针对心血管疾病预测的改进算法模型  

Improved Algorithmic Model for Cardiovascular Disease Prediction

作　　者：刘纪敏[1] 张楷第 文龙日 贾全秋 谢创森 王菲 LIU Ji-min;ZHANG Kai-di;WEN Long-ri;JIA Quan-qiu;XIE Chuang-sen;WANG Fei(School of Intelligence Equipment,Shandong University of Science and Technology,Tai’an 271000,China;School of Computer Science and Engineering,Shandong University of Science and Technology,Qingdao 266000,China;School of Big Data,Taishan College of Science and Technology,Tai’an 271000,China)

机构地区：[1]山东科技大学智能装备学院,山东泰安271000 [2]山东科技大学计算机科学与工程学院,山东青岛266000 [3]泰山科技学院大数据学院,山东泰安271000

出　　处：《软件导刊》2021年第4期20-25,共6页Software Guide

基　　金：山东科技大学人才引进科研启动基金项目(2019RCJJ023)。

摘　　要：心血管疾病是危害人类生命的高危疾病之一,整合高新技术精准预测疾病发病的可能性、降低发病率是应对该疾病的最佳方法,也是不久的将来实现精准医学的关键技术之一。为了使数据类型标准化并保证数据格式的一致性,提高疾病预测的时效性以及疾病预测结果的精准度,整合国家标准化个人查体报告书及个人日常生活健康指标等相关信息,提出使用基于随机森林与Relief的特征选择方法进行数据降维,结合改进后的误差反向传播神经网络模型对心血管疾病进行预测。为了证实该模型的有效性,进行心血管疾病预测实验,并对实验结果进行可视化比较与分析。研究结果表明,改进的误差反向传播神经网络疾病预测模型在时效性、准确性与扩展性方面表现较好,分类精度达到98.68%,灵敏度达到98.78%,特异性达到98.56%,且预测速度提升了30%左右。Cardiovascular disease is one of the high-risk diseases that endanger human life.Integrating high and new technology to ac⁃curately predict the possibility of disease occurrence and prevent the increase of incidence is the best way to deal with this disease,and it is also one of the key technologies to realize precision medicine in the near future.In order to standardize data types and ensure the consistency of the data format,improve disease predictions accuracy and timeliness,integrate national standardization personal physi⁃cal examination report and individual daily life health indicators and other relevant information,put forward the use of random forests and Relief feature selection for data dimension reduction,combined with the improved error back propagation neural network model,to predict cardiovascular disease.In order to confirm the validity of the model,the prediction experiment of cardiovascular disease was carried out,and the experimental results were compared and analyzed visually.The results show that the improved model has high time⁃liness,accuracy and scalability.The classification accuracy,sensitivity and specificity reach 98.68%,98.78%and 98.56%,respec⁃tively and the prediction speed is improved by about 30%.

关 键 词：随机森林算法 RELIEF算法 神经网络 误差反向传播神经网络 疾病预测 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]