Conventional regression analysis and machine learning in prediction of anastomotic leakage and pulmonary complications after esophagogastric cancer surgery
Open Access
- 3 May 2022
- journal article
- research article
- Published by Wiley in Journal of Surgical Oncology
- Vol. 126 (3) , 490-501
Abstract
Background and Objectives: With the current advanced data‐driven approach to health care, machine learning is gaining more interest. The current study investigates the added value of machine learning to linear regression in predicting anastomotic leakage and pulmonary complications after upper gastrointestinal cancer surgery.Methods: All patients in the Dutch Upper Gastrointestinal Cancer Audit undergoing curatively intended esophageal or gastric cancer surgeries from 2011 to 2017 were included. Anastomotic leakage was defined as any clinically or radiologically proven anastomotic leakage. Pulmonary complications entailed: pneumonia, pleural effusion, respiratory failure, pneumothorax, and/or acute respiratory distress syndrome. Different machine learning models were tested. Nomograms were constructed using Least Absolute Shrinkage and Selection Operator.Results: Between 2011 and 2017, 4228 patients underwent surgical resection for esophageal cancer, of which 18% developed anastomotic leakage and 30% a pulmonary complication. Of the 2199 patients with surgical resection for gastric cancer, 7% developed anastomotic leakage and 15% a pulmonary complication. In all cases, linear regression had the highest predictive value with the area under the curves varying between 61.9 and 68.0, but the difference with machine learning models did not reach statistical significance.Conclusion: Machine learning models can predict postoperative complications in upper gastrointestinal cancer surgery, but they do not outperform the current gold standard, linear regressionKeywords
This publication has 39 references indexed in Scilit:
- Major perioperative complications in laparoscopic spleen-preserving total gastrectomy for gastric cancer: perspectives from a high-volume centerSurgical Endoscopy, 2015
- Calcification of Arteries Supplying the Gastric Tube: A New Risk Factor for Anastomotic Leakage after Esophageal SurgeryRadiology, 2015
- Preoperative alcohol cessation prior to elective surgeryCochrane Database of Systematic Reviews, 2012
- Prediction of major postoperative complications and survival for locally advanced esophageal carcinoma patientsAsian Journal of Surgery, 2012
- The quality of cancer care initiative in the NetherlandsEuropean Journal of Surgical Oncology, 2010
- Intraoperative Transfusion of 1 U to 2 U Packed Red Blood Cells Is Associated with Increased 30-Day Mortality, Surgical-Site Infection, Pneumonia, and Sepsis in General Surgery PatientsJournal of the American College of Surgeons, 2009
- Trends in Management and Prognosis for Esophageal Cancer SurgeryArchives of Surgery, 2009
- Preoperative Prediction of the Occurrence and Severity of Complications After Esophagectomy for Cancer With Use of a NomogramThe Annals of Thoracic Surgery, 2008
- Postoperative Mortality After Esophagectomy for Cancer: Development of a Preoperative Risk Prediction ModelAnnals of Surgical Oncology, 2008
- Preoperative risk analysis and postoperative mortality of oesophagectomy for resectable oesophageal cancerBritish Journal of Surgery, 1998