Home  About Journal Instructions for Authors Editorial Board Subscribe Advertisement Messages Board Contact Us 中文

CJAP ›› 2021, Vol. 37 ›› Issue (2): 142-146.doi: 10.12047/j.cjap.0093.2021.117

• ORIGINAL ARTICLES • Previous Articles     Next Articles

Screening biomarkers for hypertensive heart disease: Analysis based on data from 7 medical institutions

ZHANG Xue-mei1, ZHONG Xiao-gang1,2, GONG Jun2, TIAN Jun1, ZHANG Yi1, CHEN Ying-zhe3,4, CUI Jing1, WANG Zeng-zi1, RAN Shu-qiong1, XIANG Tian-yu2, XIE You-hong1, SUN Xing-guo1,3△   

  1. 1. Department of Medical and Nursing, The Affiliated Rehabilitation Hospital of Chongqing Medical University, Chongqing 400050;
    2. Medical Data Science Academy, Chongqing Medical University, Chongqing 400016;
    3. State Key Laboratory of Cardiovascular Disease, National Center of Cardiovascular Disease Fuwai Hospital, Chinese Academy Science and Peking Union Medical College, Beijing 100037;
    4. Beijing Hospital of Traditional Chinese Medicine, Capital Medical University, Beijing 100010, China
  • Received:2020-08-12 Revised:2021-03-10 Online:2021-03-28 Published:2021-10-20

Abstract: Objective: To screen the influencing factors of hypertensive heart disease (HHD), establish the predictive model of HHD, and provide early warning for the occurrence of HHD. Methods: Select the patients diagnosed as hypertensive heart disease or hypertensionfrom January 1, 2016 to December 31, 2019, in the medical data science academy of a medical school. Influencing factors were screened through single factor and multi-factor analysis, and R software was used to construct the logistics model, random forest (RF) model and extreme gradient boosting (XGBoost) model. Results: Univariate analysis screened 60 difference indicators, and multifactor analysis screened 18 difference indicators (P<0.05). The area under the curve (AUC) of Logistics model, RF model and XGBoost model are 0.979, 0.983 and 0.990, respectively. Conclusion: The results of the three HHD prediction models established in this paper are stable, and the XGBoost prediction model has a good diagnostic effect on the occurrence of HHD.

Key words: hypertensive heart disease, biomarkers, machine learning, random forest, XGBoost

CLC Number: 

Copyright © 2015 CJAP, All Rights Reserved.
Powered by Beijing Magtech Co. Ltd