Machine Learning-Based Analysis in the Management of Iatrogenic Bile Duct Injury During Cholecystectomy: a Nationwide Multicenter Study.

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 r...

Descripción completa

Detalles Bibliográficos
Autores: Lopez-Lopez V, Maupoey J, López-Andujar R, Ramos E, Mils K, Martinez PA, Valdivieso A, Garcés-Albir M, Sabater L, Valladares LD, Pérez SA, Flores B, Brusadin R, Conesa AL, Cayuela V, Cortijo SM, Paterna S, Serrablo A, Sánchez-Cabús S, Gil AG, Masía JAG, Loinaz C, Lucena JL, Pastor P, Garcia-Zamora C, Calero A, Valiente J, Minguillon A, Rotellar F, Ramia JM, Alcazar C, Aguilo J, Cutillas J, Kuemmerli C, Ruiperez-Valiente JA, Robles-Campos R
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2022
País:España
Institución:Instituto de Investigación Biomédica y Sanitaria de Alicante (ISABIAL)
Repositorio:r-ISABIAL. Repositorio Institucional de Producción Científica del Instituto de Investigación Biomédica y Sanitaria de Alicante
OAI Identifier:oai:isabial.fundanetsuite.com:p9078
Acceso en línea:https://isabial.portalinvestigacion.com/publicaciones9078
Access Level:acceso abierto
Palabra clave:Artificial neural network
Cholecystectomy
Iatrogenic bile duct injury
Machine learning
Descripción
Sumario: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.

Similares en LA Referencia