Applications of association rule mining in health informatics: a survey
Applications of association rule mining in health informatics: a survey
复制标题
DOI：
10.1007/s10462-016-9483-9
复制
发表时间：
2017-03-01
影响因子：
12
通讯作者：
Guergachi, Aziz
中科院分区：
文献类型：
--
作者：
Altaf, Wasif;Shahbaz, Muhammad;Guergachi, Aziz
关联规则挖掘是一种有效的数据挖掘技术，自提出以来就在卫生信息学研究中得到了广泛的应用。由于健康信息学在过去的十年里受到了研究人员的广泛关注，并且已经发展了各种子领域，因此回顾最新的健康信息学研究是有趣的，也是必要的。随着知识发现的研究者和实践者已经应用了一系列的数据挖掘技术从健康数据中提取知识，因此，关联规则挖掘技术在健康信息学领域的应用一直是本次调查的重点和详细研究。通过对2005年至2014年关联规则挖掘在健康信息学中的应用文献的批判性分析，发现Apriori算法仍然是一种广泛使用的频繁项集生成技术，而不是更有效的替代方法。此外，还确定了与关联规则挖掘在健康信息学中的应用相关的其他限制，并提出了减轻这些限制的建议。此外，还确定了关联规则挖掘应用的算法和工具，从文献调查中得出结论，并提出了未来的研究方向。
Association rule mining is an effective data mining technique which has been used widely in health informatics research right from its introduction. Since health informatics has received a lot of attention from researchers in last decade, and it has developed various sub-domains, so it is interesting as well as essential to review state of the art health informatics research. As knowledge discovery researchers and practitioners have applied an array of data mining techniques for knowledge extraction from health data, so the application of association rule mining techniques to health informatics domain has been focused and studied in detail in this survey. Through critical analysis of applications of association rule mining literature for health informatics from 2005 to 2014, it has been explored that, instead of the more efficient alternative approaches, the Apriori algorithm is still a widely used frequent itemset generation technique for application of association rule mining for health informatics. Moreover, other limitations related to applications of association rule mining for health informatics have also been identified and recommendations have been made to mitigate those limitations. Furthermore, the algorithms and tools utilized for application of association rule mining have also been identified, conclusions have been drawn from the literature surveyed, and future research directions have been presented.