{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:43:02Z","timestamp":1773790982607,"version":"3.50.1"},"reference-count":23,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T00:00:00Z","timestamp":1687305600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Oesophagectomy is an operation with a high risk of postoperative complications. The aim of this single-centre retrospective study was to apply machine-learning methods to predict complications (Clavien\u2013Dindo grade IIIa or higher) and specific adverse events.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>Patients with resectable adenocarcinoma or squamous cell carcinoma of the oesophagus and gastro-oesophageal junction who underwent Ivor Lewis oesophagectomy between 2016 and 2021 were included. The tested algorithms were logistic regression after recursive feature elimination, random forest, k-nearest neighbour, support vector machine, and neural network. The algorithms were also compared with a current risk score (the Cologne risk score).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>457 patients had Clavien\u2013Dindo grade IIIa or higher complications (52.9 per cent) versus 407 patients with Clavien\u2013Dindo grade 0, I, or II complications (47.1 per cent). After 3-fold imputation and 3-fold cross-validation, the overall accuracies were: logistic regression after recursive feature elimination, 0.528; random forest, 0.535; k-nearest neighbour, 0.491; support vector machine, 0.511; neural network, 0.688; and Cologne risk score, 0.510. For medical complications, the results were: logistic regression after recursive feature elimination, 0.688; random forest, 0.664; k-nearest neighbour, 0.673; support vector machine, 0.681; neural network, 0.692; and Cologne risk score, 0.650. For surgical complications, the results were: logistic regression after recursive feature elimination, 0.621; random forest, 0.617; k-nearest neighbour, 0.620; support vector machine, 0.634; neural network, 0.667; and Cologne risk score, 0.624. The calculated area under the curve of the neural network was 0.672 for Clavien\u2013Dindo grade IIIa or higher, 0.695 for medical complications, and 0.653 for surgical complications.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>The neural network scored the highest accuracies compared with all of the other models for the prediction of postoperative complications after oesophagectomy.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bjs\/znad181","type":"journal-article","created":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T20:48:59Z","timestamp":1687466939000},"page":"1361-1366","source":"Crossref","is-referenced-by-count":21,"title":["Prediction of postoperative complications after oesophagectomy using machine-learning methods"],"prefix":"10.1093","volume":"110","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6121-0114","authenticated-orcid":false,"given":"Jin-On","family":"Jung","sequence":"first","affiliation":[{"name":"Department of General, Visceral, Tumour, and Transplantation Surgery, University Hospital of Cologne , Cologne , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan I","family":"Pisula","sequence":"additional","affiliation":[{"name":"Centre for Molecular Medicine Cologne (CMMC), Faculty of Medicine and University Hospital of Cologne , Cologne , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kasia","family":"Bozek","sequence":"additional","affiliation":[{"name":"Centre for Molecular Medicine Cologne (CMMC), Faculty of Medicine and University Hospital of Cologne , Cologne , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Popp","sequence":"additional","affiliation":[{"name":"Department of General, Visceral, Tumour, and Transplantation Surgery, University Hospital of Cologne , Cologne , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4764-8050","authenticated-orcid":false,"given":"Hans F","family":"Fuchs","sequence":"additional","affiliation":[{"name":"Department of General, Visceral, Tumour, and Transplantation Surgery, University Hospital of Cologne , Cologne , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wolfgang","family":"Schr\u00f6der","sequence":"additional","affiliation":[{"name":"Department of General, Visceral, Tumour, and Transplantation Surgery, University Hospital of Cologne , Cologne , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christiane J","family":"Bruns","sequence":"additional","affiliation":[{"name":"Department of General, Visceral, Tumour, and Transplantation Surgery, University Hospital of Cologne , Cologne , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7166-3675","authenticated-orcid":false,"given":"Thomas","family":"Schmidt","sequence":"additional","affiliation":[{"name":"Department of General, Visceral, Tumour, and Transplantation Surgery, University Hospital of Cologne , Cologne , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2023,6,21]]},"reference":[{"key":"2023090600095457500_znad181-B1","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1001\/jamasurg.2021.2376","article-title":"Risk prediction model of 90-day mortality after esophagectomy for cancer","volume":"156","author":"D\u2019Journo","year":"2021","journal-title":"JAMA Surg"},{"key":"2023090600095457500_znad181-B2","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1056\/NEJMoa1805101","article-title":"Hybrid minimally invasive esophagectomy for esophageal cancer","volume":"380","author":"Mariette","year":"2019","journal-title":"N Engl J Med"},{"key":"2023090600095457500_znad181-B3","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1097\/01.sla.0000133083.54934.ae","article-title":"Classification of surgical complications: a new proposal with evaluation in a cohort of 6336 patients and results of a survey","volume":"240","author":"Dindo","year":"2004","journal-title":"Ann Surg"},{"key":"2023090600095457500_znad181-B4","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1097\/SLA.0000000000001098","article-title":"International consensus on standardization of data collection for complications associated with esophagectomy: Esophagectomy Complications Consensus Group (ECCG)","volume":"262","author":"Low","year":"2015","journal-title":"Ann Surg"},{"key":"2023090600095457500_znad181-B5","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1016\/j.jss.2018.06.034","article-title":"Missing data in surgical data sets: a review of pertinent issues and solutions","volume":"232","author":"Sharath","year":"2018","journal-title":"J Surg Res"},{"key":"2023090600095457500_znad181-B6","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1001\/jamasurg.2020.4991","article-title":"Same data, opposite results?: a call to improve surgical database research","volume":"156","author":"Childers","year":"2021","journal-title":"JAMA Surg"},{"key":"2023090600095457500_znad181-B7","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.jss.2021.02.045","article-title":"Machine learning and surgical outcomes prediction: a systematic review","volume":"264","author":"Elfanagely","year":"2021","journal-title":"J Surg Res"},{"key":"2023090600095457500_znad181-B8","doi-asserted-by":"crossref","first-page":"748","DOI":"10.3390\/jpm11080748","article-title":"Application of machine learning for predicting anastomotic leakage in patients with gastric adenocarcinoma who received total or proximal gastrectomy","volume":"11","author":"Shao","year":"2021","journal-title":"J Pers Med"},{"key":"2023090600095457500_znad181-B9","doi-asserted-by":"crossref","first-page":"e27110","DOI":"10.2196\/27110","article-title":"Prediction model of anastomotic leakage among esophageal cancer patients after receiving an esophagectomy: machine learning approach","volume":"9","author":"Zhao","year":"2021","journal-title":"JMIR Med Inform"},{"key":"2023090600095457500_znad181-B10","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2023090600095457500_znad181-B11","volume-title":"Python 3 Reference Manual","author":"Van Rossum","year":"2009"},{"key":"2023090600095457500_znad181-B12","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1007\/s00423-006-0067-z","article-title":"Preoperative risk analysis\u2014a reliable predictor of postoperative outcome after transthoracic esophagectomy?","volume":"391","author":"Schr\u00f6der","year":"2006","journal-title":"Langenbecks Arch Surg"},{"key":"2023090600095457500_znad181-B13","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2023090600095457500_znad181-B14","doi-asserted-by":"crossref","first-page":"238","DOI":"10.2307\/1403797","article-title":"Discriminatory analysis. Nonparametric discrimination: consistency properties","volume":"57","author":"Fix","year":"1989","journal-title":"Int Stat Rev"},{"key":"2023090600095457500_znad181-B15","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1038\/nbt1206-1565","article-title":"What is a support vector machine?","volume":"24","author":"Noble","year":"2006","journal-title":"Nat Biotechnol"},{"key":"2023090600095457500_znad181-B16","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1038\/nbt1386","article-title":"What are artificial neural networks?","volume":"26","author":"Krogh","year":"2008","journal-title":"Nat Biotechnol"},{"key":"2023090600095457500_znad181-B17","doi-asserted-by":"crossref","first-page":"5450","DOI":"10.3390\/jcm10225450","article-title":"An automated system for ECG arrhythmia detection using machine learning techniques","volume":"10","author":"Sraitih","year":"2021","journal-title":"J Clin Med"},{"key":"2023090600095457500_znad181-B18","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1097\/MCC.0000000000000445","article-title":"How to better identify patients at high risk of postoperative complications?","volume":"23","author":"Talmor","year":"2017","journal-title":"Curr Opin Crit Care"},{"key":"2023090600095457500_znad181-B19","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1097\/MCC.0000000000000556","article-title":"Who is a high-risk surgical patient?","volume":"24","author":"Bose","year":"2018","journal-title":"Curr Opin Crit Care"},{"key":"2023090600095457500_znad181-B20","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1097\/CCM.0000000000002943","article-title":"Rare events in the ICU: an emerging challenge in classification and prediction","volume":"46","author":"Leisman","year":"2018","journal-title":"Crit Care Med"},{"key":"2023090600095457500_znad181-B21","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.1007\/s00432-022-04063-5","article-title":"Machine learning for optimized individual survival prediction in resectable upper gastrointestinal cancer","volume":"149","author":"Jung","year":"2022","journal-title":"J Cancer Res Clin Oncol"},{"key":"2023090600095457500_znad181-B22","doi-asserted-by":"crossref","first-page":"995","DOI":"10.1007\/s00595-021-02380-9","article-title":"Machine learning in gastrointestinal surgery","volume":"52","author":"Sakamoto","year":"2022","journal-title":"Surg Today"},{"key":"2023090600095457500_znad181-B23","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 Anesthesiol"}],"container-title":["British Journal of Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bjs\/article-pdf\/110\/10\/1361\/51360371\/znad181.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bjs\/article-pdf\/110\/10\/1361\/51360371\/znad181.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,6]],"date-time":"2023-09-06T00:11:20Z","timestamp":1693959080000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bjs\/article\/110\/10\/1361\/7204669"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,21]]},"references-count":23,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2023,6,21]]},"published-print":{"date-parts":[[2023,9,6]]}},"URL":"https:\/\/doi.org\/10.1093\/bjs\/znad181","relation":{},"ISSN":["0007-1323","1365-2168"],"issn-type":[{"value":"0007-1323","type":"print"},{"value":"1365-2168","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,10]]},"published":{"date-parts":[[2023,6,21]]}}}