Machine learning-based preoperative analytics for the prediction of anastomotic leakage in colorectal surgery: a swiss pilot study
Surgical Endoscopy · 2024-07 · 38 (7) · 3672-3683
DOI: 10.1007/s00464-024-10926-4 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Surgical Endoscopy, online erschienen am 22.05.2024. Verfasst von Stephanie Taha-Mehlitz und 16 weiteren Autor:innen. Beteiligte Einrichtung: Clarunis, University Center for Gastrointestinal and Liver Diseases, St. Clara Hospital and University Hospital Basel, 4002, Basel, Switzerland. Hauptthemen laut MEDLINE: Anastomotic Leak, Machine Learning. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Medtronic Foundation, University of Basel.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Clarunis, University Center for Gastrointestinal and Liver Diseases, St. Clara Hospital and University Hospital Basel, 4002, Basel, Switzerland.
- Medical Faculty, University Basel, 4056, Basel, Switzerland.
- Center for Gastrointestinal and Liver Diseases, Cantonal Hospital Basel-Landschaft, 4410, Liestal, Switzerland.
- Department of Computer Engineering, McGill University, Montreal, H3A 0E9, Canada.
- Department of Biomedical Engineering, Faculty of Medicine, University of Basel, Hegenheimermattweg 167C Allschwil, 4123, Basel, Switzerland.
- Machine Intelligence in Clinical Neuroscience (MICN) Laboratory, Department of Neurosurgery, University Hospital Zurich, 8091, Zurich, Switzerland.
ORCID-Profile: Anas Taha
Förderung
- Medtronic Foundation
- University of Basel
Zitieren
APA
Taha-Mehlitz, S., Wentzler, L., Angehrn, F., Hendie, A., Ochs, V., Wolleb, J., Staartjes, V. E., Enodien, B., Baltuonis, M., Vorburger, S., Frey, D. M., Rosenberg, R., von Flüe, M., Müller-Stich, B., Cattin, P. C., Taha, A., & Steinemann, D. (2024). Machine learning-based preoperative analytics for the prediction of anastomotic leakage in colorectal surgery: a swiss pilot study. Surgical Endoscopy, 38(7), 3672-3683. https://doi.org/10.1007/s00464-024-10926-4
Vancouver
Taha-Mehlitz S, Wentzler L, Angehrn F, Hendie A, Ochs V, Wolleb J, et al. Machine learning-based preoperative analytics for the prediction of anastomotic leakage in colorectal surgery: a swiss pilot study. Surgical Endoscopy. 2024;38(7):3672-3683. doi:10.1007/s00464-024-10926-4
BibTeX
@article{TahaMehlitz2024,
author = {Taha-Mehlitz, Stephanie and Wentzler, Larissa and Angehrn, Fiorenzo and Hendie, Ahmad and Ochs, Vincent and Wolleb, Julia and Staartjes, Victor E and Enodien, Bassey and Baltuonis, Martinas and Vorburger, Stephan and Frey, Daniel M and Rosenberg, Robert and von Flüe, Markus and Müller-Stich, Beat and Cattin, Philippe C and Taha, Anas and Steinemann, Daniel},
title = {Machine learning-based preoperative analytics for the prediction of anastomotic leakage in colorectal surgery: a swiss pilot study},
journal = {Surgical Endoscopy},
year = {2024},
volume = {38},
number = {7},
pages = {3672--3683},
doi = {10.1007/s00464-024-10926-4}
}
EUVIMED