基于机器学习的心脏病风险预测和风险因素分析

Heart Disease Risk Prediction and Risk Factor Analysis Based on Machine Learning

心脏病对人体的危害极大,甚至威胁人们的生命。基于此,通过机器学习预测心脏病,可以指导高危人群预防并降低患病风险。相比于医院检测,机器学习可以节约大量时间,并预测心脏病发病的风险。通过查询UCI数据集收集整理的303名心脏病患者的医疗记录,运用随机森林、决策树、逻辑回归以及K近邻等模型进行实验,通过对比数据中风险因素间的相关性得出,K近邻的效果更好,预测准确率高达91%。

Heart disease does great harm to human body and even threatens people's lives.Based on this,predicting heart disease through machine learning can guide high-risk groups to prevent and reduce the risk of disease.Compared with hospital detection,machine learning can save a lot of time and predict the risk of heart disease.By querying the medical records of 303 patients with heart disease collected and collated in the UCI data set,experiments were carried out using models such as random forest,decision tree,logical regression and K-nearest neighbor.By comparing the correlation between risk factors in the data,the conclusion was drawn that K-nearest neighbor is better,and the prediction accuracy is as high as 0.91%.