基于模糊聚类与机器学习的医疗数据统计分析算法设计  

Design of medical data statistical analysis algorithm based on fuzzy clustering and machine learning

作　　者：王晨宇[1] 陈曦 林昊 潘利民[1] 徐国刚[1] WANG Chenyu;CHEN Xi;LIN Hao;PAN Limin;XU Guogang(The First Affiliated Hospital of Hebei North University,Zhangjiakou 075000,China)

机构地区：[1]河北北方学院附属第一医院,河北张家口075000

出　　处：《电子设计工程》2022年第9期112-115,120,共5页Electronic Design Engineering

基　　金：河北省张家口市科技攻关计划项目(1821145I)。

摘　　要：针对传统单病种医疗费用分析方法在处理大量数据时存在效率低下的问题,提出了一种基于模糊聚类和机器学习的医疗数据统计分析算法。该方法利用模糊聚类在处理大量相关性较强数据上的优势,得到了影响医疗费用的因素;同时,对机器学习中的BP神经网络进行改进,设置双层分类器来提高算法的聚类精准度。对比实验结果表明,文中所提出医疗数据统计分析算法的平均分类精准度比基于Adaboost算法的数据分析算法高5.75%,证明了该统计分析算法的有效性与优越性。In view of the low efficiency of the traditional single disease medical cost analysis method in processing a large number of data,a medical data statistical analysis algorithm based on fuzzy clustering and machine learning is proposed. Using the advantage of fuzzy clustering in dealing with a large number of highly correlated data,this method obtains the factors affecting medical expenses;At the same time,the BP neural network in machine learning is improved and a double-layer classifier is set to improve the clustering accuracy of the algorithm. The comparative experimental results show that the average classification accuracy of the proposed medical data statistical analysis algorithm is 5.75% higher than that of the data analysis algorithm based on Adaboost algorithm,which proves the effectiveness and superiority of the statistical analysis algorithm.

关 键 词：医疗数据统计分析算法 单病种 模糊聚类 改进BP神经网络 机器学习 ADABOOST 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]