Novel Hemorrhagic Risk Score in Elderly Patients with Coronary Artery Disease and Gastrointestinal Malignant Tumor Comorbidity:A 10-year Clinical Inpatient Data Analysis from 2 Medical Centers

作     者：Nandi Bao Wanling Wang Huitao Wu Yabin Wang Hebin Che Wenwen Meng Jiaxin Miao Dong Han Fan Yin Bao Nandi;Wang Wanling;Wu Huitao;Wang Yabin;Che Hebin;Meng Wenwen;Miao Jiaxin;Han Dong;Yin Fan

作者机构：National Clinical Research Center for Geriatric DiseasesThe Second Medical Center of Chinese People's Liberation Army General HospitalBeijing 100853China Medical School of Chinese People's Liberation Army General HospitalBeijing 100853China National Engineering Laboratory for Medical Big Data Application TechnologyThe First Medical Center of Chinese People's Liberation Army General HospitalBeijing 100853China Department of OncologyThe Second Medical Center of Chinese People's Liberation Army General HospitalBeijing 100853China 

出 版 物：《Cardiology Discovery》 (心血管病探索（英文）)

年 卷 期：2021年第1卷第3期

页      面：163-172页

学科分类：1002[医学-临床医学] 100214[医学-肿瘤学] 10[医学] 

基　　金：supported in part by research grants from the National Key Research and Development Program of China(2016YFA0100900) the International Cooperation and Exchange Program of National Science Foundation of China(81820108019) the National Natural Science Foundation of China(91939303,81820108019) Health care project(19BJZ25) the Talents Support Program of the China Postdoctoral Science Foundation(BX20200154) 

主　　题：Coronary disease Gastrointestinal cancers Bleeding Multivariate analysis Risk factors Machine learning 

摘      要：Objective:Older patients with comorbidity,such as coronary heart disease(CHD)and malignant gastrointestinal tumors,are at a high risk of bleeding ***,risk prediction models based on risk factor assessment remain *** study aimed to establish an individualized bleeding risk assessment system based on the analysis of 10-year inpatient clinical big ***:Total clinical data of 56,819 patients with CHD and 25,988 patients with malignant digestive tract tumors(admitted from January 2008 to December 2017)were retrospectively collected at the First and Second Medical Centers of Chinese People s Liberation Army General *** them,1307 patients with CHD and malignant digestive tract tumors were screened as the derivation *** dependent variable was the occurrence of major clinical bleeding *** statistics and hypothesis tests of differences were performed for independent variables according to the occurrence of *** Tree,eXtreme Gradient Boosting(XGBoost),logistic regression,and random forest models were used for *** accuracy,sensitivity,specificity,and area under the receiver operating characteristic curve(AUC-ROC)were applied as the criteria for evaluating and verifying model *** evaluate this developed model,another cohort comprising 454 patients(admitted from January 2018 to December 2019)was prospectively enrolled as the validation cohort based on the same inclusion and exclusion ***:Among the 64 variables with50%missing values,the recursive feature elimination method with a random forest model was used to screen the selected *** highest accuracy was obtained following the selection of 10 scalars,and the final model was constructed *** demonstrated the best performance *** AUC-ROC of this model was 0.981,with an accuracy,sensitivity,and specificity of 0.939,0.950,and 0.927,*** the validation cohort,the AUC-ROC,accurac