• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Frontiers of Information Technology >A Machine Learning-Based Comparative Study for the Classification of Septic Shock Using Microarray Gene Expression Data
【24h】

A Machine Learning-Based Comparative Study for the Classification of Septic Shock Using Microarray Gene Expression Data

机译：基于机器学习的使用微阵列基因表达数据对败血性休克进行分类的比较研究

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

摘要

Septic shock is metabolic deviations at the cellular and cardiovascular level that causes enhanced risk of mortality in patients being treated in ICU and is prevalent all over the globe. Microarray gene profiling technology allows professionals to monitor the gene expression of the whole cell is diseased as well as a control group. In this paper, we have retrieved microarray gene expression data on septic shock and have applied different machine learning models to classify it against healthy subjects. All machine learning models classified reasonably between septic shock patients and healthy subjects with relatively good accuracy. By using this methodology, we have selected sets of best features that provide probable biomarkers of septic shock. The features elimination algorithms including chi-square, RFE and correlation-based classified helped in increasing the accuracy and selection of best discriminator genes.
机译：败血性休克是细胞和心血管水平的代谢异常，导致接受ICU治疗的患者死亡风险增加，并且在全球范围内普遍存在。芯片基因谱分析技术使专业人员能够监测整个患病细胞以及对照组的基因表达。在本文中，我们检索了败血性休克的微阵列基因表达数据，并应用了不同的机器学习模型对健康受试者进行分类。所有机器学习模型在败血性休克患者和健康受试者之间进行合理分类，且准确性相对较高。通过使用这种方法，我们选择了一些最佳功能，可以提供败血性休克的生物标志物。特征消除算法（包括卡方，RFE和基于相关性的分类）有助于提高准确性和最佳区分基因的选择。

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