Predicting operative time in robotic ventral hernia repair using machine learning: a retrospective pilot study
Langenbeck's Archives of Surgery · 2026
DOI: 10.1007/s00423-026-04057-8 ↗Kurz gefasst
Fachartikel in der Zeitschrift Langenbeck's Archives of Surgery, 2026. Verfasst von Francesco Brucchi und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathophysiology and Transplantation, University of Milan, Milan, Italy. francesco.brucchi@unimi.it. Hauptthemen laut MEDLINE: Hernia, Ventral, Operative Time, Machine Learning, Robotic Surgical Procedures. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Università degli Studi di Milano.
Abstract (Originalsprache)
BACKGROUND: Robotic ventral hernia repair (VHR) is increasingly common, yet predicting operative time remains challenging. No study has yet applied machine learning (ML) to this setting. OBJECTIVE: To compare ML models for predicting operative time in elective robotic VHR and identify key preoperative predictors. METHODS: Retrospective single-center cohort study (AZORG Hospital, Aalst, Belgium) including 208 consecutive patients undergoing elective robotic VHR (October 2020–April 2025). Three models—Random Forest, Gradient Boosting, and Ridge Regression—were trained with 5-fold cross-validation using demographics, BMI, EHS hernia size, mesh position, and surgical complexity. Performance was assessed by MAE, RMSE, and R²; feature importance by SHAP analysis. RESULTS: Median operative time was 90 min (IQR 60–130). Random Forest achieved the best performance (MAE 38.0 min, RMSE 52.8 min, R² 0.22), outperforming Gradient Boosting (R² 0.01) and Ridge Regression (R² −0.53). SHAP identified mesh position (45.0%), hernia size (30.7%), and BMI (14.2%) as the top predictors. CONCLUSION: In this pilot study, Random Forest provided modest operative time predictions (R² 0.22). Limited explained variance likely reflects the absence of surgeon experience and intraoperative variables. Although mesh position and hernia size are clinically consistent predictors, current accuracy is insufficient for clinical implementation. Larger multicenter studies incorporating surgeon-level data are needed.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Pathophysiology and Transplantation, University of Milan, Milan, Italy. francesco.brucchi@unimi.it.
- Orsi Academy, Melle, Belgium. francesco.brucchi@unimi.it.
- Division of General Surgery, Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS) Istituto Auxologico Italiano, Via Mercalli 30, Milan, 20122, Italy. francesco.brucchi@unimi.it.
- Department of Medical and Surgical Sciences, University of Bologna, Bologna, Italy.
- Department of Surgery of Alimentary Tract, IRCCS AOU di Bologna, Bologna, Italy.
- Department of General, Digestive and HPB Surgery, AZORG Hospital, Aalst, Belgium.
Förderung
- Università degli Studi di Milano
Zitieren
APA
Brucchi, F., Gori, A., Van Campenhout, I., Colpaert, J., Boterbergh, K., Potvlieghe, P., Violante, T., Rottoli, M., Dionigi, G., Muysoms, F., & Bossche, B. V. D. (2026). Predicting operative time in robotic ventral hernia repair using machine learning: a retrospective pilot study. Langenbeck's Archives of Surgery. https://doi.org/10.1007/s00423-026-04057-8
Vancouver
Brucchi F, Gori A, Van Campenhout I, Colpaert J, Boterbergh K, Potvlieghe P, et al. Predicting operative time in robotic ventral hernia repair using machine learning: a retrospective pilot study. Langenbeck's Archives of Surgery. 2026. doi:10.1007/s00423-026-04057-8
BibTeX
@article{Brucchi2026,
author = {Brucchi, Francesco and Gori, Alice and Van Campenhout, Ilia and Colpaert, Jan and Boterbergh, Kim and Potvlieghe, Peter and Violante, Tommaso and Rottoli, Matteo and Dionigi, Gianlorenzo and Muysoms, Filip and Bossche, Bert Van Den},
title = {Predicting operative time in robotic ventral hernia repair using machine learning: a retrospective pilot study},
journal = {Langenbeck's Archives of Surgery},
year = {2026},
doi = {10.1007/s00423-026-04057-8}
}
EUVIMED