Please use this identifier to cite or link to this item:
http://hdl.handle.net/2445/187831
Title: | Machine Learning-Based Analysis in the Management of Iatrogenic Bile Duct Injury During Cholecystectomy: a Nationwide Multicenter Study |
Author: | Lopez Lopez, Victor Maupoey, Javier López Andujar, Rafael Ramos Rubio, Emilio Mils, Kristel Martinez, Pedro Antonio Valdivieso, Andres Garcés Albir, Marina Sabater, Luis Díez Valladares, Luis Annese Pérez, Sergio Flores, Benito Brusadin, Roberto López Conesa, Asunción Cayuela, Valentin Martinez Cortijo, Sagrario Paterna, Sandra Serrablo, Alejandro Sánchez Cabús, Santiago González Gil, Antonio González Masía, Jose Antonio Loinaz, Carmelo Lucena, Jose Luis Pastor, Patricia Garcia Zamora, Cristina Calero, Alicia Valiente, Juan Minguillon, Antonio Rotellar, Fernando Ramia, Jose Manuel Alcazar, Cándido Aguilo, Javier Cutillas, Jose Kuemmerli, Christoph Ruiperez Valiente, Jose A. Robles Campos, Ricardo |
Keywords: | Malalties dels conductes biliars Patologia quirúrgica Bile ducts diseases Surgical pathology |
Issue Date: | 5-Jul-2022 |
Publisher: | Springer Science and Business Media LLC |
Abstract: | Background Iatrogenic bile duct injury (IBDI) is a challenging surgical complication. IBDI management can be guided by artificial intelligence models. Our study identified the factors associated with successful initial repair of IBDI and predicted the success of definitive repair based on patient risk levels. Methods This is a retrospective multi-institution cohort of patients with IBDI after cholecystectomy conducted between 1990 and 2020. We implemented a decision tree analysis to determine the factors that contribute to successful initial repair and developed a risk-scoring model based on the Comprehensive Complication Index. Results We analyzed 748 patients across 22 hospitals. Our decision tree model was 82.8% accurate in predicting the success of the initial repair. Non-type E (p < 0.01), treatment in specialized centers (p < 0.01), and surgical repair (p < 0.001) were associated with better prognosis. The risk-scoring model was 82.3% (79.0-85.3%, 95% confidence interval [CI]) and 71.7% (63.8-78.7%, 95% CI) accurate in predicting success in the development and validation cohorts, respectively. Surgical repair, successful initial repair, and repair between 2 and 6 weeks were associated with better outcomes. Discussion Machine learning algorithms for IBDI are a novel tool may help to improve the decision-making process and guide management of these patients. |
Note: | Reproducció del document publicat a: https://doi.org/10.1007/s11605-022-05398-7 |
It is part of: | Journal of Gastrointestinal Surgery, 2022, vol. 26, p. 1713–1723 |
URI: | http://hdl.handle.net/2445/187831 |
Related resource: | https://doi.org/10.1007/s11605-022-05398-7 |
ISSN: | 1873-4626 |
Appears in Collections: | Articles publicats en revistes (Institut d'lnvestigació Biomèdica de Bellvitge (IDIBELL)) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Lopez-Lopez2022_Article_MachineLearning-BasedAnalysisI.pdf | 1.12 MB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License