Detection of Atrial Fibrillation using model-based ECG analysis

Couceiro, Ricardo; Carvalho, Paulo; Henriques, J.; Antunes, M.; Harris, Matthew A.; Habetha, Jörg

doi:10.1109/icpr.2008.4761755

Cited by 86 publications

(52 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the proposed strategy [4][5] makes use of these three major physiological characteristics of AF, applied by cardiologists in their daily reasoning: i) P wave absence/presence, ii) heart rate irregularity and iii) atrial activity analysis. This knowledge-based approach increases the interpretability of the results to the medical community, while improving detection robustness.…”

Section: ) Af: Atrial Fibrillationmentioning

confidence: 99%

A Tool For ECG Analysis as a Module of a Tele-Monitoring System

et al. 2016

View full text Add to dashboard Cite

show abstract

Section: ) Af: Atrial Fibrillationmentioning

confidence: 99%

A Tool For ECG Analysis as a Module of a Tele-Monitoring System

et al. 2016

View full text Add to dashboard Cite

show abstract

“…We perform the P wave detection by comparing the candidate P wave automatically obtained by the previously mentioned wavelet-based delineation algorithm with a model of the P wave, inspired on the approach proposed by [7]. However, in our case this model was built by averaging all the annotated P waves found in the QT database [11].…”

Section: B P Wave Detectionmentioning

confidence: 99%

“…Other works, like [6], are based on the analysis of the P wave, taking also into account some statistical and electrophysiological properties of the signal, which suggests that combining various symptoms can be a key point for the implementation of accurate and efficient automatic detection algorithms. In this regard, [7] proposes the use of three different algorithms to detect AF episodes: P wave detection, heart rate analysis and atrial activity analysis. The outputs of these algorithms are subsequently combined using a neural network classifier.…”

Section: Introductionmentioning

confidence: 99%

“…Then, the outputs of both algorithms are combined using fuzzy logic to classify the heart beat under analysis as AF or normal. The scheme of the proposed technique, is similar to the one described in [7], but avoids the complex atrial activity analysis and replaces the neural network classifier by a much simpler, but yet highly accurate, fuzzy classifier. These changes allow the algorithm to meet the limited resources of the Shimmer TM , especially in terms of memory and processing power.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated real-time atrial fibrillation detection on a wearable wireless sensor platform

Rincon

Grassi

Khaled

et al. 2012

2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

Abstract-This paper presents an automated real-time atrial fibrillation (AF) detection approach that relies on the observation of two characteristic irregularities of AF episodes in the electrocardiogram (ECG) signal. The results generated after the analysis of these irregularities are subsequently analyzed in real-time using a new fuzzy classifier. We have optimized this novel AF classification framework to require very limited processing, memory storage and energy resources, which makes it able to operate in real-time on a wearable wireless sensor platform. Moreover, our experimental results indicate that the proposed on-line approach shows a similar accuracy to stateof-the-art off-line AF detectors, achieving up to 96% sensitivity and 93% specificity. Finally, we present a detailed energy study of each component of the target wearable wireless sensor platform, while executing the automated AF detection approach in a real operating scenario, in order to evaluate the lifetime of the overall system. This study indicates that the lifetime of the platform is increased by using the proposed method to detect AF in real-time and diagnose the patient with respect to a streaming application that sends the raw signal to a central coordinator (e.g., smartphone or laptop) for its ulterior processing.

show abstract

“…The fuzzy logic classifier provided sensitivity, specificity and accuracy of 100%, 76% and 88% respectively. Other techniques have been applied to classify AF rhythm including nonlinear complexity measures, wavelet transform and artificial neural networks such as described in [12][13][14][15] However, these techniques may not always be technically feasible for real-time processing of ECG data due to the requirement of high computational resources [16].…”

Section: Introductionmentioning

confidence: 99%