{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,17]],"date-time":"2026-11-17T11:51:00Z","timestamp":1794916260506,"version":"4.9.1"},"reference-count":38,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"17","license":[{"start":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T00:00:00Z","timestamp":1739404800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Background:<\/jats:title>\n            <jats:p>Postoperative pulmonary complications (PPCs) are major adverse events in neurosurgical patients. This study aimed to develop and validate machine learning models predicting PPCs after neurosurgery.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods:<\/jats:title>\n            <jats:p>PPCs were defined according to the European Perioperative Clinical Outcome standards as occurring within 7 postoperative days. Data of cases meeting inclusion\/exclusion criteria were extracted from the anesthesia information management system to create three datasets: The development (data of Huashan Hospital, Fudan University from 2018 to 2020), temporal validation (data of Huashan Hospital, Fudan University in 2021) and external validation (data of other three hospitals in 2023) datasets. Machine learning models of six algorithms were trained using either 35 retrievable and plausible features or the 11 features selected by Lasso regression. Temporal validation was conducted for all models and the 11-feature models were also externally validated. Independent risk factors were identified and feature importance in top models was analyzed.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results:<\/jats:title>\n            <jats:p>PPCs occurred in 712 of 7533 (9.5%), 258 of 2824 (9.1%), and 207 of 2300 (9.0%) patients in the development, temporal validation and external validation datasets, respectively. During cross-validation training, all models except Bayes demonstrated good discrimination with an area under the receiver operating characteristic curve (AUC) of 0.840. In temporal validation of full-feature models, deep neural network (DNN) performed the best with an AUC of 0.835 (95% confidence interval [CI]: 0.805\u20130.858) and a Brier score of 0.069, followed by Logistic regression (LR), random forest and XGBoost. The 11-feature models performed comparable to full-feature models with very close but statistically significantly lower AUCs, with the top models of DNN and LR in temporal and external validations. An 11-feature nomogram was drawn based on the LR algorithm and it outperformed the minimally modified Assess respiratory RIsk in Surgical patients in CATalonia (ARISCAT) and Laparoscopic Surgery Video Educational Guidelines (LAS VEGAS) scores with a higher AUC (LR: 0.824, ARISCAT: 0.672, LAS: 0.663). Independent risk factors based on multivariate LR mostly overlapped with Lasso-selected features, but lacked consistency with the important features using the Shapley additive explanation (SHAP) method of the LR model.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions:<\/jats:title>\n            <jats:p>The developed models, especially the DNN model and the nomogram, had good discrimination and calibration, and could be used for predicting PPCs in neurosurgical patients. The establishment of machine learning models and the ascertainment of risk factors might assist clinical decision support for improving surgical outcomes.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Trial registration:<\/jats:title>\n            <jats:p>ChiCTR 2100047474; https:\/\/www.chictr.org.cn\/showproj.html?proj=128279.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1097\/cm9.0000000000003433","type":"journal-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T22:00:08Z","timestamp":1739484008000},"page":"2170-2179","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":9,"title":["Development and multicenter validation of machine learning models for predicting postoperative pulmonary complications after neurosurgery"],"prefix":"10.1097","volume":"138","author":[{"given":"Ming","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Anesthesiology, Huashan Hospital, Fudan University, Shanghai 200040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Huashan Hospital, Fudan University, Shanghai 200040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyu","family":"Hou","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Huashan Hospital, Fudan University, Shanghai 200040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongzhi","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai 200040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingwen","family":"Xia","sequence":"additional","affiliation":[{"name":"Department of Respiratory Medicine, Huashan Hospital, Fudan University, Shanghai 200040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liyu","family":"Lin","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Chips and Systems, Fudan University, Shanghai 201203, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, College of Electronic and Information Engineering, Tongji University, Shanghai 201804, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyu","family":"You","sequence":"additional","affiliation":[{"name":"Department of Control Science and Engineering, College of Electronic and Information Engineering, Tongji University, Shanghai 201804, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiafeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Changhai Hospital, Navy Medical University, Shanghai 200433, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Shanghai Neuromedical Center, Shanghai 200331, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohong","family":"Wen","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310003, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Huashan Hospital, Fudan University, Shanghai 200040, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2025,2,13]]},"reference":[{"key":"R1-20250905","first-page":"379","article-title":"Postoperative respiratory disorders","volume":"22","author":"Ball","year":"2016","journal-title":"Curr Opin Crit Care"},{"key":"R2-20250905","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1001\/jamasurg.2016.4065","article-title":"Postoperative pulmonary complications, early mortality, and hospital stay following noncardiothoracic surgery: A multicenter study by the Perioperative Research Network Investigators","volume":"152","author":"Fernandez-Bustamante","year":"2017","journal-title":"JAMA Surg"},{"key":"R3-20250905","doi-asserted-by":"crossref","first-page":"1207","DOI":"10.1378\/chest.11-0466","article-title":"Development and validation of a risk calculator predicting postoperative respiratory failure","volume":"140","author":"Gupta","year":"2011","journal-title":"Chest"},{"key":"R4-20250905","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1093\/bja\/aex002","article-title":"Postoperative pulmonary complications","volume":"118","author":"Miskovic","year":"2017","journal-title":"Br J Anaesth"},{"key":"R5-20250905","doi-asserted-by":"crossref","first-page":"e1147","DOI":"10.1016\/j.wneu.2019.03.058","article-title":"Postoperative pulmonary complications following brain tumor resection: A national database analysis","volume":"126","author":"Longo","year":"2019","journal-title":"World Neurosurg"},{"key":"R6-20250905","doi-asserted-by":"crossref","first-page":"265165","DOI":"10.1155\/2015\/265165","article-title":"Incidence and risk factors of postoperative pulmonary complications in noncardiac Chinese patients: A multicenter observational study in university hospitals","volume":"2015","author":"Jin","year":"2015","journal-title":"Biomed Res Int"},{"key":"R7-20250905","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1097\/ANA.0000000000000756","article-title":"Using the postoperative morbidity survey to measure morbidity after cranial neurosurgery","volume":"34","author":"Luoma","year":"2022","journal-title":"J Neurosurg Anesthesiol"},{"key":"R8-20250905","doi-asserted-by":"crossref","first-page":"736","DOI":"10.3171\/2013.10.JNS122419","article-title":"Frequency and predictors of complications in neurological surgery: National trends from 2006 to 2011","volume":"120","author":"Rolston","year":"2014","journal-title":"J Neurosurg"},{"key":"R9-20250905","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1097\/ACO.0000000000000730","article-title":"Prediction of postoperative pulmonary complications","volume":"32","author":"Nijbroek","year":"2019","journal-title":"Curr Opin Anaesthesiol"},{"key":"R10-20250905","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.jhin.2020.03.015","article-title":"Postoperative pneumonia after craniotomy: Incidence, risk factors and prediction with a nomogram","volume":"105","author":"Zhang","year":"2020","journal-title":"J Hosp Infect"},{"key":"R11-20250905","doi-asserted-by":"crossref","first-page":"1551","DOI":"10.1097\/CM9.0000000000002381","article-title":"Superiority of sugammadex in preventing postoperative pulmonary complications","volume":"136","author":"Liu","year":"2023","journal-title":"Chin Med J"},{"key":"R12-20250905","doi-asserted-by":"crossref","first-page":"1338","DOI":"10.1097\/ALN.0b013e3181fc6e0a","article-title":"Prediction of postoperative pulmonary complications in a population-based surgical cohort","volume":"113","author":"Canet","year":"2010","journal-title":"Anesthesiology"},{"key":"R13-20250905","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1097\/EJA.0000000000000845","article-title":"The LAS VEGAS risk score for prediction of postoperative pulmonary complications: An observational study","volume":"35","author":"Neto","year":"2018","journal-title":"Eur J Anaesthesiol"},{"key":"R14-20250905","doi-asserted-by":"crossref","first-page":"e160","DOI":"10.1016\/j.bja.2021.11.033","article-title":"Postoperative prophylactic intermittent noninvasive ventilation versus usual postoperative care for patients at high risk of pulmonary complications: A multicentre randomised trial","volume":"130","author":"Abrard","year":"2023","journal-title":"Br J Anaesth"},{"key":"R15-20250905","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1097\/ALN.0000000000004159","article-title":"Prophylactic penehyclidine inhalation for prevention of postoperative pulmonary complications in high-risk patients: A double-blind randomized trial","volume":"136","author":"Yan","year":"2022","journal-title":"Anesthesiology"},{"key":"R16-20250905","doi-asserted-by":"crossref","first-page":"e520","DOI":"10.1016\/S2589-7500(22)00069-3","article-title":"Evaluation of prognostic risk models for postoperative pulmonary complications in adult patients undergoing major abdominal surgery: A systematic review and international external validation cohort study","volume":"4","year":"2022","journal-title":"Lancet Digit Health"},{"key":"R17-20250905","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1186\/s13741-021-00214-3","article-title":"Do ARISCAT scores help to predict the incidence of postoperative pulmonary complications in elderly patients after upper abdominal surgery? An observational study at a single university hospital","volume":"10","author":"Nithiuthai","year":"2021","journal-title":"Perioper Med (Lond)"},{"key":"R18-20250905","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1097\/ALN.0b013e31821b5839","article-title":"Derivation and diagnostic accuracy of the surgical lung injury prediction model","volume":"115","author":"Kor","year":"2011","journal-title":"Anesthesiology"},{"key":"R19-20250905","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/S0004-9514(09)70081-9","article-title":"Duration of anaesthesia, type of surgery, respiratory co-morbidity, predicted VO2max and smoking predict postoperative pulmonary complications after upper abdominal surgery: An observational study","volume":"55","author":"Scholes","year":"2009","journal-title":"Aust J Physiother"},{"key":"R20-20250905","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1097\/ALN.0000000000002960","article-title":"Artificial intelligence in anesthesiology: Current techniques, clinical applications, and limitations","volume":"132","author":"Hashimoto","year":"2020","journal-title":"Anesthesiology"},{"key":"R21-20250905","doi-asserted-by":"crossref","first-page":"e212240","DOI":"10.1001\/jamanetworkopen.2021.2240","article-title":"Use of machine learning to develop and evaluate models using preoperative and intraoperative data to identify risks of postoperative complications","volume":"4","author":"Xue","year":"2021","journal-title":"JAMA Netw Open"},{"key":"R22-20250905","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1097\/EJA.0000000000000118","article-title":"Standards for definitions and use of outcome measures for clinical effectiveness research in perioperative medicine: European Perioperative Clinical Outcome (EPCO) definitions: A statement from the ESA-ESICM joint taskforce on perioperative outcome measures","volume":"32","author":"Jammer","year":"2015","journal-title":"Eur J Anaesthesiol"},{"key":"R23-20250905","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1109\/TMI.2016.2538465","article-title":"Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images","volume":"35","author":"Pereira","year":"2016","journal-title":"IEEE Trans Med Imaging"},{"key":"R24-20250905","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1213\/ANE.0b013e318257012b","article-title":"A scoring system to predict unplanned intubation in patients having undergone major surgical procedures","volume":"115","author":"Hua","year":"2012","journal-title":"Anesth Analg"},{"key":"R25-20250905","doi-asserted-by":"crossref","first-page":"1276","DOI":"10.1097\/ALN.0b013e318293065c","article-title":"Development and validation of a score for prediction of postoperative respiratory complications","volume":"118","author":"Brueckmann","year":"2013","journal-title":"Anesthesiology"},{"key":"R26-20250905","doi-asserted-by":"crossref","first-page":"1168","DOI":"10.1097\/ALN.0000000000000216","article-title":"Predicting risk of postoperative lung injury in high-risk surgical patients: A multicenter cohort study","volume":"120","author":"Kor","year":"2014","journal-title":"Anesthesiology"},{"key":"R27-20250905","doi-asserted-by":"crossref","first-page":"848","DOI":"10.1001\/jama.2020.12866","article-title":"Effect of intraoperative low tidal volume vs conventional tidal volume on postoperative pulmonary complications in patients undergoing major surgery: A randomized clinical trial","volume":"324","author":"Karalapillai","year":"2020","journal-title":"JAMA"},{"key":"R28-20250905","doi-asserted-by":"crossref","first-page":"771246","DOI":"10.3389\/fcvm.2021.771246","article-title":"Machine learning for the prediction of complications in patients after mitral valve surgery","volume":"8","author":"Jiang","year":"2021","journal-title":"Front Cardiovasc Med"},{"key":"R29-20250905","doi-asserted-by":"crossref","first-page":"478","DOI":"10.1186\/s13054-020-03179-9","article-title":"Prediction of the development of acute kidney injury following cardiac surgery by machine learning","volume":"24","author":"Tseng","year":"2020","journal-title":"Crit Care"},{"key":"R30-20250905","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.jclinepi.2020.03.002","article-title":"Logistic regression was as good as machine learning for predicting major chronic diseases","volume":"122","author":"Nusinovici","year":"2020","journal-title":"J Clin Epidemiol"},{"key":"R31-20250905","doi-asserted-by":"crossref","first-page":"2485","DOI":"10.1038\/s41598-023-28421-6","article-title":"Logistic regression technique is comparable to complex machine learning algorithms in predicting cognitive impairment related to post intensive care syndrome","volume":"13","author":"Wu","year":"2023","journal-title":"Sci Rep"},{"key":"R32-20250905","article-title":"Calculating the sample size required for developing a clinical prediction model","volume":"368","author":"Riley","year":"2020","journal-title":"BMJ"},{"key":"R33-20250905","doi-asserted-by":"crossref","first-page":"1583","DOI":"10.1056\/NEJMp2000589","article-title":"Prediction models \u2013 Development, evaluation, and clinical application","volume":"382","author":"Pencina","year":"2020","journal-title":"N Engl J Med"},{"key":"R34-20250905","doi-asserted-by":"crossref","first-page":"e074821","DOI":"10.1136\/bmj-2023-074821","article-title":"Evaluation of clinical prediction models (part 3): Calculating the sample size required for an external validation study","volume":"384","author":"Riley","year":"2024","journal-title":"BMJ"},{"key":"R35-20250905","doi-asserted-by":"crossref","first-page":"5774","DOI":"10.3390\/jcm11195774","article-title":"Risk factors for postoperative pulmonary complications leading to increased in-hospital mortality in patients undergoing thoracotomy for primary lung cancer resection: a multicentre retrospective cohort study of the German thorax registry","volume":"11","author":"Baar","year":"2022","journal-title":"J Clin Med"},{"key":"R36-20250905","doi-asserted-by":"crossref","first-page":"932","DOI":"10.3390\/bioengineering10080932","article-title":"Development of a machine learning model of postoperative acute kidney injury using non-invasive time-sensitive intraoperative predictors","volume":"10","author":"Zamirpour","year":"2023","journal-title":"Bioengineering (Basel)"},{"key":"R37-20250905","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1093\/bja\/aex128","article-title":"High intraoperative inspiratory oxygen fraction and risk of major respiratory complications","volume":"119","author":"Staehr-Rye","year":"2017","journal-title":"Br J Anaesth"},{"key":"R38-20250905","doi-asserted-by":"crossref","first-page":"110009","DOI":"10.1016\/j.jclinane.2020.110009","article-title":"Comparison of low and high inspiratory oxygen fraction added to lung-protective ventilation on postoperative pulmonary complications after abdominal surgery: A randomized controlled trial","volume":"67","author":"Li","year":"2020","journal-title":"J Clin Anesth"}],"container-title":["Chinese Medical Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/CM9.0000000000003433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T04:00:34Z","timestamp":1757044834000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/CM9.0000000000003433"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,13]]},"references-count":38,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/cm9.0000000000003433","relation":{},"ISSN":["0366-6999","2542-5641"],"issn-type":[{"value":"0366-6999","type":"print"},{"value":"2542-5641","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,13]]},"assertion":[{"value":"2024-09-13","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}}]}}