MedPath

PREDICTION OF MASSIVE BLEEDING IN PANCREATIC SURGERY USING A MACHINE LEARNING APPROACH

Not Applicable
Conditions
pancreatic ductal adenocarcinoma
Registration Number
JPRN-jRCT1020210001
Lead Sponsor
Wakiya Taiichi
Brief Summary

This study aimed to build a model for massive intraoperative blood loss (IBL) prediction using a decision tree algorithm. Using the preoperatively available data of the patients (34 variables), we built a decision tree classification algorithm. 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 pancreatic cancer.

Detailed Description

Not available

Recruitment & Eligibility

Status
Complete
Sex
All
Target Recruitment
175
Inclusion Criteria

Patients undergoing pancreatic surgery for resectable pancreatic ductal adenocarcinoma at Hirosaki university hospital between 2007 and 2020.
Subjects must meet the following criteria to be enrolled in this study.
1. Age >20 years
2. Pathologically diagnosed with pancreatic ductal adenocarcinoma

Exclusion Criteria

Patients who lacking clinicopathological findings

Study & Design

Study Type
Observational
Study Design
Not specified
Primary Outcome Measures
NameTimeMethod
Intraoperative blood loss
Secondary Outcome Measures
NameTimeMethod
© Copyright 2025. All Rights Reserved by MedPath