面向健康体检数据的多目标Top-k频繁模式挖掘方法
DOI:
作者:
作者单位:

1.安徽大学 计算智能与信号处理教育部重点实验室, 安徽大学计算机科学与技术学院;2.安徽大学计算机科学与技术学院;3.合肥市骨科医院

作者简介:

通讯作者:

中图分类号:

TP18

基金项目:

科技部 2030-“新一代人工智能”重大项目(2018AAA0100105),国家自然科学优秀青年基金项目(61822301),国家自然科学基金 (61822301,62076001, U1804262), 安徽省自然科学基金项目(1908085MF219,2008085QF294),安徽省重点研发项目(202004j07020005),安徽高校自然科学研究项目(KJ2019A0029)


A multi-objective Top-k frequent pattern mining approach oriented for medical health data
Author:
Affiliation:

1.Key Laboratory of Intelligent Computing Signal Processing of Ministry of Education, Anhui University, School of computer science and technology, Anhui University;2.School of computer science and technology, Anhui University;3.Hefei Orthopedic Hospital

Fund Project:

the Key Project of Science and Technology Innovation 2030 supported by the Ministry of Science and Technology of China(2018AAA0100105);the National Natural Science Outstanding Youth Foundation of China(61822301);the National Natural Science Foundation of China(61822301,62076001, U1804262);the Natural Science Foundation of Anhui Province(1908085MF219); the Anhui Provincial Key Research and Development Project( 202004j07020005), the Key Program of Natural Science Project of Educational Commission of Anhui Province(KJ2019A0029)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    近年来,随着人民群众健康意识的不断增强,从海量的健康体检数据中挖掘与特定疾病相关的模式成为当前健康信息学领域的一个研究热点。为了解决现有的模式挖掘方法没有充分利用健康体检数据中检查项的异常程度与特定疾病之间相关性的问题,本文提出了一种面向健康体检数据的多目标Top-k频繁模式挖掘方法。首先,针对体检数据的特点,提出了异常度和覆盖率两个指标,在此基础上将Top-k频繁模式挖掘建模为一个多目标优化问题;其次,针对该问题,提出了一种基于偏好的种群初始化策略和一个面向模式和项的双层更新策略,并基于此设计了一种高效的进化多目标优化算法进行求解。实验结果表明,该方法所获得的Top-k个模式不仅能够有效地反映其与特定疾病之间的关联性,并且提供了多样化的模式,为健康管理提供重要的参考依据。

    Abstract:

    In recent years, with the continuous enhancement of people's health awareness, mining patterns related to specific diseases from massive health examination data has become a current research hotspot in the field of health informatics. In order to solve the problem that the existing pattern mining methods do not make full use of the correlation between the abnormality of check items in the health examination data and specific diseases, this paper proposes a multi-objective Top-k frequent pattern mining approach oriented for health examination data. First, according to the characteristics of physical examination data, two indicators of abnormality and coverage are proposed, and with these metrics, the Top-k frequent pattern mining is modeled as a multi-objective optimization problem. Second, an efficient evolutionary multi-objective optimization algorithm is designed to solve the problem, in which a preference-based population initialization strategy and a two-layer update strategy oriented to patterns and items are respectively proposed. The experimental results show that the achieved Top-k frequent patterns not only effectively reflect the correlation with the specific diseases, but also provide a variety of patterns, which gives an important reference for health management.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-04-16
  • 最后修改日期:2021-08-31
  • 录用日期:2021-09-10
  • 在线发布日期:
  • 出版日期: