Ventral hernia repair in emergency settings. A machine learning model to predict post-operative complications

BACKGROUND: Emergency ventral hernia repair remains a challenging procedure due to patient instability, contaminated surgical fields, and heterogeneity in hernia types and operative techniques. Predicting postoperative complications in this setting is difficult using traditional statistical methods. Machine learning (ML) may offer improved predictive accuracy by recognizing nonlinear patterns among multiple perioperative factors. METHODS: A retrospective multicenter analysis was performed using data from the ACTIVE (Acute Treatment for Incisional Ventral Hernias) study, including 557 adult patients undergoing emergent ventral hernia repair between 2018 and 2021 in 31 Italian surgical centers. Demographic, preoperative, intraoperative, and postoperative variables were analyzed. Three ML algorithms-Decision Tree, Random Forest, and Deep Learning Neural Network-were trained and validated using five-fold cross-validation after class balancing with SMOTE. Model performance was compared with traditional logistic regression using accuracy, area under the ROC curve (AUC), and F1 score. RESULTS: Postoperative complications occurred in 181 patients (32.5%), while major complications (Clavien-Dindo ≥ II) occurred in 10%. Random Forest achieved the best performance (AUC 0.95, accuracy 0.88, F1 score 0.86), outperforming logistic regression (AUC 0.82, accuracy 0.78). The most influential predictors were operative duration, ASA score, and sepsis for overall complications, while bowel obstruction and BMI were key factors for major complications. Surgical approach (open vs. laparoscopic) did not independently correlate with adverse outcomes, highlighting the complexity of patient- and case-specific interactions. CONCLUSIONS: Machine learning models can accurately predict postoperative complications following emergent ventral hernia repair, surpassing traditional regression methods. These findings suggest that ML-based decision tools could support risk stratification and optimize surgical planning in high-risk emergency settings. Prospective validation is warranted to integrate AI-assisted prediction into perioperative clinical workflows.

Authors

Institutions

Publication Details

Journal
Minimally Invasive Therapy & Allied Technologies
Published
2026-05-08
DOI
https://doi.org/10.1080/13645706.2026.2665459
Primary Topic
Hernia repair and management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Ventral hernia repair in emergency settings. A machine learning model to predict post-operative complications

Alberto Patriti, L Bonomo, Monica Ortenzi, Bruno Scotto et al.
Minimally Invasive Therapy & Allied Technologies
Hernia repair and management
article

Ventral hernia repair in emergency settings. A machine learning model to predict post-operative complications

Alberto Patriti, L Bonomo, Monica Ortenzi, Bruno Scotto, Mauro Podda, Lorenzo Crepaz, Antonella Nicotera, Guglielmo Clarizia, Mário Padula, Gabriele Sganga, Daunia Verdi, Nicola Baldan, Silvia Neri, Daniela Di Pietrantonio, F. P. Renzi, Francesca Ascari, Alessandro De Troia, Emanuele Pontecorvi, Pasquale Lepiane, Pasquale Cianci, Ferdinando Agresta, Elena Falsetti, Vania Silvestri, Manuela Mastronardi, Daniele Delogu, Maria Clelia Gervasi, Corrado Bottini, Alessandro Spolini, Jacopo Andreuccetti, Alberto Arezzo, Luca Leonardi, Paolo Millo, Alberto Oldani, Niccolò Petrucciani, Anna Guariniello, Isabella Mondi, Giorgio Soliani, Beatrice Torre, Diletta Corallino, Danila Azzolina, Elisa Sefora Pierobon, Giovanni Cestaro, Pier Luigi Tilocca, Lucia Romano, Hussein Abdallah, Paola Marongiu, Giorgio Brancato, Miriam Cappiello, Alessandro Capozucco, Silvio Laureti, Valentina Bianchi, Fleres Francesco, Sofia Esposito, Salvador Morales-Conde, Gabriele Anania, Carla Piras, Alberto Sartori, Mazzeo Carmelo, the ACTIVE study group, Alessandro Ferraro, Andrea Balla, Giulia Montori, Mario Nardi, Laura Vedana, Giorgio Ercolani, Silvia Palmisano, Lidia Bressan, Micaela Piccoli
article en

Abstract

BACKGROUND: Emergency ventral hernia repair remains a challenging procedure due to patient instability, contaminated surgical fields, and heterogeneity in hernia types and operative techniques. Predicting postoperative complications in this setting is difficult using traditional statistical methods. Machine learning (ML) may offer improved predictive accuracy by recognizing nonlinear patterns among multiple perioperative factors. METHODS: A retrospective multicenter analysis was performed using data from the ACTIVE (Acute Treatment for Incisional Ventral Hernias) study, including 557 adult patients undergoing emergent ventral hernia repair between 2018 and 2021 in 31 Italian surgical centers. Demographic, preoperative, intraoperative, and postoperative variables were analyzed. Three ML algorithms-Decision Tree, Random Forest, and Deep Learning Neural Network-were trained and validated using five-fold cross-validation after class balancing with SMOTE. Model performance was compared with traditional logistic regression using accuracy, area under the ROC curve (AUC), and F1 score. RESULTS: Postoperative complications occurred in 181 patients (32.5%), while major complications (Clavien-Dindo ≥ II) occurred in 10%. Random Forest achieved the best performance (AUC 0.95, accuracy 0.88, F1 score 0.86), outperforming logistic regression (AUC 0.82, accuracy 0.78). The most influential predictors were operative duration, ASA score, and sepsis for overall complications, while bowel obstruction and BMI were key factors for major complications. Surgical approach (open vs. laparoscopic) did not independently correlate with adverse outcomes, highlighting the complexity of patient- and case-specific interactions. CONCLUSIONS: Machine learning models can accurately predict postoperative complications following emergent ventral hernia repair, surpassing traditional regression methods. These findings suggest that ML-based decision tools could support risk stratification and optimize surgical planning in high-risk emergency settings. Prospective validation is warranted to integrate AI-assisted prediction into perioperative clinical workflows.

Minimally Invasive Therapy & Allied Technologies
Marche Polytechnic University (IT), University of Trieste (IT), University of Cagliari (IT), University of Ferrara (IT), Agostino Gemelli University Polyclinic (IT), Hospital Universitario Virgen Macarena (ES), Ospedale di Cattinara (IT), IRCCS Azienda Ospedliero-Universitaria di Bologna Policlinico di Sant'Orsola (IT), San Salvatore Hospital (IT), Azienda Unità Sanitaria Locale di Ferrara (IT), Azienda Socio Sanitaria Territoriale degli Spedali Civili di Brescia (IT), Ospedale Sant Antonio (IT), Azienda Ospedaliero Universitaria di Sassari (IT), Azienda Ospedaliera di Valtellina e Valchiavenna (IT), Ospedale Santa Maria (IT), Ospedali Riuniti Marche Nord (IT), Federico II University Hospital (IT), Community Health Development (US), Presidio Ospedaliero (IT), Ospedale G.B. Morgagni - L.Pierantoni (IT), Azienda Ospedaliera Sant'Andrea (IT), Arcispedale Sant'Anna (IT), IRCCS San Camillo Hospital (IT), Ospedale di Mirano (IT), Ospedale L. Bonomo (IT), Ospedale Martini (IT), Azienda Ospedaliera Universitaria Policlinico "G. Martino" (IT), Agenzia Regionale Emergenza Urgenza (IT), Center for Special Minimally Invasive and Robotic Surgery (US), Azienda Ospedale - Università Padova (IT), Azienda Ospedaliera Universitaria Policlinico "Paolo Giaccone" di Palermo (IT), Ospedale SS. Annunziata (IT), Ospedale degli Infermi (IT), Ospedale Civile di Venezia (IT), Ospedale Civile di Giaveno (IT), Ospedale Civile di Vittorio Veneto (IT), University of Turin (IT)
Openalex Percentile: Top 5%
Hernia repair and management
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.