Detection and Localization of Myocardial Infarction using K-nearest Neighbor Classifier

Abstract

This paper presents automatic detection and localization of myocardial infarction (MI) using K-nearest neighbor (KNN) classifier. Time domain features of each beat in the ECG signal such as T wave amplitude, Q wave and ST level deviation, which are indicative of MI, are extracted from 12 leads ECG. Detection of MI aims to classify normal subjects without myocardial infarction and subjects suffering from Myocardial Infarction. For further investigation, Localization of MI is done to specify the region of infarction of the heart. Total 20,160 ECG beats from PTB database available on Physio-bank is used to investigate the performance of extracted features with KNN classifier. In the case of MI detection, sensitivity and specificity of KNN is found to be 99.9% using half of the randomly selected beats as training set and rest of the beats for testing. Moreover, Arif-Fayyaz pruning algorithm is used to prune the data which will reduce the storage requirement and computational cost of search. After pruning, sensitivity and specificity are dropped to 97% and 99.6% respectively but training is reduced by 93%. Myocardial Infarction beats are divided into ten classes based on the location of the infarction along with one class of normal subjects. Sensitivity and Specificity of above 90% is achieved for all eleven classes with overall classification accuracy of 98.8%. Some of the ECG beats are misclassified but interestingly these are misclassified to those classes whose location of infarction is near to the true classes of the ECG beats. Pruning is done on the training set for eleven classes and training set is reduced by 70% and overall classification accuracy of 98.3% is achieved. The proposed method due to its simplicity and high accuracy over the PTB database can be very helpful in correct diagnosis of MI in a practical scenario.

Multiscale Energy and Eigenspace Approach to Detection and Localization of Myocardial Infarction

“…The KNN and the SVM are supervised learning models which are used for identifying the class levels of the test feature vectors. These classifiers are used for cardiac arrhythmia detection [9], [28]. The SVM is a two class classifier.…”

“…These include time-domain method [7], [8], [9], ST-segment analysis [10] [11], wavelet transform based method [12], [13], and neural network approach [14], [15], [16]. Some of them are based on modeling techniques by training and testing the system.…”

Segmentation, alignment and statistical analysis of biosignals with application to disease classification

“…It is important to note though that they considered four different classes for their localization experiment while we consider only two. Arif et al [2] again reported a very high accuracy for MI localization, but as stated previously their results are tainted by problematic formation of training and testing sets. Again, we note that the PM performs well in MI localization as compared with other methods.…”

“…Lahiri et al [19] reported a high 96% detection rate on this data set. Arif et al [2] reported a very high detection rate of 98% but their choice of training and testing data was problematic. That is, they considered classification of heart beats rather than subjects and thus heart beat data from the same subject were included in Downloaded by [Michigan State University] at 17:41 07 February 2015 both the training and testing sets, which provided skewed results.…”

Early detection of Myocardial Infarction using WBAN

“…Their accuracy was 82.5% with specificity of 79.82% and sensitivity 85.71%. Muhammad Arif et al [11] used K-Nearest Neighbor (KNN) classifier and got an accuracy of 98.3%, sensitivity of 97% and specificity of 99.6%. In [12], Akshay Dhawan et al used Multilayer Support Vector Machine (SVM) and Genetic Algorithm (GA) to detect MI.…”