Exploring the risk factors of blood transfusion in patients with isolated traumatic brain injury based on machine learning prediction models
Journal Title: Chinese Journal of Blood Transfusion - Year 2024, Vol 37, Issue 12
Abstract
[Objective] To explore the risk factors of blood transfusion in patients with isolated traumatic brain injury (iTBI) based on multiple machine learning methods, so as to establish a predictive model to provide reasonable guidance for blood transfusion in patients with iTBI. [Methods] A total of 2 273 patients with iTBI from the First Affiliated Hospital of Nanchang University from January 1, 2015 to June 30, 2021 were included to compare and analyze the differences in variables such as vital signs, clinical indicators and laboratory testing indicators between transfusion and non transfusion patients. Furthermore, six machine learning models were established to compare the performance of different models through cross validation, accuracy, specificity, recall, f1 value and area under the ROC curve. The SHAP plot was used to explain the influencing factors of blood transfusion in iTBI patients. [Results] This study included 2 273 iTBI patients, with a total of 301 patients receiving blood transfusions. There were significant differences (P<0.05) in gender, age, HR, clinical diagnosis, skull fracture, treatment methods, hemorrhagic shock, GCS, K, Ca, PT, APTT, INR, RBC, Hct, Hb and Plt between transfusion and non transfusion patients; Moreover, the LOS, incidence of complications, mechanical ventilation rate, ICU admission rate, readmission rate within 90 days and in-hospital mortality rate of transfusion patients were all higher than those of the non transfusion group (P<0.05). Six machine learning algorithms were used for model construction, and the validation results on the test set showed that the CatBoost model performed the best with an AUC of 0.911. Furthermore, the SHAP framework was used to explain and visualize the optimal model CatBoost, showing that surgical treatment, lower GCS, higher INR, lower Hct, lower K, lower Ca, age ≥60 years, skull fractures and hemorrhagic shock increase the risk of blood transfusion in patients. [Conclusion] This study established a machine learning model for predicting blood transfusion in iTBI patients, and the CatBoost model performed the best. This model may be useful and beneficial for identifying transfusion risks in this population, making clinical transfusion decisions and monitoring progress.
Authors and Affiliations
Wei LIU, Ziqing XIONG, Chenggao WU, Aiping LE
Keywords
Related Articles
- EP ID EP754450
- DOI 10.13303/j.cjbt.issn.1004-549x.2024.12.003
- Views 2
- Downloads 0
Preparation and in vitro evaluation of hemoglobin-paclitaxel dual loaded liposomes for improving tumor hypoxia resistance
Objective To prepare liposomes encapsulate hemoglobin and paclitaxel(LEHP)to improve tumor hypoxia resistance. Methods LEHP were prepared by thin-film method, and the particle size, Zeta potential and polydispersity were...
Influencing factors of red blood cell transfusion volume for premature neonatal pneumonia and its predictive value for feeding intolerance
Objective To investigate the influencing factors of red blood cell transfusion volume for premature neonatal pneumonia and its predictive value for feeding intolerance. Methods 272 infants of premature neonatal pneumonia...
Performance evaluation of nucleic acid testing system for blood screening in high-altitude areas
Objective To validate the performance of a nucleic acid testing(NAT) system for blood screening in the high-altitude Nagqu region of Tibet, in order to assess the capability of NAT in high-altitude areas and further enha...
Diagnosis and genetic analysis of severe neonatal anemia caused by α-Thalassemla combined with cold IgG anti-M
Objective To investigate the family inheritance of α-Thalassemla gene and the risk of severe anemia in neonates caused by cold IgG anti-M. Methods ABO, Rh, MN blood groups and the specificity of unexpected antibody were...
Identification of mimicking anti-Ec with literature review: a case report
[Objective] To identify a mimicking alloantibody, analyze its serological characteristics and antibody specificity, and explore transfusion strategies for mimicking alloantibody. [Methods] The antibody specificity of pat...