning system for intraoperative hypotension vs standard care on depth and duration of intraoperative hypotension during elective noncardiac surgery: the HYPE randomized clinical trial. JAMA. 2020;323(11):1052\u201360.","journal-title":"JAMA"},{"issue":"3","key":"3256_CR16","doi-asserted-by":"publisher","first-page":"198","DOI":"10.5455\/msm.2024.236-239","volume":"78","author":"QA Almulihi","year":"2024","unstructured":"Almulihi QA, Alquraini AA, Almulihi FAA, Alzahid AA, Al Qahtani S, Almulhim M, et al. Applications of artificial intelligence and machine learning in emergency medicine triage - a systematic review. Med Arch. 2024;78(3):198\u2013206.","journal-title":"Med Arch"},{"key":"3256_CR17","doi-asserted-by":"publisher","first-page":"110495","DOI":"10.1016\/j.jclinane.2021.110495","volume":"75","author":"T Shimada","year":"2021","unstructured":"Shimada T, Cohen B, Shah K, Mosteller L, Bravo M, Ince I, et al. Associations between intraoperative and post-anesthesia care unit hypotension and surgical ward hypotension. J Clin Anesth. 2021;75:110495.","journal-title":"J Clin Anesth"},{"key":"3256_CR18","doi-asserted-by":"publisher","first-page":"103470","DOI":"10.1016\/j.redox.2024.103470","volume":"79","author":"X Qi","year":"2025","unstructured":"Qi X, Wang S, Fang C, Jia J, Lin L, Yuan T. Machine learning and SHAP value interpretation for predicting comorbidity of cardiovascular disease and cancer with dietary antioxidants. Redox Biol. 2025;79:103470.","journal-title":"Redox Biol"},{"issue":"11","key":"3256_CR19","doi-asserted-by":"publisher","first-page":"e70056","DOI":"10.1111\/cts.70056","volume":"17","author":"AV Ponce-Bobadilla","year":"2024","unstructured":"Ponce-Bobadilla AV, Schmitt V, Maier CS, Mensing S, Stodtmann S. Practical guide to SHAP analysis: explaining supervised machine learning model predictions in drug development. Clin Transl Sci. 2024;17(11):e70056.","journal-title":"Clin Transl Sci"},{"issue":"6","key":"3256_CR20","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1536\/ihj.16-624","volume":"58","author":"M Nakahigashi","year":"2017","unstructured":"Nakahigashi M, Tsukaguchi H, Morimoto S, Nakano C, Ueda H, Someya K, et al. Determinants of the change in arterial stiffness in peritoneal dialysis patients. Int Heart J. 2017;58(6):915\u201325.","journal-title":"Int Heart J"},{"issue":"2","key":"3256_CR21","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1536\/ihj.18-455","volume":"60","author":"M Sakamoto","year":"2019","unstructured":"Sakamoto M, Matsutani D, Kayama Y. Clinical implications of baroreflex sensitivity in type 2 diabetes. Int Heart J. 2019;60(2):241\u20136.","journal-title":"Int Heart J"},{"issue":"5","key":"3256_CR22","doi-asserted-by":"publisher","first-page":"2077","DOI":"10.1007\/s11845-021-02825-7","volume":"191","author":"E Jorge-Galarza","year":"2022","unstructured":"Jorge-Galarza E, Torres-Tamayo M, Mart\u00ednez-Alvarado MDR, Pe\u00f1a-Aparicio B, Gonz\u00e1lez-Salazar C, Reyes-Barrera J, et al. Cardiovascular autonomic responses during head-up tilt test in newly diagnosed type 2 diabetes. Ir J Med Sci. 2022;191(5):2077\u201384.","journal-title":"Ir J Med Sci"},{"issue":"5","key":"3256_CR23","doi-asserted-by":"publisher","first-page":"1420","DOI":"10.1161\/ATVBAHA.120.314102","volume":"40","author":"D Cseh","year":"2020","unstructured":"Cseh D, Climie RE, Offredo L, Guibout C, Thomas F, Zanoli L, et al. Type 2 diabetes mellitus is independently associated with decreased neural baroreflex sensitivity: the Paris prospective study III. Arterioscler Thromb Vasc Biol. 2020;40(5):1420\u20138.","journal-title":"Arterioscler Thromb Vasc Biol"},{"issue":"1","key":"3256_CR24","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1186\/s12933-018-0743-7","volume":"17","author":"D Matsutani","year":"2018","unstructured":"Matsutani D, Sakamoto M, Minato S, Kayama Y, Takeda N, Horiuchi R, et al. Visit-to-visit HbA1c variability is inversely related to baroreflex sensitivity independently of HbA1c value in type 2 diabetes. Cardiovasc Diabetol. 2018;17(1):100.","journal-title":"Cardiovasc Diabetol"},{"issue":"1","key":"3256_CR25","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1213\/ANE.0000000000007216","volume":"141","author":"R Mukkamala","year":"2025","unstructured":"Mukkamala R, Schnetz MP, Khanna AK, et al. Intraoperative hypotension prediction: current methods, controversies, and research outlook. Anesth Analg. 2025;141(1):61\u201373.","journal-title":"Anesth Analg"},{"issue":"2","key":"3256_CR26","doi-asserted-by":"publisher","first-page":"3508","DOI":"10.1097\/JS9.0000000000003968","volume":"112","author":"Q Cui","year":"2026","unstructured":"Cui Q, Zhang L, Wang Y, et al. The association between preoperative baroreflex sensitivity and post-induction hypotension in elderly patients: a prospective cohort study. Int J Surg. 2026;112(2):3508\u201318.","journal-title":"Int J Surg"},{"issue":"1","key":"3256_CR27","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1186\/s12872-024-03844-9","volume":"24","author":"B Shan","year":"2024","unstructured":"Shan B, Li X, Chen J, et al. Predictive value of estimated plasma volume for postoperative hypotension in percutaneous intramyocardial septal radiofrequency ablation treating for hypertrophic obstructive cardiomyopathy. BMC Cardiovasc Disord. 2024;24(1):156.","journal-title":"BMC Cardiovasc Disord"},{"issue":"4","key":"3256_CR28","doi-asserted-by":"publisher","first-page":"179","DOI":"10.17245\/jdapm.2023.23.4.179","volume":"23","author":"E Bae","year":"2023","unstructured":"Bae E, Kim S, Park J, et al. Preoperative risk evaluation and perioperative management of patients with obstructive sleep apnea: a narrative review. J Dent Anesth Pain Med. 2023;23(4):179\u201392.","journal-title":"J Dent Anesth Pain Med"},{"issue":"3","key":"3256_CR29","doi-asserted-by":"publisher","first-page":"204","DOI":"10.2174\/157339907781368931","volume":"3","author":"RE Maser","year":"2007","unstructured":"Maser RE, Lenhard MJ, DeCherney GS, et al. An overview of the effect of weight loss on cardiovascular autonomic function. Curr Diabetes Rev. 2007;3(3):204\u201311.","journal-title":"Curr Diabetes Rev"}],"container-title":["Cardiovascular Diabetology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12933-026-03256-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12933-026-03256-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12933-026-03256-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T23:16:42Z","timestamp":1788304602000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12933-026-03256-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["3256"],"URL":"https:\/\/doi.org\/10.1186\/s12933-026-03256-3","relation":{},"ISSN":["1475-2840"],"issn-type":[{"value":"1475-2840","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"28 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study was approved by the Ethics Committee of the General Hospital of Central Theater Command of People\u2018s Liberation Army. The requirement for written informed consent was waived due to the retrospective and prospective observational design.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. (This manuscript does not contain any individual person\u2019s data in any form.)","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"265"}}