...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Cardiovascular Disease Research >Diagnosis and Identification of Risk Factors for Heart Disease Patients Using Generalized Additive Model and Data Mining Techniques
【24h】

Diagnosis and Identification of Risk Factors for Heart Disease Patients Using Generalized Additive Model and Data Mining Techniques

机译：广义加性模型和数据挖掘技术对心脏病患者危险因素的诊断和识别

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Background: Yearly death rate is increasing due to heart disease. Major factors for the increasing death rate due toheart disease are (a) misdiagnosed by the medical doctors or (b) ignorance by the patients. Heart diseases can bedescribed as any kind of disorder which affects the heart. Methods: The dataset of ‘statlog’ from the UCI MachineLearning with 270 patients related to heart disease isused in this article. The dataset comprises attributes of patientsdiagnosed with heart diseases. The diagnosis was used to confirm whether heart disease is present or absent in thepatient. The present article aims to identify the risk factors/variables which influence this diagnosis. Classification is avery important part of the disease diagnosis but it is also relevant to identify the risk factors/variables. Two classificationtechniques namely Support Vector Machines (SVM), Multi-Layer Perceptrons ensembles (MLPE) and one advancedregression technique,Generalized additive model (GAM) with binomial distribution and‘logit’ link have been introducedfor diagnosis and risk factors/variables identification. Results: GAM explains 65% deviance with adjusted R square value0.70 approximately. Sensitivity analysis has been performed under SVM, which is the best model for this dataset withapproximately 85% classification accuracy rate. MLPE gives 82% classification accuracy rate approximately.Maximumheart rate, vessel, old peak, chest pain, thallium scan are the most important factors/variables find through both sensitivityanalysis under SVM and GAM. Conclusion: The present article attempt to remove some new information regardingheart disease through probabilistic modeling which may provide better assistance for treatment decision making usingthe individual patient risk factors and the benefits of a specific treatment. These findings may help the medical practitionersfor better medical treatment.
机译：背景：由于心脏病，每年的死亡率正在增加。由于心脏病导致死亡率增加的主要因素是（a）医生误诊或（b）患者无知。心脏病可以说是任何一种影响心脏的疾病。方法：本文使用UCI MachineLearning的“ statlog”数据集，其中包含270名与心脏病相关的患者。该数据集包括被诊断患有心脏病的患者的属性。该诊断用于确认患者是否存在心脏病。本文旨在确定影响该诊断的危险因素/变量。分类是疾病诊断的重要组成部分，但也与确定风险因素/变量有关。引入了两种分类技术，分别是支持向量机（SVM），多层感知器集合（MLPE）和一种高级回归技术，具有二项式分布的通用加性模型（GAM）和“ logit”链接，用于诊断和风险因素/变量识别。结果：GAM解释了65％的偏差，调整后的R平方值约为0.70。在支持向量机下进行了敏感性分析，这是此数据集的最佳模型，分类准确率约为85％。 MLPE的分类准确率大约为82％。最大心率，血管，旧峰，胸痛，th扫描是通过SVM和GAM进行敏感性分析得出的最重要因素/变量。结论：本文试图通过概率模型消除一些有关心脏病的新信息，这些信息可能会为利用个体患者危险因素和特定治疗获益的治疗决策提供更好的帮助。这些发现可能有助于医生更好地治疗。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号