Application of machine learning in predictive analysis of blood usage for liver transplantation surgery
Journal Title: Chinese Journal of Blood Transfusion - Year 2024, Vol 37, Issue 3
Abstract
Objective To explore the application of machine learning in scientific and rational blood preparation and predictive analysis for surgical blood usage before liver transplantation surgery. Methods Clinical basic information including gender, age, clinical diagnosis and surgical methods of 356 liver transplantation patients were collected. The duration (Time) and preoperative laboratory test results of hemoglobin (Hb), hematocrit (Hct), platelet count (Plt), prothrombin time (PT), activated partial thromboplastin time (APTT), fibrinogen (Fib), total bilirubin (TBIL), albumin (ALB), creatinine (Crea) and total protein (TP), as well as the amount of intraoperative blood transfusion were collected. A machine learning model capable of predicting the risk of massive blood transfusion during liver transplantation surgery was established by Python, and was evaluated to select the optimal predictive model. Results Among the 7 machine learning models constructed, the logistic regression model performed the best (AUROC: 0.90, F1 score: 0.82), with an accuracy of 79.44% and precision of 79.69%, followed by the random forest classifier (AUROC: 0.87, F1 score: 0.83), with an accuracy of 79.44% and precision of 77.94%. Conclusion Establishing a machine learning prediction model by Python is of significant clinical importance for scientific blood preparation, predicting the risk of massive blood transfusion and ensuring the safety of blood use in liver transplantation surgery.
Authors and Affiliations
Peng ZONG, Wenli ZHANG, Ping LI, Changfeng SHAO, Haiyan WANG
Keywords
Related Articles
- EP ID EP738783
- DOI 10.13303/j.cjbt.issn.1004549x.2024.03.010
- Views 60
- Downloads 0
Chinese expert consensus on clinical application of irradiated blood
Transfusion associated graft versus host disease (TA-GVHD) is a serious transfusion adverse reaction. It is widely believed that transfusion of irradiated blood is the most effective method to prevent TA-GVHD. There are...
Platelet lncRNA as a biomarker for early screening of lung adenocarcinoma: a preliminary study
Objective To explore the diagnostic value of platelet long non-coding RNA (lncRNA) as a biomarker for early screening of lung adenocarcinoma (LUAD). Methods The GSE183635 and GSE89843 datasets, which contained the platel...
Evaluation of CLIA plus NAT for detecting HBsAg single-ELISA-reactive samples of blood donors
Objective To study the detection performance of HBsAg single-ELISA-reactive samples of blood donors. Methods Two kinds of ELISA reagents from different manufacturers (named as reagents A and B) were used for HBsAg screen...
Diversity of IgG autoantibodies of 4 Chinese intravenous immunoglobulins
Objective To develop methods to display the IgG autoantibody repertoire of intravenous immunoglobulin (IVIG) products, analyze the different types of antibodies and study the diversity of IgG autoantibody in 4 IVIG prepa...
Complement content in plasma under different storage conditions
Objective To investigate the changes in complement content in component blood before blood transfusion. Methods 180 samples from 20 plasma donors were collected at different stages of the preparation process, stored at d...