

ORIGINAL ARTICLE 

Year : 2021  Volume
: 11
 Issue : 2  Page : 7991 

Evaluating morphological features of electrocardiogram signals for diagnosing of myocardial infarction using classificationbased feature selection
Seyed Ataddin Mahmoudinejad^{1}, Naser Safdarian^{2}
^{1} Department of Medical Physics and Biomedical Engineering, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran ^{2} School of Medicine, Dezful University of Medical Sciences, Dezful; Young Researchers and Elite Club, Tabriz Branch, Islamic Azad University, Tabriz, Iran
Date of Submission  06Feb2020 
Date of Decision  12Mar2020 
Date of Acceptance  25Jul2020 
Date of Web Publication  24May2021 
Correspondence Address: Seyed Ataddin Mahmoudinejad Ph.D. Candidate in Tehran University of Medical Sciences, Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran Iran
Source of Support: None, Conflict of Interest: None
DOI: 10.4103/jmss.JMSS_12_20
Background: Cardiovascular disease (CVD) is the first cause of world death, and myocardial infarction (MI) is one of the five primary disorders of CVDs which the patient electrocardiogram (ECG) analysis plays a dominant role in MI diagnosis. This research aims to evaluate some extracted features of ECG data to diagnose MI. Methods: In this paper, we used the PhysikalischTechnische Bundesanstalt database and extracted some morphological features, such as total integral of ECG, integral of the Twave section, integral of the QRS complex, and Jpoint elevation from a cycle of normal and abnormal ECG waveforms. Since the morphology of healthy and abnormal ECG signals is different, we applied integral to different ECG cycles and intervals. We executed 100 of iterations on a 10fold and 5fold crossvalidation method and calculated the average of statistical parameters to show the performance and stability of four classifiers, namely logistic regression (LR), simple decision tree, weighted Knearest neighbor, and linear support vector machine. Furthermore, different combinations of proposed features were employed as a feature selection procedure based on classifier's performance using the aforementioned trained classifiers. Results: The results of our proposed method to diagnose MI utilizing all the proposed features with an LR classifier include 90.37%, 94.87%, and 86.44% for accuracy, sensitivity, specificity, respectively. Also, we calculated the standard deviation value for the accuracy of 0.006. Conclusion: Our proposed classificationbased method successfully classified and diagnosed MI using different combinations of presented features. Consequently, all proposed features are valuable in MI diagnosis and are praiseworthy for future works.
Keywords: Biological signal processing, classification, crossvalidation, electrocardiography, feature selection, linear support vector machine, myocardial infarction, simple tree, weighted Knearest neighbor
How to cite this article: Mahmoudinejad SA, Safdarian N. Evaluating morphological features of electrocardiogram signals for diagnosing of myocardial infarction using classificationbased feature selection. J Med Signals Sens 2021;11:7991 
How to cite this URL: Mahmoudinejad SA, Safdarian N. Evaluating morphological features of electrocardiogram signals for diagnosing of myocardial infarction using classificationbased feature selection. J Med Signals Sens [serial online] 2021 [cited 2021 Jun 14];11:7991. Available from: https://www.jmssjournal.net/text.asp?2021/11/2/79/316678 
Introduction   
Myocardial infarction
The first cause of world death is cardiovascular disease (CVD), which causes more death than other diseases annually. In 2015, about 17.7 million people died from CVD, accounting for 31% of the world's total deaths, of which about 7.4 million people died from the stroke and 7.6 million deaths were because of coronary heart disease. Myocardial infarction (MI) is one of the five main complications of CVDs, which include persistent angina, unstable angina, heart failure, MI, and sudden death.^{[1],[2]} Consequently, early diagnosis of MI has critical importance in medical applications for the effective treatment of patients.
MI or “heart attack” occurs when one of the coronary arteries is completely blocked. A region of the myocardium fed by the coronary artery dies, and loses its blood and deprives of oxygen and other nutrients. The sudden and total occlusion of the artery, which precipitates the infarction, is usually due to coronary artery spasm or superimposed thrombosis.^{[3]} As the STsegment is the most widely used feature for MI detection, the onset of MI can be distinguished into two kinds of MI, namely an STsegment elevation MI, which is caused by the blockage of an artery from the heart, and a nonSTsegment elevation MI, which depends on Tinversion or ST depression.^{[4],[5],[6],[7]}
Usually, in most cases of infarction, electrocardiogram (ECG) signal processing based on the investigation of the morphology of multilead ECG results in precise diagnosis.^{[8]} Early ECG variations and specific electrocardiographic changes associated with MI occurred with the onset of myocardial dysfunctions.^{[3],[7]}
During acute MI, the ECG evolves through three stages:
 Twave peaking followed by Twave inversion
 STsegment elevation
 Emergence of a new Qwave.
However, during an acute infarction, commonly, all three states can appear in the ECG, but it is possible to have any of these conditions without another one. For example, it is not unusual at all that the STsegment elevation occurs without Twave inversion. Considering all the three states, we can predict MI with the least error.^{[3],[9]} Some of these methods introduced are as follows:
 If the Twave peaks and then reverses, it represents myocardial ischemia. In addition, if an acute MI occurs, then Twave can remain reverse about more than a few months to several years
 If the STsegment raises and joins with the Twave, then it indicates a myocardial injury. Furthermore, the STsegment usually recovers to baseline within a few hours when infarction happens
 If a new Qwave appears within hours to days, then it signifies MI. In most cases, the Qwave persists for the rest of the patient life.^{[3]}
The localization of infarction is essential since its prognostic and therapeutic effects are in the heart regions, which are already dead. Infarctions categorized into several general anatomic categories. These are inferior infarctions, lateral infarctions, anterior infarctions, and posterior infarctions. Combinations can also be realized, such as anterolateral infarctions, which are very common.^{[3]}
 Inferior infarction: The structural electrocardiographic changes of infarction reveal in the inferior leads such as II, III, and AVF
 Lateral infarction: In this infarction, the occlusion of the left circumflex artery leading to changes in the left lateral leads AVL, I, V5, and V6
 Anterior infarction: This infarction marked by specific changes in the precordial leads (V1–V6)
 Posterior infarction: In this infarction, since there are no leads overlying the posterior wall of the heart, therefore, the anterior leads, especially V1, are needed to investigate for reciprocal changes, which are indeed essential to diagnose posterior MI.
Research background
According to all studies, MI diagnosing generally constitutes four major phases, including signal preprocessing step, ECG wave segmentation, feature extraction, and classification. In general, signal features extracted from the timedomain, the frequencydomain, and the transformdomain.^{[5],[10]} The importance of an efficient feature selection method is undeniable and affects the overall performance of classification methods.
There are several automated, semiautomated, or manual signal segmentation approaches for signal feature extraction. For example, Al Touma et al. proposed a system which utilized two algorithms, and the first algorithm could detect the critical points on the ECG waveforms and the second algorithm could detect possible MI based on the analysis of the aforementioned critical points.^{[4]} Further, Gupta and Kundu applied a statistical index, namely dissimilarity factor “D” to classify normal and inferior MI data, without the need for any direct clinical feature extraction. Accordingly, the Twave and the QRS sections of inferior MI datasets were automatically extracted from the leads II, III, and aVF and then compared with corresponding segments of healthy patients using the PhysikalischTechnische Bundesanstalt (PTB) database.^{[11]}
Some research analyzes and investigates the effects and arrangements of each MI feature. Carley presented that the location of leads V1–V6 depends on historical convention, and there is clear evidence that STelevation, indicative of acute MI, exists outside of the standard 12lead ECG.^{[12]} Accordingly, we consider it as an essential factor to detect and localize MI in the current study. Besides, Muhammad Arif et al. employed timedomain features of each beat in the ECG signal, including Twave amplitude, Qwave, and STelevation using Knearest neighbor (KNN) classifier in an automated scheme for diagnosis and localization of MI.^{[13]} Similarly, Safdarian et al. applied two new timedomain features including total integral and Twave integral as morphological signal features to detect and localize the MI in the left ventricle of the heart.^{[14]}
On the other hand, some researches focused on the features in the frequency domain or the transform domain of the ECG signal. As an example, Nidhyananthan et al. proposed a waveletbased method, which applied for detecting MI along with useridentity using a support vector machine (SVM) classifier to classify the normal and abnormal cases in these signals. In addition, the RR interval utilized to authenticate the ECG signal.^{[15]} In addition, Sharma et al. represented a novel technique on multiscale energy and Eigen space approach to detect and localize MI from multilead ECG. Moreover, the nearest neighbor (KNN), and the SVM, along with both linear and radial basis function kernels applied as classifiers.^{[16]}
Moreover, Noorian et al. proposed the radial basis function neural networks classifier with wavelet coefficient as features extracted from frank lead to diagnose and localize MI.^{[17]} Moreover, Tripathy et al. proposed the multiscale convolutional neural network for automatic MI localization using the FourierBessel (FB) series expansionbased empirical wavelet transform (EWT) for signal segmentation and feature extraction.^{[8]} Concerning the use of neural networks, similarly, Zhang et al. proposed a multilead bidirectionalgated recurrent unit neural network, and their results show that the algorithm has higher sensitivity, positive predictivity, accuracy, and universality.^{[7]}
In this study, we focused on the feature selection section as an essential part of a successful MI diagnosing and classification. We presented a classificationbased feature selection method to analyze the worthiness of the extracted ECG morphological features and to tackle the problem of feature selection.
Objectives
The main objective of our study is to evaluate the efficiency of the proposed extracted morphological features from ECG data in MI diagnosis and not necessarily diagnosing MI only. The higher the quality of ECG extracted features, the better the results in the early diagnosis of MI.
Materials and Methods   
Signal acquisition
In this study, we proposed a classificationbased feature selection procedure to evaluate the ECG morphological features for diagnosing MI. At this point, we collect our ECG data from PhysioNet. In the PTB database, the ECGs were derived from patients with various heart diseases and healthy volunteers.^{[18]}
In our research, we have assigned two diagnostic classes, including 148 MI subjects and 52 standard control subjects, since we investigated MI types. Consequently, the sum of 59 healthy ECG records alongside 156 MI records forms the complete database of 215 signal records.
Signal preprocessing and feature extraction from electrocardiogram signals
The raw ECG records contain various artifacts such as muscle noise, power line interference noise, and baseline wander.^{[4],[10]} In this article, we implemented two filters, namely the bandpass FIR filter (ECG band 0.5–150 Hz) and IIR notch filter (55 Hz) to remove noise from ECG signals. The notch filter removes the power line interference noise of 50–60 Hz. Moreover, the bandpass FIR filter is designed using a minimum order Kaiser window for the removal of ECG baseline wander. We utilized MATLAB filter design application and the design configuration summary of each filter presented and also, the Bode plot for the filters and also, signal optimization are shown in [Figure 1] and [Figure 2].  Figure 1: (a) Notch filter magnitude response (dB) and phase response; (b) FIR bandpass Filter magnitude response (dB) and phase response
Click here to view 
 Figure 2: (a) Raw electrocardiogram signal, (b) electrocardiogram baseline wander correction, (c) filtered electrocardiogram signal, (d) final smoothed filtered electrocardiogram signal, (e) raw electrocardiogram periodogram power spectral density estimate, and (f) optimized electrocardiogram periodogram power spectral density estimate
Click here to view 
IIR notch filter
 Filter order: 2
 Sampling frequency: 1000
 Notch Bandwidth: 10 Hza
 Passband ripple (Apass): 0.1 dB
FIR bandpass filter
 Filter order: 124
 Sampling frequency: 1000
 Window: Kaiser
 End of the first stopband (Fstop1): 0.5 Hz
 Beginning of the passband (Fpass1): 10 Hz
 End of the passband (Fpass2): 100 Hz
 Beginning of the second stopband (Fstop2): 150 Hz
 Passband ripple (Apass): 0.1 dB
 Stopband attenuation for both stopbands (Astop1, Astop2): 40 dB.
In this review, we focused on ECG features and identified fundamental characteristics to extract, classify, and eventually determine exact MI types, which are presented below:
 Peaking of the Twave (hyperacute Twave) followed by inversion of the Twave
 Elevation of the ST segment.
The idea is to integrate the ECG signal and extract the above features. Accordingly, we compute definite integrals of “ECG cycle,” “QRS complex,” and “Twave” using “trapz” function in MATLAB (R2016b) software. As a result, we can extract morphology variations and hyperacute Twave features of ECG signal in MI as well. Furthermore, we use ECG Jpoint elevation value to estimate STelevation and also extract it as a feature from three ECG leads, namely lead I, lead II, and lead V2.
According to the MATLAB software, the “trapz” operates numerical integration via the trapezoidal method, which can divide the area down into trapezoidal segments to approximate the integration over an interval. Therefore, the approximation is as follows:
Where the spacing between each point is equal to the scalar value .
Thus, we obtain a general “features matrix” with 215 rows and 11 columns, which include features and labels. Consequently, the features extraction process of ECG signals accomplishes. The final features matrix arrays contain {F1, F2, F3, F4, F5, F6, F7}; features accompany with two class and four class labels.
 F1: Integral of a complete ECG cycle
 F2: Integral of ORS complex
 F3: Integral of Twave
 F4: ST elevation in lead I
 F5: ST elevation in lead II
 F6: ST elevation in lead V2
 F7: Twave inversion (0 for no inversion and 1 for inversion).
The laptop we used had Windows 8.1 as the operating system, a Core i7 CPU, and 12 GB of RAM.
In this study, initially, we create a database from ECGextracted features. Subsequently, we can classify MI and obtain the results using a 5fold crossvalidation technique to detect MI from ECG data. The 5fold crossvalidation divides the ECG data into four training datasets and a validation dataset as the inputs of four classifiers, namely the fine decision tree, the linear SVM (LSVM), the weighted KNN, and the logistic regression (LR). We suggest the diagnosis of MI by evaluating ECG data using two procedures, including the twoclass and the fourclass classification. The dataset in the twoclass classification method contains healthful records and MI records, however; in the fourclass classification procedure, we have healthful records, inferior, anterior, and posterior MI records.
Statistical analysis
Statistical analyses to investigate the relationship between the features
To test the normality of the data (features extracted from the ECG signals), the test of the normality of the following features was performed in SPSS software (Version 20, IBM Corp. Released 2011. IBM SPSS Statistics for Windows, Version 20.0. Armonk, NY: IBM Corp.).
Features include F1, F2, F3, F4, F5, F6, and F7; [Table 1] shows the test results for the above features.
As shown in [Table 1], and according to P value and the skewness results for all seven sets of extracted features, it indicates that the features are abnormal. Furthermore, [Table 1] represents the comparison of variance status and skewness values of all three groups of the above characteristics.
Since the data of all seven groups of features do not have a normal distribution, parametric tests (such as ttest or ANOVA test) cannot be used to analyze these features. Therefore, we must use nonparametric analyses to investigate the independence of features. We then examine whether there is a significant difference between the seven sets of extracted features using the Friedman nonparametric test.
The results of Friedman nonparametric test show that there is a significant difference between the seven groups of different features due to the P < 0.01. In other words, the Chisquare value of Friedman's test is confirmed with an error of <1% and a confidence level of 99%. According to [Table 2] and [Table 3], because of the significant difference between the different groups of extracted features, we can use them to enter classification algorithms. Finally, let us look at the accuracy, sensitivity, and specificity values used by classifying algorithms on these data.
Statistical analysis to examine the relationship between data sets of extracted features from healthy and myocardial infarction classes
To test the normality of the data (extracted features from ECG signals of healthy and patient data), the following test of the normality of the following features was performed in SPSS software (Version 20). Review classes are given below.
Moreover, the features examined in the above have seven independent classes including F1, F2, F3, F4, F5, F6, and F7.
In the previous section, the normality test was examined. At this stage, since the two healthy and MI classes represent two completely independent nonparametric groups, we use Mann–Whitney and Kolmogorov–Smirnov tests.
First, the tests above are performed on all seven features for two class labels (only healthy and only MI). [Table 4] shows the results of the above two tests and reveals that all the features extracted from healthy ECG and MI samples (except for feature 4) in both groups (with label 1 for healthy and label 2 for MI, respectively) have a P < 0.05 value for both tests, which means that there is a significant difference between the data of healthy individuals and MI for these extracted features (except for the feature number 4, of course).
Then, analyses are performed on all seven features for four class labels (healthy samples and three types of MI patient samples). At this stage, since one healthy class and three patient classes represent four completely independent groups, we use Kruskal–Wallis and median tests because these tests can be performed on more than two independent nonparametric groups.
In [Table 5], the results of the above two tests indicate that all the extracted features from the ECG signals of healthy and patient samples (except for F4 in the Kruskal–Wallis test, and F2 and F4 in the median test for all four healthy and patient classes, label 1, label 2, label 3, and label 4, respectively) have valued P < 0.05 for both tests. It means that there is a significant difference between the data of healthy people and MI patients for all the extracted features, except for the two features mentioned above. Therefore, choosing these features to distinguish between healthy data and three MI patient groups is rational and performs acceptable discrimination between the classes as well.
According to [Table 5], the significant difference between the different classes of extracted features is noticeable, and we can use them to enter classification algorithms.
Classification
In this section, we compute integral of filtered ECG signal to extract aforementioned features, and next, we choose Jpoint elevation value in mv unit manually for 215 data samples and use these characteristics to create feature matrix. Furthermore, we apply 5fold and 10fold crossvalidation for each of the classifiers and calculate the sensitivity and specificity using these two formulas below.^{[7],[10],[19],[20]}
Moreover, we executed 100 iterations for 5fold and 10fold crossvalidation on the 2class and 4class classification to show the stability of the proposed models.
Kfold crossvalidation
The crossvalidation estimate of accuracy equals the overall number of correct classifications divided by the number of samples in the dataset. Accordingly, assume that the inducer J maps a given dataset into a classifier and D_{ }_{(i}_{)} is the test set that includes sample x_{i} = (v_{i}, y_{i}). Note that δ is the mean square error function, then the crossvalidation estimate of accuracy is:^{[21]}
Logistic regression
LR is used to describe the data and explain the relationship between a dependent binary variable and one or more independent variables.^{[22],[23]} The regression analysis uses the log odds to compute output Y. Further, it tackles the problem of probabilities limitation and uses a cost function to compute the individual cost of each observation Yp. The LR equation is:
β = A0+A1(x) (7)
Further,
We define a cost function threshold of 0.5 for decisionmaking, so we have:
if Y ≥ 0.5: cost = Log(Y_{p}) (9)
if Y ≤ 0.5: cost = Log(1Y_{p}) (10)
Where β is the log odds and A0 and A1 are logistic coefficients with initial values determined by optimization, which must minimize the cost function. Hence, the probability Y using a sigmoid function is:
Linear support vector machine
In machine learning, the SVMs include supervised learning models, which are a set of points in the ndimensional data that specify the boundaries of the classes to classify the data. Consider a collection of training samples that each sample belongs to one or the other of two classes, the SVM finds the optimal hyperplane, which splits all data points of one class from those of the other class.^{[10],[24]}
This discussion follows Hastie et al.^{[24]} and Cristianini and ShaweTaylor.^{[25]} The training data define as a set of points (vectors) x_{i} along with their groups y_{i}. For some dimension d, the x_{i} ∊ R^{d}, and the y_{i} = ±1. The equation of a hyperplane is:
f(x) = βx' + b (12)
Where β ∊ R^{d} and b is a real number.
The following problem defines the optimal separating hyperplane (i.e., the decision boundary). Find β and b, which minimize β such that for all data points (x_{i},y_{i}), y_{j}f (x_{j}) ≥ 1–ξ_{i}. Hence, for i ∊ {1,…, n}, we define ξ_{i} = max (0, 1–y_{j}f (x_{j})). The support vectors are the x_{i }on the boundary for those which y_{j}f (x_{j}) = 1. For mathematical ease, the problem is usually assumed as the equivalent problem of minimizing β.^{[24],[26]} In our work and according to MATLAB, the length of beta is equal to the number of predictors used to train the model so for more information check MATLAB help. Finally, we have:
Where if C grows too large, the algorithm will reduce β, leading to a hyperplane that classifies each training sample correctly. Conversely, if C becomes too small, then the algorithm increases β causing large training error.^{[26]}
Decision tree
The decision tree learning is one of the predictive modeling methods applied in statistics, which maps observations about an item (presented in the branches) to conclude on the target value of the item (shown in the leaf). In tree classification, the target variable can accept a limited set of values; in these tree structures, leaves and branches, respectively, represent class labels and a combination of features, which leads to those class labels.^{[10],[27]}
Knearest neighbors' algorithm
One of the nonparametric methods in pattern recognition is the KNN algorithm utilized for classification, which the term nearest is the foundation of the KNN so that each new instance compares to all prior cases and then assigns to the group with closer samples to each other. Since the KNN output is a class membership, therefore, the KNN assigns the sample to the class most common among its k nearest neighbors (k is a positive integer, typically small). The sample assigns to a class of that single nearest neighbor if k = 1.^{[10],[22]}
In the weighted KNN classifier, we assign a weight 1/k to the k nearest neighbors and all others a weight zero. That is, where the i^{th} nearest neighbor assigns a weight ω_{ni} with .^{[23]}
Let denotes the weighted nearest classifier with weights . With regard to regularity conditions on class distributions, the excess risk has the following asymptotic expansions
for constants β_{1} and β_{2}, where and .
The optimal weighting scheme , which moderates the two terms in the aforementioned above, is given as follows: set for i = 1, 2, …,k* and for i = k* + 1,…,n.^{[19]}
Results   
According to [Table 6], in twoclass classification, the LR represents optimal accuracy, sensitivity, and specificity considering the standard deviation (SD) value and is more reliable caparisoning the other classifiers to diagnose MI. The comprehensive analysis of twoclass classification reveals that the LR with 90.37% of precision has a better performance in comparison with the others. In the fourclass classification, we should estimate sensitivity and specificity for each class individually. Therefore, in [Table 7], we only report accuracy and related SD values for the models. The truepositive rate (TPR) (sensitivity), the falsenegative rate (FNR), the positive predictive value (PPV), and the false predictive rate (FPR) for each classifier are determined in [Figure 3],[Figure 4],[Figure 5],[Figure 6].  Figure 3: Twoclass classification confusion matrices using 10fold crossvalidation for (a) logistic regression, (b) linear support vector machine, (c) weighted Knearest neighbor, and (d) simple tree classifiers
Click here to view 
 Figure 4: Fourclass classification confusion matrices using 10fold crossvalidation for linear support vector machine classifier
Click here to view 
 Figure 5: Fourclass classification confusion matrices using 10fold crossvalidation for weighted Knearest neighbor classifier
Click here to view 
 Figure 6: Fourclass classification confusion matrices using 10fold crossvalidation for simple tree classifier
Click here to view 
 Table 6: 5fold and 10fold crossvalidation for twoclass classification using different classifiers
Click here to view 
 Table 7: 5fold and 10fold crossvalidation for fourclass classification using different classifiers
Click here to view 
Discussion   
There are representative performance schematics of all classifiers and their confusion matrices, as shown in [Figure 3],[Figure 4],[Figure 5],[Figure 6]. Let us define each class to analyze the twoclass and fourclass classifications.
 Twoclass classification
Class 1: healthy records, Class 2: MI records.
 Fourclass classification
Class 1: healthy records, Class 2: anterior MI records, Class 3: inferior MI records, and Class 4: posterior MI records.
For example, in [Figure 3]a, the leftsided image represents the number of observations for the LR classifier. Moreover, the middle schematic indicates PPV and FPR. Furthermore, the rightsided schematic shows the TPR and FNR for each class in the twoclass classification using 10fold crossvalidation. According to the aforementioned rightsided image, TPR for the first class is 81%, declaring that 81% of normal records correctly classified as healthy ECG, and FNR for the first class is 19%, demonstrating that 19% of healthy ECG records misclassified and predicted as MI records. Accordingly, the same comprehension analytic procedure can be applied for the fourclass classification in ,[Figure 4],[Figure 5],[Figure 6] for different classifiers.
According to Tables and Figures, the performance of LSVM with 73.44% of accuracy is considerable in fourclass classification. Note that all classifiers failed to predict the fourth class successfully just because of minimal sample volume.
As our main objective is to show how valuable is the strength of extracted features in the successful diagnosis of the MI, it is more satisfying to choose a different combination of signal features as an efficient method to observe how the accuracy of each classifier changes. According to the feature matrix, it consists of seven key features, namely F1, F2, F3, F4, F5, F6, and F7. In the proposed method, three signal features remain as default. Since F1, F2, and F3 extracted from lead II, we consider them as homogenous features and should always persist.
Based on [Table 8], the precision of all classifiers with the set of {F1, F2, F3, F5, F6, F7} is more reliable in comparison with other sets of selected features in twoclass classification. Furthermore, the F4, which is the set of Jpoint elevation values of ECG signals of lead I in mv, decreases the accuracy of classifiers. On the other hand, it seems that ignoring F4 from all features leads to a significant increase in the precision of classifiers.
As noted in the Statistical Analysis section, in the twoclass analysis, the F4 feature did not differ significantly between healthy and MI samples. According to [Table 4] and [Table 5], in fourclass analysis, the same F4 feature did not make a significant difference between healthy and three MI samples, which confirms the best results of all the classifiers in distinguishing between extracted features. Note that other extracted features ({F1, F2, F3, F5, F6, F7}), following statistical analysis, and the results of the accuracy of all the classifiers presented in this article, have a significant difference, both in twoclass labeling and in fourclass labeling.  Table 8: 10fold crossvalidation for twoclass and fourclass classification with different classifiers and also various combinations of selected features
Click here to view 
In MI diagnosis studies, various approaches applied including using wavelet, applying a similarity factor between normal, MI recordkeeping, employing eigenvalue, and the energy of ECG signal as extracted features. Since our method applied mentioned classifiers, a similar approach should be compared to our work to achieve a reasonable assessment. Accordingly, [Table 9] presents a comparison of our results to other research works. In the proposed method, it is clear that in 10fold crossvalidation with the LR classifier, the accuracy, sensitivity, and specificity achieved an acceptable result in comparison with the others. According to [Table 6], [Table 7], [Table 8], [Table 9], we executed 100 iterations for 5fold and 10fold crossvalidation and calculating the statistical average and SD on the twoclass and fourclass classification to show that the proposed method along with the “Statistical Analysis” section has acceptable and reliable results and the compatibility of both results is not accidental.  Table 9: The comparative analysis of the proposed method with other methods for twoclass classification
Click here to view 
Conclusion   
In this study, we examined different extracted features from ECG data in a classificationbased feature selection method, and the results show that they are more efficient in the twoclass classification in comparison with the fourclass. The ECG Jpoint belonging to all leads is a valuable feature, but in case of better accuracy, it is recommended to extract it by precise automatic algorithms. In addition, the results show that eliminating the F4 feature, which consists of the values of Jpoint in lead I, approximately increases the precision of all classifiers in the proposed combination of features space. It is essential to point out the more accurate extraction algorithms, the better classification, and results. Finally, the proposed features are valuable for the diagnosis and localization of MI and are recommended for future works.
Suggestions and future studies
There are several suggestions for future studies. To improve the performance of classifiers, the accuracy of the feature extraction technique should increase. As a whole, these are our suggestions for future research:
 A robust and precise algorithm to detect all parts of ECG correctly
 Detect pathologic Q wave and extract it as a feature
 Using other classifiers and especially the nonlinear classifiers.
Compliance with ethical standards
Disclosure of potential conflicts of interest
Since data have obtained from PhysioNet Database free of charge, this study has not funded by any real person or legal institution.
Informed consent and research involving human participants and/or animals
This article does not contain any studies with human participants and/or animals performed by any of the authors but as we have obtained human participant's data from PhysioNet Database so, there have been no practical experiments on human by any of the present authors.
Financial support and sponsorship
None.
Conflicts of interest
There are no conflicts of interest.
Seyed Ataddin Mahmoudinejad received the B.Eng. Degree in biomedical engineering from the Islamic Azad University of Dezful, Dezful, Iran, in 2013. In 2015, he graduated from the M.Sc. Eng. in biomedical engineering from Islamic Azad University of Kazeroon, Kazeroon, Iran. Since then, he has been with the Technology Development Centre, Dezful University of Medical Sciences, Dezful, Iran. Also, he is currently a member of the Intellectual Property Committee of the Medical University of Dezful. In 2019, he became a PhD student at the medical university of Tehran, Tehran, Iran. His researches interests are biomedical signal processing artificial intelligence and medical robotic. He studies biomedical engineering in the field of medical robotic until now.
Email: [email protected]
Naser Safdarian received M.Sc in Biomedical Engineering from Science and Research Branch, Islamic Azad University, Tehran, Iran, in 2011. His researches interests are Biomedical Signal Processing, especially ECG and EMG Signal Processing, Intelligence Algorithms, Optimization, and Medical Image Processing. He is currently a PhD student in Biomedical Engineering.
Email: [email protected]
References   
1.  Cardiovascular Diseases (CVDs), Fact Sheet. World Health Organization, Media Centre; Updated May, 2017. 
2.  Mendis S, Thygesen K, Kuulasmaa K, Giampaoli S, Mähönen M, Ngu Blackett K, et al. World Health Organization definition of myocardial infarction: 200809 revision. Int J Epidemiol 2011;40:13946. 
3.  Thaler M. The only EKG Book you'll Ever Need. Lippincott Williams & Wilkins (LWW); 2017. 
4.  Al Touma A, Tafreshi R, Khan M, editors. Detection of Cardiovascular Abnormalities Through 5Lead System Algorithm. IEEE: 2016 IEEEEMBS International Conference on Biomedical and Health Informatics (BHI); 2016. 
5.  Lu H, Ong K, Chia P, editors. An automated ECG classification system based on a neurofuzzy system. Comput Cardiol 2000;27:38790. 
6.  de Bliek EC. ST elevation: Differential diagnosis and caveats. A comprehensive review to help distinguish ST elevation myocardial infarction from nonischemic etiologies of ST elevation. Turk J Emerg Med 2018;18:10. 
7.  Zhang X, Li R, Dai H, Liu Y, Zhou B, Wang Z. Localization of Myocardial Infarction with Multilead Bidirectional Gated Recurrent Unit Neural Network. IEEE Access; 2019. 
8.  Tripathy RK, Bhattacharyya A, Pachori RB. Localization of Myocardial Infarction from Multilead ECG signals using multiscale analysis and convolutional neural network. IEEE Sensors J 2019;19:1143748. 
9.  Lines GT, de Oliveira BL, Skavhaug O, Maleckar MM. Simple twave metrics may better predict early ischemia as compared to st segment. IEEE Trans Biomed Eng 2016;64:13059. 
10.  Ansari S, Farzaneh N, Duda M, Horan K, Andersson HB, Goldberger ZD, et al. A review of automated methods for detection of myocardial ischemia and infarction using electrocardiogram and electronic health records. IEEE Rev Biomed Eng 2017;10:26498. 
11.  Gupta R, Kundu P, editors. Dissimilarity Factor Based Classification of Inferior Myocardial Infarction ECG. IEEE: 2016 IEEE First International Conference on Control, Measurement and Instrumentation (CMI); 2016. 
12.  Carley SD. Beyond the 12 lead: Review of the use of additional leads for the early electrocardiographic diagnosis of acute myocardial infarction. Emerg Med (Fremantle) 2003;15:14354. 
13.  Arif M, Malagore IA, Afsar FA. Detection and localization of myocardial infarction using Knearest neighbor classifier. J Med Syst 2012;36:27989. 
14.  Safdarian N, Dabanloo NJ, Attarodi G. A new pattern recognition method for detection and localization of myocardial infarction using Twave integral and total integral as extracted features from one cycle of ECG signal. J Biomed Sci Eng 2014;7:818. 
15.  Nidhyananthan SS, Saranya S, Kumari RS, editors. Myocardial Infarction Detection and Heart Patient Identity Verification. IEEE: 2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET); 2016. 
16.  Sharma LN, Tripathy RK, Dandapat S. Multiscale energy and eigenspace approach to detection and localization of myocardial infarction. IEEE Trans Biomed Eng 2015;62:182737. 
17.  Noorian A, Dabanloo NJ, Parvaneh S, editors. Wavelet based method for localization of myocardial infarction using the electrocardiogram. Comput Cardiol 2014;2014:6458. 
18.  Goldberger AL, Amaral LA, Glass L, Hausdorff JM, Ivanov PC, Mark RG, et al. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation 2000;101:E21520. 
19.  Samworth RJ. Optimal weighted nearest neighbour classifiers. Ann Statist 2012;40:273363. 
20.  Wu J, Bao Y, Chan SC, Wu H, Zhang L, Wei XG, editors. Myocardial Infarction Detection and ClassificationA New MultiScale Deep Feature Learning Approach. IEEE: 2016 IEEE International Conference on Digital Signal Processing (DSP); 2016. 
21.  Kohavi R, editor. A Study of CrossValidation and Bootstrap for Accuracy Estimation and Model Selection. Montreal, Canada: Ijcai; 1995. 
22.  Altman NS. An introduction to kernel and nearestneighbor nonparametric regression. Am Statist 1992;46:17585. 
23.  Stone CJ. Consistent nonparametric regression. Ann Statist 1977;5:595620. 
24.  Hastie T, Tibshirani R, Friedman J, Franklin J. The elements of statistical learning: Data mining, inference and prediction. Mathem Intelligencer 2005;27:835. 
25.  Cristianini N, ShaweTaylor J. An Introduction to Support Vector Machines and Other KernelBased Learning Methods. . London: Cambridge University Press; 2000. 
26.  Cortes C, Vapnik VN. Support vector networks. Machine Learning 1995;20:27395. 
27.  Quinlan JR. Induction of decision trees. Machine Learning 1986;1:81106. 
[Figure 1], [Figure 2], [Figure 3], [Figure 4], [Figure 5], [Figure 6]
[Table 1], [Table 2], [Table 3], [Table 4], [Table 5], [Table 6], [Table 7], [Table 8], [Table 9]
