ABSTRACT
With the change of national lifestyle and the aggravation of population aging, the incidence of hypertension in China is increasing year by year, which has become a major public health problem. Based on this, this study selected data from a survey conducted by the China Health and Nutrition Survey (CHNS), and carried out univariate and multivariate analyses of the risk factors of hypertension, and 10 variables of high correlation were extracted to construct hypertensive diseases risk prediction models using Random Forest, XGBoost and LightGBM algorithms. Overall, combining the accuracy, precision, recall and AUC value of the models, the Random Forest prediction model is the most effective among all the models with 91.21% accuracy, 88.89% precision, 93.31% recall and 95.27% AUC value.The prediction model has good credibility and accuracy, which provides a scientific basis for the screening of people at high risk of hypertension and reduces the risk of hypertension in a certain extent.
- Roth G A, Forouzanfar M H, Moran A E, Demographic and Epidemiologic Drivers of Global Cardiovascular Mortality[J]. The New England Journal of Medicine, 2015, 372(14):1333-1341.Google ScholarCross Ref
- Excerpts from the China Cardiovascular Health and Disease Report 2019: Hypertension section[J]. Chinese Hypertension Miscellany Journal, 2021, 29(03):203-214.Google Scholar
- Lyngdoh A C, Choudhury N A, Moulik S . Diabetes Disease Prediction Using Machine Learning Algorithms[C]// 2020 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES) - IECBES 2020. IEEE, 2020: 118-125.Google Scholar
- Patil P.B., Mallikarjun Shastry P., Ashokumar P.S.. MACHINE LEARNINGBASED ALGORITHM FOR RISK PREDICTION OF CARDIO VASCULARDISEASE (CVD)[J]. Journal of Critical Reviews, 2020, 7(09):64-70.Google Scholar
- Kim MinJeong. Building a Cardiovascular Disease Prediction Model for Smartwatch Users Using Machine Learning: Based on the Korea National Health and Nutrition Examination Survey[J]. Biosensors, 2021, 11(7):36-42.Google Scholar
- Dimopoulos Alexandros C, Nikolaidou Mara, Caballero Francisco Félix, Engchuan Worrawat, Sanchez-Niubo Albert, Arndt Holger, Ayuso-Mateos José Luis, Haro Josep Maria, Chatterji Somnath, Georgousopoulou Ekavi N, Pitsavos Christos, Panagiotakos Demosthenes B. Machine learning methodologies versus cardiovascular risk scores, in predicting disease risk.[J]. BMC medical research methodology, 2018, 18(1):68-77.Google Scholar
- Ibomoiye Domor Mienye, Yanxia Sun, Zenghui Wang. An improved ensemble learning approach for the prediction of heart disease risk[J]. Informatics in Medicine Unlocked, 2020, 20:46-52.Google Scholar
- Li Junchao. A machine-learning-based study on the prediction of cardiovascular diseases [D]. Dalian Polytechnic University Dalian University of Technology, 2021. 001243:2-5.Google Scholar
- M. Wang, Y. Huang, Y. Song, Study on environmental and lifestyle factors for the North-South differential of cardiovascular disease in China[J]. Front Public Health, 2021, 9:615152.Google ScholarCross Ref
- China Hypertension Prevention and Control Guidelines Revision Committee, Hypertension Alliance (China), Chinese Medical Association Cardiovascular Disease Branch, Chinese hypertension prevention and treatment guidelines (2018 revision) [J]. Chinese Cardiovascular Journal, 2019, 1:1-45.Google Scholar
Index Terms
- Integrated Learning Based Risk Prediction Study for Hypertensive Diseases
Recommendations
Tensor Factorization-Based Prediction With an Application to Estimate the Risk of Chronic Diseases
Tensor factorization has emerged as a powerful method to address the challenges of high dimensionality and sparsity regarding disease development and comorbidity. Chronic diseases have a high likelihood to co-occur, such that patients suffering from one ...
Prediction and informative risk factor selection of bone diseases
With the booming of healthcare industry and the overwhelming amount of electronic health records (EHRs) shared by healthcare institutions and practitioners, we take advantage of EHR data to develop an effective disease risk management model that not ...
High-Risk Prediction of Cardiovascular Diseases via Attention-Based Deep Neural Networks
High-risk prediction of cardiovascular disease is of great significance and impendency in medical fields with the increasing phenomenon of sub-health these years. Most existing pathological methods for the prognosis prediction are either costly or prone ...
Comments