Ability of a Machine Learning Algorithm to Predict the Need for Perioperative Red Blood Cells Transfusion in Pelvic Fracture Patients: A Multicenter Cohort Study in China

Abstract

Background: Predicting the perioperative requirement for red blood cells (RBCs) transfusion in patients with the pelvic fracture may be challenging. In this study, we constructed a perioperative RBCs transfusion predictive model (ternary classifications) based on a machine learning algorithm.Materials and Methods: This study included perioperative adult patients with pelvic trauma hospitalized across six Chinese centers between September 2012 and June 2019. An extreme gradient boosting (XGBoost) algorithm was used to predict the need for perioperative RBCs transfusion, with data being split into training test (80%), which was subjected to 5-fold cross-validation, and test set (20%). The ability of the predictive transfusion model was compared with blood preparation based on surgeons' experience and other predictive models, including random forest, gradient boosting decision tree, K-nearest neighbor, logistic regression, and Gaussian naïve Bayes classifier models. Data of 33 patients from one of the hospitals were prospectively collected for model validation.Results: Among 510 patients, 192 (37.65%) have not received any perioperative RBCs transfusion, 127 (24.90%) received less-transfusion (RBCs < 4U), and 191 (37.45%) received more-transfusion (RBCs ≥ 4U). Machine learning-based transfusion predictive model produced the best performance with the accuracy of 83.34%, and Kappa coefficient of 0.7967 compared with other methods (blood preparation based on surgeons' experience with the accuracy of 65.94%, and Kappa coefficient of 0.5704; the random forest method with an accuracy of 82.35%, and Kappa coefficient of 0.7858; the gradient boosting decision tree with an accuracy of 79.41%, and Kappa coefficient of 0.7742; the K-nearest neighbor with an accuracy of 53.92%, and Kappa coefficient of 0.3341). In the prospective dataset, it also had a food performance with accuracy 81.82%.Conclusion: This multicenter retrospective cohort study described the construction of an accurate model that could predict perioperative RBCs transfusion in patients with pelvic fractures.

Effectiveness of Preoperative Red Cell Preparation and Intraoperative Massive Transfusion in Brain Tumor Operation

“…26 In addition, Huang et al predicted PRC transfusion using various algorithms of ML and reported that the random forest algorithm had the best performance of prediction with 82.35%. 27 Therefore, predicting the PRC transfusion in patients with brain tumors by novel methods has been challenged. To create a predictive model in clinical prediction tools, feature selection is a critical step, and one technique of feature selection may be to investigate the significant factors associated with PRC transfusion using multivariable analysis.…”

A Novel System for Measuring Pterygium's Progress Using Deep Learning

“…Kappa consistency test ( 28 ) is usually used to investigate whether different diagnostic methods have consistency in diagnostic results. The original hypothesis of kappa consistency test is that there is no significant consistency between the two diagnostic results.…”

Economic impact of a machine learning-based strategy for preparation of blood products in brain tumor surgery

“…Chang et al [30] used ML with various algorithms for predicting blood transfusions in orthopedic surgery; the tool had sensitivity from 69.0-79.2%, specificity from 62.3-71.7%, and accuracy from 70.3-72.2%. Moreover, Huang et al [31] predicted PRC transfusions in patients with pelvic fracture surgery and reported that an extreme gradient boosting algorithm enabled the best predictability with sensitivity of 93%, specificity of 97%, and accuracy of 95.1%.…”