Machine learning versus logistic regression for the prediction of complications after pancreatoduodenectomy

Aug 2, 2026

Upload by Himbo

Machine learning is increasingly promoted to build postoperative complication prediction models, yet its advantage over logistic regression using structured clinical data remains uncertain. This retrospective observational study used nationwide Dutch Pancreatic Cancer Audit data from 16 centers (Jan 2014–Jan 2021) to compare model performance for postoperative pancreatic fistula and delayed gastric emptying after pancreatoduodenectomy. The study found no meaningful superiority of machine learning over logistic regression for either outcome.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Abstract

Background

Methods

Results

Conclusion

Introduction

EUR Research Information Portal Machine learning versus logistic regression for the prediction of complications after pancreatoduodenectomy Published in: Surgery Publication status and date: Published: 01/09/2023 DOI (link to publisher): 10.1016/j.surg.2023.03.012 Document Version Version created as part of publication process; publisher's layout; not normally made publicly available Document License/Available under: CC BY Citation for the published version (APA): Ingwersen, E. W. , Stam, W. T. , Dutch Pancreatic Cancer Group, Meijs, B. J. V. , Roor, J. , Besselink, M. G. , Groot Koerkamp, B. , de Hingh, I. H. J. T. , van Santvoort, H. C. , Stommel, M. W. J. , & Daams, F. (2023) . Machine learning versus logistic regression for the prediction of complications after pancreatoduodenectomy. Surgery, 174(3), 435-440. [https://doi.org/10.1016/j.surg.2023.03.012](https://doi.org/10.1016/j.surg.2023.03.012) Link to publication on the EUR Research Information Portal Terms and Conditions of Use Except as permitted by the applicable copyright law, you may not reproduce or make this material available to any third party without the prior written permission from the copyright holder(s) . Copyright law allows the following uses of this material without prior permission: • you may download, save and print a copy of this material for your personal use only; • you may share the EUR portal link to this material. In case the material is published with an open access license (e.g. a Creative Commons (CC) license), other uses may be allowed. Please check the terms and conditions of the specific license. Take-down policy If you believe that this material infringes your copyright and/or any other intellectual property rights, you may request its removal by contacting us at the following email address: [openaccess.library@eur.nl. Please](openaccess.library@eur.nl. Please) provide us with all the relevant information, including the reasons why you believe any of your rights have been infringed. In case of a legitimate complaint, we will make the material inaccessible and/or remove it from the website. Surgery xxx (2023) 1e6 Contents lists available at ScienceDirect Surgery journal [homepage: www.elsevier.com/locate/surg](homepage: www.elsevier.com/locate/surg) | Machine learning versus logistic regression for the prediction of complications after pancreatoduodenectomy
Erik W. Ingwersen, MDa,b,c, Wessel T. Stam, MDa,b,c, Bono J.V. Meijs, MDa,b,c, Joran Roor, MScd, Marc G. Besselink, MD, PhDb,c,e, Bas Groot Koerkamp, MD, PhDf, Ignace H.J.T. de Hingh, MD, PhDg, Hjalmar C. van Santvoort, MD, PhDh,
Martijn W.J. Stommel, MD, PhDi, Freek Daams, MD, PhDa,b, *, for the Dutch Pancreatic Cancer Group
a Amsterdam UMC, location Vrije Universiteit Amsterdam, Department of Surgery, Amsterdam, the Netherlands b Cancer Center Amsterdam, the Netherlands
c Amsterdam Gastroenterology Endocrinology and Metabolism, the Netherlands d SAS institute B. V., Huizen, the Netherlands
e Department of Surgery, Amsterdam UMC, University of Amsterdam, the Netherlands f Erasmus MC, University Medical Center Rotterdam, the Netherlands
g Catharina Cancer Institute, the Netherlands h UMC Utrecht Cancer Center, the Netherlands i Radboud University Medical Center, the Netherlands | | | | --- | --- | --- | | a r t i c l e i n f o | | a b s t r a c t | | Article history:
Accepted 20 March 2023 Available online xxx | | Background: Machine learning is increasingly advocated to develop prediction models for postoperative complications. It is, however, unclear if machine learning is superior to logistic regression when using structured clinical data. Postoperative pancreatic ﬁstula and delayed gastric emptying are the two most common complications with the biggest impact on patient condition and length of hospital stay after pancreatoduodenectomy. This study aimed to compare the performance of machine learning and logi

FAQs

What is the main goal of the study?

To compare the performance of machine learning and logistic regression models in predicting postoperative complications after pancreatoduodenectomy, focusing on postoperative pancreatic fistula and delayed gastric emptying.

What data and timeframe were used?

The study used a retrospective observational design with nationwide data from 16 centers in the Dutch Pancreatic Cancer Audit from January 2014 to January 2021.

Did machine learning outperform logistic regression?

No. The study concluded that machine learning did not outperform logistic regression modeling for predicting postoperative complications after pancreatoduodenectomy.

Aug 2, 2026

Upload by Himbo