ABSTRACT
The WHO MONICA dataset was used as an example, and a logistic regression model was used to statistically analyze the data, and then a Bayesian causal network model was constructed using the MMHC hybrid algorithm to analyze the causal relationships among cardiovascular disease risk factors, and Bayesian estimation was used to learn the conditional probabilities of each node of the network so as to predict the survival of patients, and to compare the Bayesian causal network model with respect to logistic regression model in the field of chronic diseases. Bayesian causal network model results showed that hospitalization status, age at diagnosis, and angina status were direct causes of cardiovascular mortality, while previous myocardial infarction, sex, and smoking had indirect effects on cardiovascular mortality through other variables. Compared to logistic regression models, Bayesian causal networks based on the MMHC algorithm are more applicable in clinical research because they can intuitively and effectively identify and define the complex causal relationships between survival outcomes and cardiovascular disease and cardiovascular disease with each other. By analyzing this relationship, we are able to implement timely and targeted preventive and therapeutic measures and avoid possible mortality outcomes in high-risk populations.
- Bacciu, D., Etchells, T. A., & Paulo J. G. Lisboa…. (2013). Efficient identification of independence networks using mutual information. Computational Statistics, 28(2), 621-646.Google ScholarDigital Library
- Biery, D. W., Berman, A. N. , Singh, A., Divakaran, S. , & Blankstein, R..(2020). Association of smoking cessation and survival among young adults with myocardial infarction in the partners young-mi registry. JAMA Network Open, 3(7), e209649.Google ScholarCross Ref
- Dagenais, Gilles R., (2020).Variations in common diseases, hospital admissions, and deaths in middle-aged adults in 21 countries from five continents (PURE): a prospective cohort study. The Lancet, 395(10226):785-794.Google ScholarCross Ref
- Hoshino, A. , Wang, W. J. , Wada, S. , Mcdermott-Roe, C. , & Arany, Z. . (2019). The ADP/ATP translocase drives mitophagy independent of nucleotide exchange. Nature, 575(7782), -.Google Scholar
- Hu Shengshou. (2020). Report on Cardiovascular Health and Diseases in China 2019:an Updated Summary. Chinese Circulation Journal, 35(9),22.Google Scholar
- Kalisch, Markus, Bühlman, & Peter. (2007). Estimating high-dimensional directed acyclic graphs with the pc-algorithm. Journal of Machine Learning Research.Google Scholar
- Marjan Walli-Attaei, , (2020). Variations between women and men in risk factors, treatments, cardiovascular disease incidence, and death in 27 high-income, middle-income, and low-income countries (PURE): a prospective cohort study. The Lancet, DOI: 10.1016/S0140-6736(20)30543-2Google ScholarCross Ref
- Moran, Andrew, E., Forouzanfar, Mohammad, & H., (2014). The global burden of ischemic heart disease in 1990 and 2010. Circulation, 129(14), 1493-1501.Google ScholarCross Ref
- Neeland, I. J. , Ross, R. , JP Després, Matsuzawa, Y. , & Eckel, R. H. . (2019). Visceral and ectopic fat, atherosclerosis, and cardiometabolic disease: a position statement. The Lancet Diabetes & Endocrinology, 7(9).Google Scholar
- Spirtes, P. , Glymour, C. , & Scheines, R. . (2000). Causation, Prediction, and Search. The MIT Press. 2nd edition.Google Scholar
- Tsamardinos, I. . (2006). The max-min hill-climbing bayesian network structure learning algorithm. Machine Learning, 65(1), pp. 31-78.Google ScholarDigital Library
- Wang Dezheng, Shen Chengfeng, Zhang Ying, .(2017). Fifteen-year trend in incidence of acute myocardial infarction in Tianjin of China [J]. Chinese Journal of Cardiology, 45(2):154-159.Google Scholar
- Wenchi, G. , Venkatesh, A. K. , Xueke, B. , Si, X. , Jing, L. , & Xi, L. , (2018). Time to hospital arrival among patients with acute myocardial infarction in China: a report from China peace prospective study. European Heart Journal Quality of Care & Clinical Outcomes.Google Scholar
- Yasin, A. , & Leray, P. . (2011). IMMPC: A Local Search Approach for Incremental Bayesian Network Structure Learning. Springer, Berlin, Heidelberg, 2011:401-412.Google ScholarCross Ref
Index Terms
- Study on the Causal Relationship of Cardiovascular Disease Influencing Factors Based on Bayesian Causal Network
Recommendations
Prediction of CardioVascular Disease (CVD) using Ensemble Learning Algorithms
CODS-COMAD '22: Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)Over the last decade, CardioVascular Diseases (CVD) and allied heart disorders have been the leading cause of death world wide. Early prediction of CVD can help high-risk patients make lifestyle changes and as a result can reduce complications. ...
Artificial neural network-based cardiovascular disease prediction using spectral features
AbstractThe major cause of the increasing world mortality rate is cardiovascular disease (CVD), killing 17.9 million people annually. Current techniques are costly, challenging to operate on, and an expert is needed to confirm the diagnosis ...
Graphical abstractDisplay Omitted
Highlights- Developed a low-cost PCG acquisition system (PAS) to record different heart sounds from patients.
A new method for estimating the probability of causal relationships from observational data: Application to the study of the short-term effects of air pollution on cardiovascular and respiratory disease
AbstractIn this paper we investigate which airborne pollutants have a short-term causal effect on cardiovascular and respiratory disease using the Ancestral Probabilities (AP) procedure, a novel Bayesian approach for deriving the probabilities ...
Highlights- We introduce the AP procedure for estimating the probability of causal relationships.
Comments