Predicting futility of upfront surgery in perihilar cholangiocarcinoma: Machine learning analytics model to optimize treatment allocation Journal Article


Authors: Ratti, F.; Marino, R.; Olthof, P. B.; Pratschke, J.; Erdmann, J. I.; Neumann, U. P.; Prasad, R.; Jarnagin, W. R.; Schnitzbauer, A. A.; Cescon, M.; Guglielmi, A.; Lang, H.; Nadalin, S.; Topal, B.; Maithel, S. K.; Hoogwater, F. J. H.; Alikhanov, R.; Troisi, R.; Sparrelid, E.; Roberts, K. J.; Malagò, M.; Hagendoorn, J.; Malik, H. Z.; Olde Damink, S. W. M.; Kazemier, G.; Schadde, E.; Charco, R.; de Reuver, P. R.; Koerkamp, B. G.; Aldrighetti, L.; Perihilar Cholangiocarcinoma Collaboration Group
Article Title: Predicting futility of upfront surgery in perihilar cholangiocarcinoma: Machine learning analytics model to optimize treatment allocation
Abstract: Background:<bold> </bold>Whilst resection remains the only curative option for perihilar cholangiocarcinoma (PHC), it is well known that such surgery is associated with a high risk of morbidity and mortality. Nevertheless, beyond facing life-threatening complications, patients may also develop early disease recurrence, defining a "futile" outcome in PHC surgery. The aim of this study is to predict the high-risk category (futile group) where surgical benefits are reversed and alternative treatments may be considered.Methods: The study cohort included prospectively maintained data from 27 Western tertiary referral centers: the population was divided in a development and a validation cohort. The Framingham Heart Study methodology was used to develop a preoperative scoring system predicting the "futile" outcome.Results:<bold> </bold>A total of 2271 cases were analysed: among them, 309 were classified within the "futile group" (13.6%). ASA score >= 3 (OR 1.60; p = 0.005), bilirubin at diagnosis >= 50 mmol/L (OR 1.50; p = 0.025), Ca 19-9 >= 100 U/mL (OR 1.73; p = 0.013), preoperative cholangitis (OR 1.75; p = 0.002), portal vein involvement (OR 1.61; p = 0.020), tumor diameter >= 3 cm (OR 1.76; p < 0.001) and left sided resection (OR 2.00; p < 0.001) were identified as independent predictors of futility. The point system developed, defined three (i.e., low, intermediate, and high) risk classes, which showed good accuracy (AUC 0.755) when tested on the validation cohort.Conclusion:<bold> </bold>The possibility to accurately estimate, through a point system, the risk of severe postoperative morbidity and early recurrence, could be helpful in defining the best management strategy (surgery vs. non-surgical treatments) according to preoperative features.Copyright (c) 2023 American Association for the Study of Liver Diseases.
Keywords: classification; liver resection; outcomes; hilar cholangiocarcinoma; impact; failure; preoperative biliary drainage; surgical complications; early recurrence; risk score
Journal Title: Hepatology
Volume: 79
Issue: 2
ISSN: 0270-9139
Publisher: John Wiley & Sons  
Date Published: 2024-02-01
Start Page: 341
End Page: 354
Language: English
ACCESSION: WOS:001125457100001
DOI: 10.1097/hep.0000000000000554
PROVIDER: wos
PUBMED: 37530544
Notes: Source: Wos
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. William R Jarnagin
    903 Jarnagin