Prediction of massive bleeding in pancreatic surgery based on preoperative patient characteristics using a decision tree

Abstract

Massive intraoperative blood loss (IBL) negatively influence outcomes after surgery for pancreatic ductal adenocarcinoma (PDAC). However, few data or predictive models are available for the identification of patients with a high risk for massive IBL. This study aimed to build a model for massive IBL prediction using a decision tree algorithm, which is one machine learning method. One hundred and seventy-five patients undergoing curative surgery for resectable PDAC at our facility between January 2007 and October 2020 were allocated to training (n = 128) and testing (n = 47) sets. Using the preoperatively available data of the patients (34 variables), we built a decision tree classification algorithm. Of the 175 patients, massive IBL occurred in 88 patients (50.3%). Binary logistic regression analysis indicated that alanine aminotransferase and distal pancreatectomy were significant predictors of massive IBL occurrence with an overall correct prediction rate of 70.3%. Decision tree analysis automatically selected 14 predictive variables. The best predictor was the surgical procedure. Though massive IBL was not common, the outcome of patients with distal pancreatectomy was secondarily split by glutamyl transpeptidase. Among patients who underwent PD (n = 83), diabetes mellitus (DM) was selected as the variable in the second split. Of the 21 patients with DM, massive IBL occurred in 85.7%. Decision tree sensitivity was 98.5% in the training data set and 100% in the testing data set. Our findings suggested that a decision tree can provide a new potential approach to predict massive IBL in surgery for resectable PDAC.

Postoperative long‑term outcomes of acute normovolemic hemodilution in pancreatic cancer: A propensity score matching analysis

“…Several lines of evidence have shown an association between increased blood loss and poor outcomes in PDAC surgery (15,16,44). Our previous study also demonstrated those relationships (29). These data suggest that more intraoperative blood loss may negatively influence the prognosis of ANH.…”

“…A total of 155 patients undergoing curative pancreatic surgery for resectable PDAC at our facility between January 2007 and May 2018 were included in the study. A portion of the subjects in this study had been included in our previous study ( 18 , 29 ). Resectability status was made based on National Comprehensive Cancer Network guidelines.…”

Postoperative Long-term Outcomes of Acute Normovolemic Hemodilution in Pancreatic Cancer: A Propensity Score Matching Analysis

“…[15,16,38] Our previous study also demonstrated those relationships. [29] These data suggest that more intraoperative blood loss may negatively in uence the prognosis of ANH. At the same time, we must be deliberate and critically consider that ANH can potentially cause increased intraoperative blood loss.…”

“…A portion of the subjects in this study had been included in our previous study. [18,29] Resectability status was made based on National Comprehensive Cancer Network guidelines. All patients had a con rmed pathologic diagnosis.…”

Artificial intelligence in pancreatic surgery: current applications

“…The aim of the decision-tree algorithm of Wakiya et al [69] was to identify risk factors leading to massive intraoperative blood loss and consecutively to inferior postoperative outcomes after surgery for PDAC. The AI algorithm generated 14 predictive variables based on preoperative patient characteristics with the best predictors being the type of surgical procedure (open vs MIPS), portal vein resection as well as elevated liver function tests, presence of obstructive jaundice and preoperative biliary drainage.…”