In Transplantation and cellular therapy
BACKGROUND : As a serious complication following allogenic hematopoietic stem cell transplantation (allo-HSCT), venous thromboembolism (VTE) is significantly related to increased nonrelapse mortality. Therefore, distinguishing patients at high risk of death who should receive specific therapeutic management is key to improving survival.
OBJECTIVES : This study aimed to establish a machine-learning-based prognostic model for the identification of posttransplantation VTE patients who have a high risk of death.
STUDY DESIGN : We retrospectively evaluated 256 consecutive VTE patients who underwent allo-HSCT at our center between 2008 and 2019. These patients were further randomly divided into 1) a derivation (80%) cohort of 205 patients and 2) a test (20%) cohort of 51 patients. The least absolute shrinkage and selection operator (LASSO) approach was utilized to choose the potential predictors from the primary dataset. Eight machine learning classifiers were utilized to produce eight candidate models. A 10-fold cross-validation (CV) procedure was used to internally evaluate the models and to select the best-performing model for external assessment using the test cohort.
RESULTS : In total, 256 of 7238 patients were diagnosed with VTE after transplantation. Among them, 118 patients (46.1%) had catheter-related venous thrombosis (CRT), 107 (41.8%) had isolated deep-vein thrombosis (DVT), 20 (7.8%) had isolated pulmonary embolism (PE), and 11 (4.3%) had concomitant DVT and PE. The two-year overall survival (OS) rate of patients with VTE was 68.8%. Using LASSO regression, eight potential features were selected from the 54 candidate variables. The best-performing algorithm based on the 10-fold cross-validation runs was a logistic regression classifier. Therefore, a prognostic model named BRIDGE was then established to predict the 2-year OS rate. The areas under the curves (AUCs) of the BRIDGE model were 0.883, 0.871, and 0.858 for the training, validation, and test cohorts, respectively. The Hosmer-Lemeshow goodness-of-fit test showed a high agreement between the predicted and observed outcomes. Decision curve analysis indicated that VTE patients could benefit from the clinical application of the prognostic model. A BRIDGE risk score calculator for predicting the study result is available online (184.108.40.206:8080/bridge/).
CONCLUSION : We established the BRIDGE model to precisely predict the risk for all-cause death in VTE patients after allo-HSCT. Identifying VTE patients who have a high risk of death can help physicians treat these patients in advance, which will improve patient survival.
Deng Rui-Xin, Zhu Xiao-Lu, Zhang Ao-Bei, He Yun, Fu Hai-Xia, Wang Feng-Rong, Mo Xiao-Dong, Wang Yu, Zhao Xiang-Yu, Zhang Yuan-Yuan, Han Wei, Chen Huan, Chen Yao, Yan Chen-Hua, Wang Jing-Zhi, Han Ting-Ting, Chen Yu-Hong, Chang Ying-Jun, Xu Lan-Ping, Huang Xiao-Jun, Zhang Xiao-Hui
Hematopoietic stem cell transplantation, machine learning, prognostic model, venous thromboembolism