A New Time-Window Prediction Model For Traumatic Hemorrhagic Shock Based on Interpretable Machine Learning. Issue 1 (January 2022)

• Record Type: Journal Article
• Authors: Zhao, Yuzhuo; Jia, Lijing; Jia, Ruiqi; Han, Hui; Feng, Cong; Li, Xueyan; Wei, Zijian; Wang, Hongxin; Zhang, Heng; Pan, Shuxiao; Wang, Jiaming; Guo, Xin; Yu, Zheyuan; Li, Xiucheng; Wang, Zhaohong; Chen, Wei; Li, Jing; Li, Tanshi
• Is Part Of: Shock. Volume 57:Issue 1(2022)
• Publication Date: 2022-01
• Subjects: Interpretability -- machine learning -- prediction window -- shock index -- time series -- traumatic hemorrhagic shock -- 95% CI -- 95% confidence interval -- AUPRC -- area under the precision-recall curve -- AUROC -- area under the receiver operating characteristic curve -- BE -- base excess -- BP -- blood pressure -- DBP -- diastolic blood pressure -- EMR -- electronic medical record -- Hb -- hemoglobin -- Hct -- hematocrit -- HR -- heart rate -- IQR -- interquartile range -- Lac -- lactate -- LOS -- length of stay -- MBP -- mean blood pressure -- MIMIC III -- the Medical Information Mart for Intensive Care III -- PaCO2 -- partial pressure of carbon dioxide -- PaO2 -- partial pressure of oxygen -- PLAGH-ERD -- the PLA General Hospital Emergency Rescue Database -- PLT -- platelets -- RESP -- respiration rate -- SBP -- systolic blood pressure -- SHAP -- Shapley additive explanation -- SI -- shock index -- TCO2 -- total carbon dioxide -- TEMP -- temperature -- THS -- traumatic hemorrhagic shock -- WBC -- white blood cell count; Shock -- Periodicals; Shock -- Periodicals; Choc (Pathologie) -- Périodiques; Shock; Periodicals; 616.0475
• DOI: 10.1097/SHK.0000000000001842
• Languages: English
• ISSNs: 1073-2322

Abstract

Abstract : ABSTRACT: Early warning prediction of traumatic hemorrhagic shock (THS) can greatly reduce patient mortality and morbidity. We aimed to develop and validate models with different stepped feature sets to predict THS in advance. From the PLA General Hospital Emergency Rescue Database and Medical Information Mart for Intensive Care III, we identified 604 and 1, 614 patients, respectively. Two popular machine learning algorithms (i.e., extreme gradient boosting [XGBoost] and logistic regression) were applied. The area under the receiver operating characteristic curve (AUROC) was used to evaluate the performance of the models. By analyzing the feature importance based on XGBoost, we found that features in vital signs (VS), routine blood (RB), and blood gas analysis (BG) were the most relevant to THS (0.292, 0.249, and 0.225, respectively). Thus, the stepped relationships existing in them were revealed. Furthermore, the three stepped feature sets (i.e., VS, VS + RB, and VS + RB + sBG) were passed to the two machine learning algorithms to predict THS in the subsequent T hours (where T = 3, 2, 1, or 0.5), respectively. Results showed that the XGBoost model performance was significantly better than the logistic regression. The model using vital signs alone achieved good performance at the half-hour time window (AUROC = 0.935), and the performance was increased when laboratory results were added, especially when the time window was 1 h (AUROC = 0.950 and 0.968, respectively). These good-performing interpretable models demonstrated acceptable generalization ability in external validation, which could flexibly and rollingly predict THS T hours (where T = 0.5, 1) prior to clinical recognition. A prospective study is necessary to determine the clinical utility of the proposed THS prediction models. Abstract : Supplemental Digital Content is available in the text