A clinical-radiomics model based on noncontrast computed tomography to predict hemorrhagic transformation after stroke by machine learning: a multicenter study

作者全名："Ren, Huanhuan; Song, Haojie; Wang, Jingjie; Xiong, Hua; Long, Bangyuan; Gong, Meilin; Liu, Jiayang; He, Zhanping; Liu, Li; Jiang, Xili; Li, Lifeng; Li, Hanjian; Cui, Shaoguo; Li, Yongmei"

作者地址："[Ren, Huanhuan; Wang, Jingjie; Liu, Jiayang; Li, Yongmei] Chongqing Med Univ, Dept Radiol, Affiliated Hosp 1, 1 Youyi Rd, Chongqing 400016, Peoples R China; [Ren, Huanhuan; Xiong, Hua; Long, Bangyuan; Gong, Meilin] Chongqing Gen Hosp, Dept Radiol, Chongqing, Peoples R China; [Song, Haojie; Cui, Shaoguo] Chongqing Normal Univ, Coll Comp & Informat Sci, 37 Middle Univ Town Rd, Chongqing 400016, Peoples R China; [He, Zhanping] Cent South Univ, Dept Radiol, Haikou Affiliated Hosp, Xiangya Sch Med, Haikou, Peoples R China; [Liu, Li] Peoples Hosp Yubei Dist Chongqing City, Dept Radiol, Chongqing, Peoples R China; [Jiang, Xili] Brain Hosp Hunan Prov, Second Peoples Hosp Hunan Prov, Dept Radiol, Changsha, Peoples R China; [Li, Lifeng] Univ South China, Changsha Cent Hosp, Affiliated Changsha Cent Hosp, Hengyang Med Sch,Dept Radiol, Changsha, Peoples R China; [Li, Hanjian] Hainan Med Univ, Dept Radiol, Affiliated Hosp 1, Haikou, Peoples R China"

通信作者："Li, YM (通讯作者)，Chongqing Med Univ, Dept Radiol, Affiliated Hosp 1, 1 Youyi Rd, Chongqing 400016, Peoples R China.; Cui, SG (通讯作者)，Chongqing Normal Univ, Coll Comp & Informat Sci, 37 Middle Univ Town Rd, Chongqing 400016, Peoples R China."

来源：INSIGHTS INTO IMAGING

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:000961972700003

JCR分区：Q1

影响因子：4.1

年份：2023

卷号：14

期号：1

开始页：　

结束页：　

文献类型：Article

关键词：Acute ischemic stroke; Hemorrhagic transformation; Noncontrast computed tomography; Radiomics; Machine learning

摘要："ObjectiveTo build a clinical-radiomics model based on noncontrast computed tomography images to identify the risk of hemorrhagic transformation (HT) in patients with acute ischemic stroke (AIS) following intravenous thrombolysis (IVT).Materials and methodsA total of 517 consecutive patients with AIS were screened for inclusion. Datasets from six hospitals were randomly divided into a training cohort and an internal cohort with an 8:2 ratio. The dataset of the seventh hospital was used for an independent external verification. The best dimensionality reduction method to choose features and the best machine learning (ML) algorithm to develop a model were selected. Then, the clinical, radiomics and clinical-radiomics models were developed. Finally, the performance of the models was measured using the area under the receiver operating characteristic curve (AUC).ResultsOf 517 from seven hospitals, 249 (48%) had HT. The best method for choosing features was recursive feature elimination, and the best ML algorithm to build models was extreme gradient boosting. In distinguishing patients with HT, the AUC of the clinical model was 0.898 (95% CI 0.873-0.921) in the internal validation cohort, and 0.911 (95% CI 0.891-0.928) in the external validation cohort; the AUC of radiomics model was 0.922 (95% CI 0.896-0.941) and 0.883 (95% CI 0.851-0.902), while the AUC of clinical-radiomics model was 0.950 (95% CI 0.925-0.967) and 0.942 (95% CI 0.927-0.958) respectively.ConclusionThe proposed clinical-radiomics model is a dependable approach that could provide risk assessment of HT for patients who receive IVT after stroke."

基金机构：　

基金资助正文：