| 魏珍,张雪雷,饶华祥,王华芳,王祥,仇丽霞.禁忌搜索算法的贝叶斯网络模型在冠心病影响因素分析中的应用[J].Chinese journal of Epidemiology,2016,37(6):895-899 |
| 禁忌搜索算法的贝叶斯网络模型在冠心病影响因素分析中的应用 |
| Using the Tabu-search-algorithm-based Bayesian network to analyze the risk factors of coronary heart diseases |
| Received:October 15, 2015 |
| DOI：10.3760/cma.j.issn.0254-6450.2016.06.031 |
| KeyWord: 贝叶斯网络 禁忌搜索算法 logistic回归 冠心病 影响因素 |
| English Key Word: Bayesian network Tabu search algorithm Logistic regression Coronary heart disease Influencing factors |
| FundProject: |
| Author Name | Affiliation | E-mail | | Wei Zhen | Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan 030001, China | | | Zhang Xuelei | Department of Information, Shaanxi Provincial Center for Disease Control and Prevention, Xi'an 710054, China | | | Rao Huaxiang | Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan 030001, China | | | Wang Huafang | Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan 030001, China | | | Wang Xiang | Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan 030001, China | | | Qiu Lixia | Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan 030001, China | qlx_1126@163.com |
|
| Hits: 3458 |
| Download times: 2458 |
| Abstract: |
| 以10792例冠心病调查数据为例,依据禁忌搜索算法构建冠心病患病及其影响因素的贝叶斯网络模型,用极大似然估计法计算网络各节点的条件概率,并分析冠心病的影响因素,评价贝叶斯网络模型相对于传统的logistic回归模型在疾病影响因素分析中的优劣,探讨贝叶斯网络模型在临床研究中的适用性。分析结果表明,贝叶斯网络可以揭示冠心病各影响因素间的关联及与冠心病的关系,比logistic回归分析更符合实际理论,表明贝叶斯网络模型在冠心病影响因素分析中具有较好的适用性及应用前景。 |
| English Abstract: |
| Under the available data gathered from a coronary study questionnaires with 10 792 cases, this article constructs a Bayesian network model based on the tabu search algorithm and calculates the conditional probability of each node, using the Maximum-likelihood. Pros and cons of the Bayesian network model are evaluated to compare against the logistic regression model in the analysis of coronary factors. Applicability of this network model in clinical study is also investigated. Results show that Bayesian network model can reveal the complex correlations among influencing factors on the coronary and the relationship with coronary heart diseases. Bayesian network model seems promising and more practical than the logistic regression model in analyzing the influencing factors of coronary heart disease. |
|
View Fulltext
Html FullText
View/Add Comment Download reader |
| Close |
|
|
|