Machine learning-based preoperative analytics for the prediction of anastomotic leakage in colorectal surgery: a swiss pilot study

Machine learning-based preoperative analytics for the prediction of anastomotic leakage in colorectal surgery: a swiss pilot study

Background Anastomotic leakage (AL), a severe complication following colorectal surgery, arises from defects at the anastomosis site. This study evaluates the feasibility of predicting AL using machine learning (ML) algorithms based on preoperative data. Methods We retrospectively analyzed data incl...

Full description

Saved in:
Bibliographic Details
Published in:Surgical endoscopy Vol. 38; no. 7; pp. 3672 - 3683
Main Authors: Taha-Mehlitz, Stephanie, Wentzler, Larissa, Angehrn, Fiorenzo, Hendie, Ahmad, Ochs, Vincent, Wolleb, Julia, Staartjes, Victor E., Enodien, Bassey, Baltuonis, Martinas, Vorburger, Stephan, Frey, Daniel M., Rosenberg, Robert, von Flüe, Markus, Müller-Stich, Beat, Cattin, Philippe C., Taha, Anas, Steinemann, Daniel
Format: Journal Article
Language:English
Published: New York Springer US 01-07-2024
Springer Nature B.V
Subjects:
Abdominal Surgery
Algorithms
Colorectal surgery
Gastroenterology
Gynecology
Hepatology
Machine learning
Medicine
Medicine & Public Health
Pilot projects
Proctology
Regression analysis
Surgery
Surgical anastomosis
Surgical outcomes
Prediction of anastomotic leakage
Anastomotic leakage
Anastomotic insufficiency
Colorectal surgery
Prediction tool
Machine learning
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background Anastomotic leakage (AL), a severe complication following colorectal surgery, arises from defects at the anastomosis site. This study evaluates the feasibility of predicting AL using machine learning (ML) algorithms based on preoperative data. Methods We retrospectively analyzed data including 21 predictors from patients undergoing colorectal surgery with bowel anastomosis at four Swiss hospitals. Several ML algorithms were applied for binary classification into AL or non-AL groups, utilizing a five-fold cross-validation strategy with a 90% training and 10% validation split. Additionally, a holdout test set from an external hospital was employed to assess the models' robustness in external validation. Results Among 1244 patients, 112 (9.0%) suffered from AL. The Random Forest model showed an AUC-ROC of 0.78 (SD: ± 0.01) on the internal test set, which significantly decreased to 0.60 (SD: ± 0.05) on the external holdout test set comprising 198 patients, including 7 (3.5%) with AL. Conversely, the Logistic Regression model demonstrated more consistent AUC-ROC values of 0.69 (SD: ± 0.01) on the internal set and 0.61 (SD: ± 0.05) on the external set. Accuracy measures for Random Forest were 0.82 (SD: ± 0.04) internally and 0.87 (SD: ± 0.08) externally, while Logistic Regression achieved accuracies of 0.81 (SD: ± 0.10) and 0.88 (SD: ± 0.15). F1 Scores for Random Forest moved from 0.58 (SD: ± 0.03) internally to 0.51 (SD: ± 0.03) externally, with Logistic Regression maintaining more stable scores of 0.53 (SD: ± 0.04) and 0.51 (SD: ± 0.02). Conclusion In this pilot study, we evaluated ML-based prediction models for AL post-colorectal surgery and identified ten patient-related risk factors associated with AL. Highlighting the need for multicenter data, external validation, and larger sample sizes, our findings emphasize the potential of ML in enhancing surgical outcomes and inform future development of a web-based application for broader clinical use.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0930-2794
1432-2218
1432-2218
DOI:10.1007/s00464-024-10926-4