Research On Characteristic Of Common Heart Disease Based On Multiscale Entropy

In recent years,the mortality rate of cardiovascular disease in China has been the first of all diseases,the number of its patients in the next few years will continue to increase.Cardiovascular disease has brought both great economic and social burdens to our lives.Electrocardiogram(ECG)can accurately reflect the electrical activity of the heart and the performance of the heart of the working state,which is commonly used as a reference method for the clinicians to determine the majority of cardiovascular disease.However,with the growth in the number of its patients,clinicians directly determine the occurrence of cardiovascular disease by ECG will burden them greatly,and prone to misjudgment and missed sentence.Therefore,the ECG automatic analysis technology used in the diagnosis of clinical cardiovascular disease has gradually become the focus of the current field of ECG research.Multi-scale entropy(MSE)is being more and more applied in the field of biomedical signal processing because of its physical significance and systematic analysis.Based on multi-scale entropy,this paper studies the two common heart diseases of atrial fibrillation(AF)and congestive heart failure(CHF),and meanwhile proposes a multi-scale entropy-based congestive heart failure judgment algorithm and a multi-Atrial fibrillation determination algorithm for scale entropy.The main contents of this paper are as follows:(1)The characteristics of congestive heart failure were studied based on multi-scale entropy.Comparing to the differences between the heart rate variability in patients with congestive heart failure and normal subjects,it was found that the mean value of multiscale entropy of healthy people was greater than that of congestive heart attenuated patients,which indicates that the ECG signal complexity of the patients with congestive heart failure is lower than healthy people.In this paper,we propose a new algorithm for the diagnosis of congestive heart failure based on the multi-scale entropy and the mean square root of the difference between two consecutive RR intervals.We use the ECG data in the MIT-BIH ECG database to verify the performance of the algorithm.The accuracy of the algorithm is 91.67%,and the judgment result shows that the algorithm has certain clinical application value.(2)The characteristics of atrial fibrillation were studied based on multi-scale entropy,and the difference between heart rate variability of patients with atrial fibrillation and normal subjects was compared.It was found that the mean value of multi-scale entropy of healthy people was higher than that of atrial fibrillation which illustrates that heart failure in patients with ECG signal complexity is lower than healthy people.Afterwards,based on the multi-scale entropy and the ratio of the low-band energy and the high-band energy of the signal power spectrum,a new algorithm for determining the atrial fibrillation is designed.After we using the ECG data in the MIT-BIH ECG database to verify the performance of the algorithm,it shows the accuracy,sensitivity and positive predictive rate of the algorithm are 93.06%、91.67% and 94.29% respectively.