Lingxiao He1, Lei Luo2, Xiaoling Hou1, Dengbin Liao1, Ran Liu3, Chaowei Ouyang1, Guanglin Wang4. 1. Trauma Center of West China Hospital/West China School of Nursing, Sichuan University, Guo Xue Road 37#, Chengdu, 610041, China. 2. College of Chemical Engineering, Sichuan University, Chengdu, China. 3. Engineering Research Center of Medical Information Technology, Ministry of Education, West China Hospital of Sichuan University, Chengdu, China. 4. Trauma Center of West China Hospital/West China School of Medicine, Sichuan University, Guo Xue Road 37#, Chengdu, 610041, China. wglfrank@163.com.
Abstract
BACKGROUND: Venous thromboembolism (VTE) is a common complication of hospitalized trauma patients and has an adverse impact on patient outcomes. However, there is still a lack of appropriate tools for effectively predicting VTE for trauma patients. We try to verify the accuracy of the Caprini score for predicting VTE in trauma patients, and further improve the prediction through machine learning algorithms. METHODS: We retrospectively reviewed emergency trauma patients who were admitted to a trauma center in a tertiary hospital from September 2019 to March 2020. The data in the patient's electronic health record (EHR) and the Caprini score were extracted, combined with multiple feature screening methods and the random forest (RF) algorithm to constructs the VTE prediction model, and compares the prediction performance of (1) using only Caprini score; (2) using EHR data to build a machine learning model; (3) using EHR data and Caprini score to build a machine learning model. True Positive Rate (TPR), False Positive Rate (FPR), Area Under Curve (AUC), accuracy, and precision were reported. RESULTS: The Caprini score shows a good VTE prediction effect on the trauma hospitalized population when the cut-off point is 11 (TPR = 0.667, FPR = 0.227, AUC = 0.773), The best prediction model is LASSO+RF model combined with Caprini Score and other five features extracted from EHR data (TPR = 0.757, FPR = 0.290, AUC = 0.799). CONCLUSION: The Caprini score has good VTE prediction performance in trauma patients, and the use of machine learning methods can further improve the prediction performance.
BACKGROUND:Venous thromboembolism (VTE) is a common complication of hospitalized traumapatients and has an adverse impact on patient outcomes. However, there is still a lack of appropriate tools for effectively predicting VTE for traumapatients. We try to verify the accuracy of the Caprini score for predicting VTE in traumapatients, and further improve the prediction through machine learning algorithms. METHODS: We retrospectively reviewed emergency traumapatients who were admitted to a trauma center in a tertiary hospital from September 2019 to March 2020. The data in the patient's electronic health record (EHR) and the Caprini score were extracted, combined with multiple feature screening methods and the random forest (RF) algorithm to constructs the VTE prediction model, and compares the prediction performance of (1) using only Caprini score; (2) using EHR data to build a machine learning model; (3) using EHR data and Caprini score to build a machine learning model. True Positive Rate (TPR), False Positive Rate (FPR), Area Under Curve (AUC), accuracy, and precision were reported. RESULTS: The Caprini score shows a good VTE prediction effect on the trauma hospitalized population when the cut-off point is 11 (TPR = 0.667, FPR = 0.227, AUC = 0.773), The best prediction model is LASSO+RF model combined with Caprini Score and other five features extracted from EHR data (TPR = 0.757, FPR = 0.290, AUC = 0.799). CONCLUSION: The Caprini score has good VTE prediction performance in traumapatients, and the use of machine learning methods can further improve the prediction performance.
Authors: Jonathan P Meizoso; Charles A Karcutskie; Juliet J Ray; Xiomara Ruiz; Enrique Ginzburg; Nicholas Namias; Carl I Schulman; Kenneth G Proctor Journal: J Surg Res Date: 2016-08-31 Impact factor: 2.192
Authors: Frederick B Rogers; Steven R Shackford; Michael A Horst; Jo Ann Miller; Daniel Wu; Eric Bradburn; Amelia Rogers; Margaret Krasne Journal: J Trauma Acute Care Surg Date: 2012-08 Impact factor: 3.313
Authors: Kostas Stoitsas; Saurabh Bahulikar; Leonie de Munter; Mariska A C de Jongh; Maria A C Jansen; Merel M Jung; Marijn van Wingerden; Katrijn Van Deun Journal: Sci Rep Date: 2022-10-10 Impact factor: 4.996