Adaptive Neural Network-Based ECG Data Compression According to the Morphology

1IntroductionElbo（ECG）offersalotofilllcorralltinfondionforthediagnosisOfheartdis－eases．Berz1，seahaormalEChcax［lrins＞llleu＂knownsituations，thcycanbeCSUghtinthelongti1Ylecontin～11xHlltoriDg．ndterrnoultonngsystemwhichcanrecord24－hoUrECGdataisoneofeffectiveme～toprovidethefun～．AlthOUghthehag6scaleICmorestohavebeeddevelopepbedeavailabletostorelOngtboeECGdsta，itisveqdifficultyandtioublesomethatalopnUmbeOfdstaisprasersandstoredortiallsillltted．InthedigitedECGdata，thereare…     

Tachyarrhythmia in a baboon: a case report

An adult baboon with multiple organ symptomatology and tachycardia was successfully treated with one-time electrical cardioversion. The case is presented to demonstrate the need to include ECG monitoring in diagnostic assessment of primate animals with nonspecific symptoms.     

1D-CADCapsNet: One dimensional deep capsule networks for coronary artery disease detection using ECG signals

PurposeCardiovascular disease (CVD) is a leading cause of death globally. Electrocardiogram (ECG), which records the electrical activity of the heart, has been used for the diagnosis of CVD. The automated and robust detection of CVD from ECG signals plays a significant role for early and accurate clinical diagnosis. The purpose of this study is to provide automated detection of coronary artery disease (CAD) from ECG signals using capsule networks (CapsNet).MethodsDeep learning-based approaches have become increasingly popular in computer aided diagnosis systems. Capsule networks are one of the new promising approaches in the field of deep learning. In this study, we used 1D version of CapsNet for the automated detection of coronary artery disease (CAD) on two second (95,300) and five second-long (38,120) ECG segments. These segments are obtained from 40 normal and 7 CAD subjects. In the experimental studies, 5-fold cross validation technique is employed to evaluate performance of the model.ResultsThe proposed model, which is named as 1D-CADCapsNet, yielded a promising 5-fold diagnosis accuracy of 99.44% and 98.62% for two- and five-second ECG signal groups, respectively. We have obtained the highest performance results using 2 s ECG segment than the state-of-art studies reported in the literature.Conclusions1D-CADCapsNet model automatically learns the pertinent representations from raw ECG data without using any hand-crafted technique and can be used as a fast and accurate diagnostic tool to help cardiologists.     

Outflow-tract ventricular tachycardia: Can 12 lead ECG during sinus rhythm identify underlying cardiac sarcoidosis?

BackgroundPatients with outflow tract ventricular tachycardia (OTVT) with normal echocardiogram are labeled as idiopathic VT (IVT). However, a subset of these patients is subsequently diagnosed with underlying cardiac sarcoidosis (CS). Objective:Whether electrocardiogram (ECG) abnormalities in sinus rhythm (SR) can differentiate underlying CS from IVT.MethodsWe retrospectively analyzed the SR-ECGs of 42 patients with OTVT/premature ventricular complexes (PVC) and normal echocardiography. All underwent advanced imaging with cardiac magnetic resonance (CMR)/¹⁸FDG PET-CT for screening of CS. Twenty-two patients had significant abnormalities in cardiac imaging and subsequently had biopsy-proven CS (Cases). Twenty patients had normal imaging and were categorized as IVT (Controls). SR-ECGs of all patients were analyzed by 2 independent, blinded observers.ResultsBaseline characteristics were comparable. Among the ECG features analyzed – fascicular (FB) or bundle branch block (BBB) was seen in 9/22 Cases vs. 1/20 controls (p = 0.01). Among patients without FB or BBB, fragmented QRS (fQRS) was present in 9/13 cases but in none of the controls (p < 0.001). Low voltage QRS was more often seen among cases as compared to controls (10/22 vs. 3/20 p = 0.03). A stepwise algorithm based on these 3 sets of ECG findings helped to diagnose CS among patients presenting with OTVT/PVC with sensitivity of 91%, specificity of 75%, a PPV of 80%, and a NPV of 88%.ConclusionsIn patients presenting with OTVT/PVC: FB/BBB, fQRS, and low QRS voltage on the baseline ECG were more often observed among patients with underlying CS as compared to true IVT. These findings may help to distinguish underlying CS among Cases presenting with OTVT/PVC.     

Comparison of arrhythmia detection by conventional Holter and a novel ambulatory ECG system using patch and Android App,over 24 h period

BackgroundAmbulatory electrocardiogram (AECG) is done for evaluation of arrhythmia. Commonly used AECG system is 24 h Holter. Patch based second generation AECG monitoring devices, which can record for longer periods, are now available.ObjectiveAndroid App based WebCardio using WiPatch is a new AECG system which records ECG in two leads for 72 h. Our study compared the arrhythmia detection by WebCardio and conventional Holter by simultaneously connecting both for 24 h in patients having indication for AECG.MethodsThe AECG of patients who had simultaneous recording with WebCardio and conventional Holter, in the department of Cardiology, Medical College, Thrissur were evaluated. Ability to detect any of the 6 arrhythmias :1) atrial fibrillation (AF), 2) atrioventricular (AV) block, 3) sinus pause of ≥3 s (SP), 4) supraventricular tachycardia (SVT), 5) premature ventricular complex (PVC) and 6) ventricular tachycardia (VT)/ventricular fibrillation (VF) was compared. Detection of each arrhythmia was also compared.Results141 patients had simultaneous recordings by both systems of AECG. The WebCardio picked up at least one of the 6 arrhythmias; AF, AV block, SP, SVT, PVC or VT/VF in 98 cases compared to 88 in the Holter (McNemars test, two tail P = 0.006). In eleven cases WebCardio detected an arrhythmia where Holter could not. In one case Holter identified an arrhythmia and WebCardio could not. Individual arrhythmias; AF, SP, SVT and VT/VF were detected equally by both systems. AV block (23 Vs 18, p = 0.0625) and PVCs (83 Vs 74, p = 0.0636) were detected in more number of cases in WebCardio. In the five cases where WebCardio alone identified AV block, four had poor quality of P wave in the Holter.ConclusionArrhythmia was picked up in more number of patients by the WebCardio compared to Holter. This was due to higher pickup of AV block and PVCs by WebCardio. Difference in AV block identification was due to better quality of P in WebCardio. WebCardio is a good alternative to Holter for AECG.     

Myocardial Infarction Detection and Localization Using Optimal Features Based Lead Specific Approach

ObjectivesObjective of this paper is to present a reliable and accurate technique for Myocardial Infarction (MI) detection and localization.Material and methodsStationary wavelet transform has been used to decompose the ECG signal. Energy, entropy and slope based features were extracted at specific wavelet bands from selected lead of ECG. k-Nearest Neighbors (kNN) with Mahalanobis distance function has been used for classification. Sensitivity (Se), specificity (Sp), positive predictivity (+P), accuracy (Acc), and area under the receiver operating characteristics curve (AUC) analyzed over 200 subjects (52 health control, 148 with MI) from Physikalisch-Technische Bundesanstalt (PTB) database has been used for performance analysis. To handle the imbalanced data adaptive synthetic (ADASYN) sampling approach has been adopted.ResultsFor detection of MI, the proposed technique has shown an AUC = 0.99, Se = 98.62%, Sp = 99.40%, PPR = 99.41% and Acc = 99.00% using 12 top ranked features, extracted from multiple leads of ECG and AUC = 0.99, Se = 98.34%, Sp = 99.77%, PPR = 99.77% and Acc = 99.05% using 12 features extracted from a single ECG lead (i.e. lead V5). For localization of MI, the proposed technique has an AUC = 0.99, Se = 98.78%, Sp = 99.86%, PPR = 98.80%, and Acc = 99.76% using 5 top ranked features from multiple leads of ECG and AUC = 0.98, Se = 96.47%, Sp = 99.60%, PPR = 96.49% and Acc = 99.28% using 8 features extracted from a single ECG lead (i.e. lead V3).ConclusionThus for MI detection and localization, the proposed technique is independent of time-domain ECG fiducial markers and can work using specific leads of ECG.     

Empirical Mode Decomposition and Wavelet Transform Based ECG Data Compression Scheme

ObjectiveIn health-care systems, compression is an essential tool to solve the storage and transmission problems. In this regard, this paper reports a new electrocardiogram (ECG) data compression scheme which employs sifting function based empirical mode decomposition (EMD) and discrete wavelet transform.MethodEMD based on sifting function is utilized to get the first intrinsic mode function (IMF). After EMD, the first IMF and four significant sifting functions are combined together. This combination is free from many irrelevant components of the signal. Discrete wavelet transform (DWT) with mother wavelet ‘bior4.4’ is applied to this combination. The transform coefficients obtained after DWT are passed through dead-zone quantization. It discards small transform coefficients lying around zero. Further, integer conversion of coefficients and run-length encoding are utilized to achieve a compressed form of ECG data.ResultsCompression performance of the proposed scheme is evaluated using 48 ECG records of the MIT-BIH arrhythmia database. In the comparison of compression results, it is observed that the proposed method exhibits better performance than many recent ECG compressors. A mean opinion score test is also conducted to evaluate the true quality of the reconstructed ECG signals.ConclusionThe proposed scheme offers better compression performance with preserving the key features of the signal very well.     

Electrocardiogram data mining based on frame classification by dynamic time warping matching

This paper presents an electrocardiogram (ECG) data mining scheme based on the ECG frame classification realised by a dynamic time warping (DTW) matching technique, which has been used successfully in speech recognition. We use the DTW to classify ECG frames because ECG and speech signals have similar non-stationary characteristics. The DTW mapping function is obtained by searching the frame from its end to start. A threshold is setup for DTW matching residual either to classify an ECG frame or to add a new class. Classification and establishment of a template set are carried out simultaneously. A frame is classified into a category with a minimal residual and satisfying a threshold requirement. A classification residual of 1.33% is achieved by the DTW for a 10-min ECG recording.     

Apolipoprotein E gene polymorphism and the risk of left ventricular dysfunction among Egyptian β-thalassemia major

In Egypt, β-thalassemia is the most common hereditary hemolytic anemia. Cardiac dysfunction, secondary to iron overload with formation of oxygen free radicals, is the most common cause of death in β-thalassemia patients. This study was designed to determine whether the allelic genotype of apolipoprotein E (Apo E), which exhibits antioxidant properties, could represent a genetic risk factor for the development of left ventricular (LV) dysfunction in β-thalassemia major. Fifty Egyptian β-thalassemia major patients were subjected to echocardiography to assess LV function. Apo E genotyping by polymerase chain reaction restriction fragment length polymorphism (PCR-RFLP) was done for all patients in addition to 50 age and sex matched healthy control subjects. Patients were classified into three groups. Group I and II were clinically asymptomatic. Group II subjects had evidence of LV dilatation, while Group III patients had clinical and echocardiographic findings of LV failure. Apo E4 allele was significantly higher among Group II and III than in controls. In conclusion, Apo E4 allele can be considered as a genetic risk factor for LV dysfunctions in β-thalassemic patients. It could be used as predictive indicator for additional risk of LV failure, particularly in asymptomatic patients with LV dilatation, requiring a closer follow-up, to prevent further disease progression.     

Is CD36 gene polymorphism in region encoding lipid-binding domain associated with early onset CAD?

CD36 is a fatty acid translocase in striated muscle cells and cardiomyocytes. Some study suggested that alterations in CD36 gene may be associated with coronary artery disease (CAD) risk. The aim of the current study was to compare the frequency of CD36 variants in region encoding lipid-binding domain in Caucasian patients with early-onset CAD, no-CAD adult controls and neonates. The study group comprised 100 patients with early onset CAD. The genetic control groups were 306 infants and 40 no-CAD adults aged over 70 years. Exons 4, 5 and 6 including fragments of flanking introns were studied using the denaturing high-performance liquid chromatography technique and direct sequencing. Changes detected in analyzed fragment of CD36: IVS3-6 T/C (rs3173798), IVS4-10 G/A (rs3211892), C311T (Thr104Ile, not described so far) in exon 5, G550A (Asp184Asn, rs138897347), C572T (Pro191Leu, rs143150225), G573A (Pro191Pro, rs5956) and A591T (Thr197Thr, rs141680676) in exon 6. No significant differences in the CD36 genotype, allele and haplotype frequencies were found between the three groups. Only borderline differences (p = 0.066) were found between early onset CAD patients and newborns in the frequencies of 591T allele (2.00% vs 0.50%) and CGCGCGT haplotype (2.00% vs 0.50%) with both IVS3-6C and 591T variant alleles. In conclusion, CD36 variants: rs3173798, rs3211892, rs138897347, rs5956, rs143150225 rs141680676 and C311T do not seem to be involved in the risk of early-onset CAD in Caucasian population.