Automatic cardiac arrhythmia detection and classification using vectorcardiograms and complex networks.

This paper intends to bring new insights in the methods for extracting features for cardiac arrhythmia detection and classification systems. We explore the possibility for utilizing vectorcardiograms (VCG) along with electrocardiograms (ECG) to get relevant informations from the heartbeats on the MIT-BIH database. For this purpose, we apply complex networks to extract features from the VCG. We follow the ANSI/AAMI EC57:1998 standard, for classifying the beats into 5 classes (N, V, S, F and Q), and de Chazal's scheme for dataset division into training and test set, with 22 folds validation setup for each set. We used the Support Vector Machinhe (SVM) classifier and the best result we chose had a global accuracy of 84.1%, while still obtaining relatively high Sensitivities and Positive Predictive Value and low False Positive Rates, when compared to other papers that follows the same evaluation methodology that we do.

Surface ECG vector characteristics of organized and disorganized atrial activity during atrial fibrillation.

BACKGROUND: The aim of this study was to examine atrial organization from vectorcardiograms (VCGs) derived from the surface ECG of atrial fibrillatory waves. METHODS: We retrieved ECGs recorded during ventricular asystole from 22 patients with AF undergoing ablation of the AV junction. The synthesized VCG of each f-wave cycle of each ECG and its plane of best fit, described by azimuth and elevation angles relative to the frontal plane, were computed. RESULTS: Fifteen of the 22 ECGs had at least 30% of the planes in a single 30-degree region of azimuth angles. Of these 15, 12 had the greatest percentage of planes with azimuth angles within 30 degrees of the sagittal plane; two were near the frontal plane; and one near the right anterior oblique plane. CONCLUSIONS: Varying degrees of organization were observed from VCGs of fibrillatory waves with the more organized examples having planes predominately near the sagittal plane.

Integraçäo de detector e classificador de complexos QRS / Integration of detector and classifying of QRS complexes

Este trabalho apresenta a integração e a avaliação conjunta de um detector e um classificador de complexos QRS, desenvolvidos separadamente. O detector foi avaliado com sinais de 47 pacientes, obtendo-se 0,20 por cento de falsos positivos e 0,26 por cento de falsos negativos. O algoritmo de classificação foi desenvolvido com 32 destes sinais, sendo avaliado com os 15 restantes, obtendo-se um índice de 97,84 por cento de classificação correta.

Abstract - This work presents the integration and evaluation of a detector and a classifier of QRS complexes. developed separately. The detector was evaluated using data from 47 patients. giving 0.20% false positives and 0,26% false negatives. The classifier was developed using 32 signals and evaluated with the remaining 15, giving 97,84% correct classification

Comparison of multigroup logistic and linear discriminant ECG and VCG classification.

The performance of logistic (LOG) and linear discriminant analysis (LDA) has been studied, both for the conventional 12-lead electrocardiogram (ECG) and the orthogonal Frank 3-lead electrocardiogram (VCG), using a large validated data base. Classification rules were derived form a learning set (N = 2446) and applied to a test set (N = 820) to differentiate between normal, left, right and biventricular hypertrophy, anterior, inferior and combined myocardial infarction (MI). Total accuracy of LOG, assuming no normal distribution and using population proportions as prior probabilities, was up to 3% higher than that of LDA, depending on the number of variables used. The 12- and 3-lead LOG and LDA formulas resulted in very similar accuracy rates, i.e., between 67 and 70% for the seven-group and between 77 and 84% for the five-group analysis. LDA posterior probabilities were systematically more extreme than LOG ones. Correct classification of normals' specificity by LDA was 5 to 9% higher, but sensitivity for different groups was 1.5 to 10% lower than by LOG, with sample size proportions as priors. Specificity could be improved by changing the priors at the cost of lower sensitivity and vice versa, both for the LDA and LOG models. Classification results at 95% specificity were only slightly different, except for anterior MI where LOG scored 6% better. Other measures of performance demonstrated that the LDA model was overconfident and that the LOG model fitted better the real class membership of the patients. In conclusion, logistic ECG and VCG models improve the total accuracy of classification by about 1 to 3% when compared to LDA. More importantly, reliability of classification represents the improvement we want to emphasize. These methods may enhance the diagnostic utility of the ECG and VCG in routine practice.

Influence of population on the classification of ECG-VCG's using linear regression techniques.

This paper describes the influence of different populations on statistical multivariate classification rules and classification results where the word "population" refers only to the frequency of diagnoses to be expected, the so-called prior probabilities. Using linear regression as a multivariate classification technique and six groups consisting of five pathological conditions and normals as test data, it has been shown: (a) That the population influences to a great extent the selection of the best ECG-VCG measurements for the classification rule. (b) That a mismatch of the populations in the learning and test sets can considerably decrease the number of correct classifications. (c) That a certain correction of the mismatch can be achieved when the prior probabilities in the learning and test sets are known, Further, the paper discusses the change of prior probabilities over the years at the Variety Club Heart Hospital in the University of Minnesota and its effect on the performance of the classification algorithm which has been used.