Evaluation of Rule Interestingness Measures with a Clinical Dataset on Hepatitis
Evaluation of Rule Interestingness Measures with a Clinical Dataset on Hepatitis
复制标题
DOI：
10.1007/978-3-540-30116-5_34
复制
发表时间：
2004-09
期刊：
影响因子：
--
通讯作者：
M. Ohsaki;Shinya Kitaguchi;K. Okamoto;H. Yokoi;Takahira Yamaguchi
中科院分区：
文献类型：
--
作者：
M. Ohsaki;Shinya Kitaguchi;K. Okamoto;H. Yokoi;Takahira Yamaguchi
本研究实证研究了传统规则兴趣度度量的性能，并讨论了它们在医学领域通过人机交互支持 KDD 的实用性。我们比较了医学专家的评估结果和从肝炎数据集中发现的规则的选定措施的评估结果。 Recall、Jaccard、Kappa、CST、χ2-M 和 Peculiarity 表现出最高的性能，并且许多指标在我们的实验条件下表现出互补趋势。这些结果表明，某些措施可以在一定程度上预测真正有趣的规则，并且它们的组合使用将是有用的。
This research empirically investigates the performance of conventional rule interestingness measures and discusses their practicality for supporting KDD through human-system interaction in medical domain. We compared the evaluation results by a medical expert and those by selected measures for the rules discovered from a dataset on hepatitis. Recall, Jaccard, Kappa, CST,χ2-M, and Peculiarity demonstrated the highest performance, and many measures showed a complementary trend under our experimental conditions. These results indicate that some measures can predict really interesting rules at a certain level and that their combinational use will be useful.