Massive transfusion prediction in patients with multiple trauma by decision tree: a retrospective analysis
- PDF / 357,452 Bytes
- 7 Pages / 595.276 x 790.866 pts Page_size
- 21 Downloads / 194 Views
ORIGINAL ARTICLE
Massive transfusion prediction in patients with multiple trauma by decision tree: a retrospective analysis Liu Wei1 • Wu Chenggao1 • Zou Juan1 • Le Aiping1
Received: 10 October 2019 / Accepted: 31 August 2020 Ó Indian Society of Hematology and Blood Transfusion 2020
Abstract Early initial massive transfusion protocol and blood transfusion can reduce patient mortality, however accurately identifying the risk of massive transfusion (MT) remains a major challenge in severe trauma patient therapy. We retrospectively analyzed clinical data of severe trauma patients with and without MT. Based on analysis results, we established a MT prediction model of clinical and laboratory data by using the decision tree algorithm in patients with multiple trauma. Our results demonstrate that shock index, injury severity score, international normalized ratio, and pelvis fracture were the most significant risk factors of MT. These four indexes were incorporated into the prediction model, and the model was validated by using the testing dataset. Moreover, the sensitivity, specificity, accuracy and area under curve values of prediction model for MT risk prediction were 60%, 92%, 90% and 0.85. Our study provides an easy and understandable classification rules for identifying risk factors associated with MT that may be useful for promoting trauma management. Keywords Massive hemorrhage Multiple trauma Massive transfusion Decision tree Algorithm
& Le Aiping [email protected] 1
Department of Blood Transfusion, The First Affiliated Hospital of Nanchang University, 17 Yongwaizheng Street, Nanchang 330006, Jiangxi, People’s Republic of China
Introduction Trauma is a major global public problem and the leading cause of death [1–4]. About 50% of trauma deaths occur as a result of uncontrolled hemorrhage within the first 48 h after trauma [3, 4]. In recent years, with the clinical progress of damage control resuscitation (DCR) and massive transfusion protocol (MTP), the mortality of trauma patient has reduced [5, 6]; however, the mortality of trauma patients with massive hemorrhage remains high. Previous studies have shown that the mortality of trauma patients was associated with an increase of blood transfusion; furthermore, the mortality of massive transfusion (MT) patients is significantly higher than non-MT patients [7–9]. For massive hemorrhage in trauma patients, MTP plays an important role in early DCR and improved survival [6, 10, 11]. MTP is defined as rapid hemorrhage control through early administration of blood products in a balanced ratio for the prevention and immediate correction of coagulopathy, and to minimize occurrence of increased use of crystalloid fluids [12–14]. Studies have shown that early start MTP could reduce the risk of MT and related complications. They have also been shown to improve outcomes [12–14]. However, it is still difficult to identify the MT risk early and accurately. Decision tree (DT) is a machine learning method used as a powerful solution to classify and predict problems [15
Data Loading...
