{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T11:52:07Z","timestamp":1790941927314,"version":"4.1.0"},"reference-count":27,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2024,2,17]],"date-time":"2024-02-17T00:00:00Z","timestamp":1708128000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Pioneers in Health Care Innovation Fund, University of Twente"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Esophageal cancer can be treated effectively with esophagectomy; however, the postoperative complication rate is high. In this paper, we study to what extent machine learning methods can predict anastomotic leakage and pneumonia up to two days in advance. We use a dataset with 417 patients who underwent esophagectomy between 2011 and 2021. The dataset contains multimodal temporal information, specifically, laboratory results, vital signs, thorax images, and preoperative patient characteristics. The best models scored mean test set AUROCs of 0.87 and 0.82 for leakage 1 and 2 days ahead, respectively. For pneumonia, this was 0.74 and 0.61 for 1 and 2 days ahead, respectively. We conclude that machine learning models can effectively predict anastomotic leakage and pneumonia after esophagectomy.<\/jats:p>","DOI":"10.3390\/diagnostics14040439","type":"journal-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T04:36:22Z","timestamp":1708403782000},"page":"439","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Complication Prediction after Esophagectomy with Machine Learning"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6220-0508","authenticated-orcid":false,"given":"Jorn-Jan","family":"van de Beld","sequence":"first","affiliation":[{"name":"Faculty of EEMCS, University of Twente, 7500 AE Enschede, The Netherlands"},{"name":"Hospital Group Twente (ZGT), 7609 PP Almelo, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2086-2065","authenticated-orcid":false,"given":"David","family":"Crull","sequence":"additional","affiliation":[{"name":"Hospital Group Twente (ZGT), 7609 PP Almelo, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3229-685X","authenticated-orcid":false,"given":"Julia","family":"Mikhal","sequence":"additional","affiliation":[{"name":"Hospital Group Twente (ZGT), 7609 PP Almelo, The Netherlands"},{"name":"Faculty of BMS, University of Twente, 7500 AE Enschede, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6718-6653","authenticated-orcid":false,"given":"Jeroen","family":"Geerdink","sequence":"additional","affiliation":[{"name":"Hospital Group Twente (ZGT), 7609 PP Almelo, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8023-9717","authenticated-orcid":false,"given":"Anouk","family":"Veldhuis","sequence":"additional","affiliation":[{"name":"Hospital Group Twente (ZGT), 7609 PP Almelo, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3813-9732","authenticated-orcid":false,"given":"Mannes","family":"Poel","sequence":"additional","affiliation":[{"name":"Faculty of EEMCS, University of Twente, 7500 AE Enschede, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8986-9076","authenticated-orcid":false,"given":"Ewout A.","family":"Kouwenhoven","sequence":"additional","affiliation":[{"name":"Hospital Group Twente (ZGT), 7609 PP Almelo, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,2,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","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":"ref_3","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.1016\/S0140-6736(12)60516-9","article-title":"Minimally invasive versus open oesophagectomy for patients with oesophageal cancer: A multicentre, open-label, randomised controlled trial","volume":"379","author":"Biere","year":"2012","journal-title":"Lancet"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.1097\/SLA.0000000000003210","article-title":"Reporting National Outcomes After Esophagectomy and Gastrectomy According to the Esophageal Complications Consensus Group (ECCG)","volume":"271","author":"Busweiler","year":"2020","journal-title":"Ann. Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1097\/SLA.0000000000002611","article-title":"Benchmarking Complications Associated with Esophagectomy","volume":"269","author":"Low","year":"2019","journal-title":"Ann. Surg."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","article-title":"AI in health and medicine","volume":"28","author":"Rajpurkar","year":"2022","journal-title":"Nat. Med."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Stokes, K., Castaldo, R., Federici, C., Pagliara, S., Maccaro, A., Cappuccio, F., Fico, G., Salvatore, M., Franzese, M., and Pecchia, L. (2022). The use of artificial intelligence systems in diagnosis of pneumonia via signs and symptoms: A systematic review. Biomed. Signal Process. Control, 72.","DOI":"10.1016\/j.bspc.2021.103325"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1097\/01.sla.0000143123.24556.1c","article-title":"Predictive Factors for Postoperative Pulmonary Complications and Mortality After Esophagectomy for Cancer","volume":"240","author":"Law","year":"2004","journal-title":"Ann. Surg."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1938","DOI":"10.1016\/j.athoracsur.2008.03.014","article-title":"Preoperative Prediction of the Occurrence and Severity of Complications After Esophagectomy for Cancer with Use of a Nomogram","volume":"85","author":"Lagarde","year":"2008","journal-title":"Ann. Thorac. Surg."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1577","DOI":"10.1245\/s10434-008-9867-4","article-title":"Postoperative Mortality After Esophagectomy for Cancer: Development of a Preoperative Risk Prediction Model","volume":"15","author":"Ra","year":"2008","journal-title":"Ann. Surg. Oncol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1007\/s00464-022-09516-z","article-title":"Machine learning applications in upper gastrointestinal cancer surgery: A systematic review","volume":"37","author":"Burchell","year":"2023","journal-title":"Surg. Endosc."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1111\/1759-7714.12990","article-title":"C-reactive protein to albumin ratio is a key indicator in a predictive model for anastomosis leakage after esophagectomy: Application of classification and regression tree analysis","volume":"10","author":"Shao","year":"2019","journal-title":"Thorac. Cancer"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.12669\/pjms.39.5.8050","article-title":"Prediction model using risk factors associated with anastomotic leakage after minimally invasive esophagectomy","volume":"39","author":"Su","year":"2023","journal-title":"Pak. J. Med. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.amsu.2020.05.011","article-title":"Risk factors and therapeutic measures for postoperative complications associated with esophagectomy","volume":"55","author":"Ahmadinejad","year":"2020","journal-title":"Ann. Med. Surg."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1159\/000357350","article-title":"A new clinical scoring system to define pneumonia following esophagectomy for cancer","volume":"31","author":"Verhage","year":"2014","journal-title":"Dig. Surg."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Aiolfi, A., Asti, E., Rausa, E., Bonavina, G., Bonitta, G., and Bonavina, L. (2018). Use of C-reactive protein for the early prediction of anastomotic leak after esophagectomy: Systematic review and Bayesian meta-analysis. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0209272"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"9118","DOI":"10.3748\/wjg.v21.i30.9118","article-title":"Diagnostic value of drain amylase for detecting intrathoracic leakage after esophagectomy","volume":"21","author":"Berkelmans","year":"2015","journal-title":"World J. Gastroenterol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1494","DOI":"10.1016\/j.athoracsur.2010.12.036","article-title":"Prediction of Major Pulmonary Complications After Esophagectomy","volume":"91","author":"Ferguson","year":"2011","journal-title":"Ann. Thorac. Surg."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1981","DOI":"10.1056\/NEJMra2301725","article-title":"The Current and Future State of AI Interpretation of Medical Images","volume":"388","author":"Rajpurkar","year":"2023","journal-title":"N. Engl. J. Med."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_21","doi-asserted-by":"crossref","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":"ref_22","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1038\/s41746-022-00712-8","article-title":"Multimodal machine learning in precision health: A scoping review","volume":"5","author":"Kline","year":"2022","journal-title":"NPJ Digit. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1038\/s41746-020-00341-z","article-title":"Fusion of medical imaging and electronic health records using deep learning: A systematic review and implementation guidelines","volume":"3","author":"Huang","year":"2020","journal-title":"NPJ Digit. Med."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1002\/jso.26910","article-title":"Conventional regression analysis and machine learning in prediction of anastomotic leakage and pulmonary complications after esophagogastric cancer surgery","volume":"126","author":"Bahadoer","year":"2022","journal-title":"J. Surg. Oncol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"8144","DOI":"10.1007\/s00464-022-09249-z","article-title":"A novel nomogram predicting the risk of postoperative pneumonia for esophageal cancer patients after minimally invasive esophagectomy","volume":"36","author":"Jin","year":"2022","journal-title":"Surg. Endosc."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1038\/s41551-023-01045-x","article-title":"A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics","volume":"7","author":"Zhou","year":"2023","journal-title":"Nat. Biomed. Eng."},{"key":"ref_27","unstructured":"Liu, K., Li, Y., Xu, N., and Natarajan, P. (2018). Learn to Combine Modalities in Multimodal Deep Learning. arXiv."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/14\/4\/439\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:01:00Z","timestamp":1760104860000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/14\/4\/439"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,17]]},"references-count":27,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["diagnostics14040439"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics14040439","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,17]]}}}