Prediction of Hemorrhagic Complication after Thrombolytic Therapy Based on Multimodal Data from Multiple Centers: An Approach to Machine Learning and System Implementation

作者全名："Cui, Shaoguo; Song, Haojie; Ren, Huanhuan; Wang, Xi; Xie, Zheng; Wen, Hao; Li, Yongmei"

作者地址："[Cui, Shaoguo; Song, Haojie; Xie, Zheng; Wen, Hao] Chongqing Normal Univ, Sch Comp & Informat Sci, Chongqing 401331, Peoples R China; [Ren, Huanhuan; Li, Yongmei] Chongqing Med Univ, Affiliated Hosp 1, Dept Radiol, Chongqing 400016, Peoples R China; [Ren, Huanhuan] Chongqing Gen Hosp, Dept Radiol, Chongqing 400013, Peoples R China; [Wang, Xi] Peking Univ, Sch Econ, Beijing 100871, Peoples R China"

通信作者："Ren, HH (通讯作者)，Chongqing Med Univ, Affiliated Hosp 1, Dept Radiol, Chongqing 400016, Peoples R China.; Ren, HH (通讯作者)，Chongqing Gen Hosp, Dept Radiol, Chongqing 400013, Peoples R China."

来源：JOURNAL OF PERSONALIZED MEDICINE

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:000902453800001

JCR分区：Q2

影响因子：3.4

年份：2022

卷号：12

期号：12

开始页：　

结束页：　

文献类型：Article

关键词：hemorrhagic complication; machine learning; XGB; clinical decision support system

摘要："Hemorrhagic complication (HC) is the most severe complication of intravenous thrombolysis (IVT) in patients with acute ischemic stroke (AIS). This study aimed to build a machine learning (ML) prediction model and an application system for a personalized analysis of the risk of HC in patients undergoing IVT therapy. We included patients from Chongqing, Hainan and other centers, including Computed Tomography (CT) images, demographics, and other data, before the occurrence of HC. After feature engineering, a better feature subset was obtained, which was used to build a machine learning (ML) prediction model (Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGB)), and then evaluated with relevant indicators. Finally, a prediction model with better performance was obtained. Based on this, an application system was built using the Flask framework. A total of 517 patients were included, of which 332 were in the training cohort, 83 were in the internal validation cohort, and 102 were in the external validation cohort. After evaluation, the performance of the XGB model is better, with an AUC of 0.9454 and ACC of 0.8554 on the internal validation cohort, and 0.9142 and ACC of 0.8431 on the external validation cohort. A total of 18 features were used to construct the model, including hemoglobin and fasting blood sugar. Furthermore, the validity of the model is demonstrated through decision curves. Subsequently, a system prototype is developed to verify the test prediction effect. The clinical decision support system (CDSS) embedded with the XGB model based on clinical data and image features can better carry out personalized analysis of the risk of HC in intravenous injection patients."

基金机构："National Natural Science Foundation of China [62003065]; Humanity and Social Science Project of Ministry of Education of China [22A10637019]; Chongqing Science and Technology Bureau [CSTB2022NSCQ-MSX1206, CSTB2022TFII-OFX0042, cstc2019jscx-mbdxX0061]; Science and Technology Research Program of Chongqing Municipal Education Commission [KJZD-K20220051]; Planning Foundation Project of Chongqing Federation of Social Sciences [2022NDYB119]; Medical Research Program of the Chongqing National Health Commission; Chongqing Science and Technology Bureau, China [2021MSXM155]; Chongqing Normal University [20XLB004]; Chongqing Postgraduate Scientific Research Innovation Project [CYS22555]"

基金资助正文："This research was funded by National Natural Science Foundation of China (grant number 62003065), Humanity and Social Science Project of Ministry of Education of China (grant number 22A10637019), Chongqing Science and Technology Bureau (grant number CSTB2022NSCQ-MSX1206, CSTB2022TFII-OFX0042 and cstc2019jscx-mbdxX0061), Science and Technology Research Program of Chongqing Municipal Education Commission (grant number KJZD-K20220051), Planning Foundation Project of Chongqing Federation of Social Sciences (grant number 2022NDYB119), Medical Research Program of the Chongqing National Health Commission and Chongqing Science and Technology Bureau, China (grant number 2021MSXM155), Chongqing Normal University (grant number 20XLB004), Chongqing Postgraduate Scientific Research Innovation Project (grant number CYS22555)."