TY - JOUR
T1 - Predicting futility of upfront surgery in perihilar cholangiocarcinoma
T2 - Machine learning analytics model to optimize treatment allocation
AU - Ratti, Francesca
AU - Marino, Rebecca
AU - Olthof, Pim B.
AU - Pratschke, Johann
AU - Erdmann, Joris I.
AU - Neumann, Ulf P.
AU - Prasad, Raj
AU - Jarnagin, William R.
AU - Schnitzbauer, Andreas A.
AU - Cescon, Matteo
AU - Guglielmi, Alfredo
AU - Lang, Hauke
AU - Nadalin, Silvio
AU - Topal, Baki
AU - Maithel, Shishir K.
AU - Hoogwater, Frederik J. H.
AU - Alikhanov, Ruslan
AU - Troisi, Roberto
AU - Sparrelid, Ernesto
AU - Roberts, Keith J.
AU - Malagò, Massimo
AU - Hagendoorn, Jeroen
AU - Malik, Hassan Z.
AU - Olde Damink, Steven W. M.
AU - Kazemier, Geert
AU - Schadde, Erik
AU - Charco, Ramon
AU - de Reuver, Philip R.
AU - Groot Koerkamp, Bas
AU - Aldrighetti, Luca
N1 - Publisher Copyright: © 2024 John Wiley and Sons Inc.. All rights reserved.
PY - 2024/2/1
Y1 - 2024/2/1
N2 - Background: While resection remains the only curative option for perihilar cholangiocarcinoma, 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 perihilar cholangiocarcinoma 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 into a development and a validation cohort. The Framingham Heart Study methodology was used to develop a preoperative scoring system predicting the "futile" outcome. Results: A total of 2271 cases were analyzed: among them, 309 were classified within the "futile group" (13.6%). American Society of Anesthesiology (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 (ie, low, intermediate, and high) risk classes, which showed good accuracy (AUC 0.755) when tested on the validation cohort. Conclusions: 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. nonsurgical treatments) according to preoperative features.
AB - Background: While resection remains the only curative option for perihilar cholangiocarcinoma, 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 perihilar cholangiocarcinoma 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 into a development and a validation cohort. The Framingham Heart Study methodology was used to develop a preoperative scoring system predicting the "futile" outcome. Results: A total of 2271 cases were analyzed: among them, 309 were classified within the "futile group" (13.6%). American Society of Anesthesiology (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 (ie, low, intermediate, and high) risk classes, which showed good accuracy (AUC 0.755) when tested on the validation cohort. Conclusions: 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. nonsurgical treatments) according to preoperative features.
UR - http://www.scopus.com/inward/record.url?scp=85178334655&partnerID=8YFLogxK
U2 - 10.1097/HEP.0000000000000554
DO - 10.1097/HEP.0000000000000554
M3 - Article
C2 - 37530544
SN - 0270-9139
VL - 79
SP - 341
EP - 354
JO - Hepatology
JF - Hepatology
IS - 2
ER -