Previous identification of QRS onset and offset is not essential for classifying QRS complexes in a single lead

Millet, José; Pérez, Miguel Ángel Quiñones; Joseph, G.; Mocholi, Antonio José Jimenez; Chorro, J.

doi:10.1109/cic.1997.647890

Cited by 12 publications

(16 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the inclusion of the absolute amplitude of an ECG beat and the addition of heartbeat segmentation information to the feature-extraction process [11], AND (C) THE CLUSTERING PERFORMANCE OF CLASSIFIER IX AND SYSTEM FROM [12] were worthwhile steps. This latter observation contradicts the findings of Millet et al [22].…”

Section: A Performance Of the Candidate Configurationscontrasting

confidence: 57%

Automatic Classification of Heartbeats Using ECG Morphology and Heartbeat Interval Features

Chazal

O’Dwyer²,

Reilly

2004

IEEE Trans. Biomed. Eng.

1,336

918

View full text Add to dashboard Cite

Abstract-A method for the automatic processing of the electrocardiogram (ECG) for the classification of heartbeats is presented. The method allocates manually detected heartbeats to one of the five beat classes recommended by ANSI/AAMI EC57:1998 standard, i.e., normal beat, ventricular ectopic beat (VEB), supraventricular ectopic beat (SVEB), fusion of a normal and a VEB, or unknown beat type. Data was obtained from the 44 nonpacemaker recordings of the MIT-BIH arrhythmia database. The data was split into two datasets with each dataset containing approximately 50 000 beats from 22 recordings. The first dataset was used to select a classifier configuration from candidate configurations. Twelve configurations processing feature sets derived from two ECG leads were compared. Feature sets were based on ECG morphology, heartbeat intervals, and RR-intervals. All configurations adopted a statistical classifier model utilizing supervised learning. The second dataset was used to provide an independent performance assessment of the selected configuration. This assessment resulted in a sensitivity of 75.9%, a positive predictivity of 38.5%, and a false positive rate of 4.7% for the SVEB class. For the VEB class, the sensitivity was 77.7%, the positive predictivity was 81.9%, and the false positive rate was 1.2%. These results are an improvement on previously reported results for automated heartbeat classification systems.Index Terms-Electrocardiogram (ECG), heartbeat classifier, linear discriminant analysis, statistical classifier model.

show abstract

Section: A Performance Of the Candidate Configurationscontrasting

confidence: 57%

Automatic Classification of Heartbeats Using ECG Morphology and Heartbeat Interval Features

Chazal

O’Dwyer²,

Reilly

2004

IEEE Trans. Biomed. Eng.

1,336

918

View full text Add to dashboard Cite

show abstract

“…Some authors consider that it must be done at a second detection step, when T waves have been eliminated and wave onsets and offsets have been identified [20,21,9]. …”

Section: Introductionmentioning

confidence: 99%

Ventricular beat detection in single channel electrocardiograms

Dotsinsky

Stoyanov

2004

BioMed Eng OnLine

View full text Add to dashboard Cite

show abstract

“…Besides, this detection algorithm has minimal beat detection latency, low computational consumption and fast detection ability. Table 3 Performance evaluations and comparisons AED algorithms Se (%) Sp (%) Tabakov et al [7] 99.37 99.51 Afonso et al [8] 99.59 99.56 Poli et al [9] 99.60 99.51 Dotsinsky and Stoyanov [10] 99.04 99.62 Kaiser and Findeis [11] 99.68 99.72 Datex-Ohmeda Corp. [12] 99.86 99.88 Millet et al [13] …”

Section: Experimental Results and Performance Evaluationsmentioning

confidence: 99%

A piecewise geometric analysis method for real-time ambulatory ECG detection

Zhou

Zuo

et al. 2015

THC

View full text Add to dashboard Cite

Abstract. BACKGROUND:As one of the pervasive healthcare services, Ubiquitous cardiac care (UCC) systems should have at least two significant characteristics: real-time detection capability for cardiac arrhythmia events and a small resource requirement for its computation and storage. PURPOSE: Due to the strict-constrained system support and ambulatory signal quality in the out-of-hospital pervasive healthcare applications, a dedicated real-time AED (Ambulatory Electrocardiograph Detection) algorithm has been implemented. METHODOLOGY: By adopting the piecewise geometric analysis method, this algorithm can provide a real-time continuous detection capability for QRS complexes, which consists of three main functional modules: the Data preparation; the R-wave vertex discovery; and the QRS complex recognition. Currently, this algorithm has been applied on an on-line UCC application system at the hospital for more than 30 patients. RESULT: The performance evaluation has been made not only on the standard MIT-BIH cardiac arrhythmia database but also on the clinical testing. The experiential results explore this algorithm has in average sensitivity of 99.37% and specificity of 99.72%. CONCLUSION: This AED algorithm has minimal beat detection latency and a less computation consumption, which make it meet the requirements of ubiquitous cardiac care applications.

show abstract

Previous identification of QRS onset and offset is not essential for classifying QRS complexes in a single lead

Cited by 12 publications

References 4 publications

Automatic Classification of Heartbeats Using ECG Morphology and Heartbeat Interval Features

Automatic Classification of Heartbeats Using ECG Morphology and Heartbeat Interval Features

Ventricular beat detection in single channel electrocardiograms

A piecewise geometric analysis method for real-time ambulatory ECG detection

Contact Info

Product

Resources

About