What does this research mean for the field?

Artificial neural networks utilizing autoregressive parameters and periodogram samples can be effectively developed to classify ECG rhythms, including critical treat/no-treat scenarios for defibrillation. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

December 24, 2002

ECG rhythm classification using artificial neural networks

Q: What is the clinical evidence from this study?

Study design: Other. Population: Arrhythmia. Intervention: Artificial neural networks (multilayered perceptron) vs. Learning vector quantization (LVQ) algorithm. Primary outcome: ECG rhythm classification (3-class and 2-class problems).

View Full Paper

Ask AI

Bookmark

Key result

Artificial neural networks using autoregressive parameters and periodogram samples were developed for ECG rhythm classification and compared with a learning vector quantization algorithm.

Why the study?

Does an artificial neural network using AR parameters and periodogram samples improve ECG rhythm classification compared to an LVQ algorithm?

Population

ECG signals from two different ECG data bases

Comparison

Artificial neural networks using autoregressive… vs Previous method using the AR model with learning…

Design

Other

Authors

GØGeir E. ØienNorwegian University of Science and Technology NBN.A. BertelsenUniversity of Stavanger TETrygve EftestølUniversity of Stavanger

Discussion

Member takes

Implication

May aid ECG rhythm classification; extends AR-LVQ methods but leaves open clinical validation.

Structured PICO

Does an artificial neural network using AR parameters and periodogram samples improve ECG rhythm classification compared to an LVQ algorithm?

Population

ECG signals from two different ECG data bases

Intervention

Artificial neural networks (forward-connected multilayered perceptron ANNs) using autoregressive parameters and periodogram samples as feature vectors

Comparator

Previous method using the AR model with learning vector quantization (LVQ) algorithm

Outcome

Classification accuracy for a 3-class problem (normal sinus rhythm vs two abnormal rhythms) and a 2-class problem ('treat/no-treat')surrogate

Artificial neural networks can be applied to ECG rhythm classification for both diagnostic and therapeutic (treat/no-treat) decision-making.

Cite This Study

Øien et al. (2002) studied Arrhythmia. Artificial neural networks (multilayered perceptron) vs. Learning vector quantization (LVQ) algorithm was evaluated on ECG rhythm classification (3-class and 2-class problems). Artificial neural networks using autoregressive parameters and periodogram samples were developed for ECG rhythm classification and compared with a learning vector quantization algorithm.

synapsesocial.com/papers/6a1565ab5347fbb1739fb82b https://doi.org/10.1109/dspws.1996.555575

View Full Paper

Ask AI

Bookmark

ECG rhythm classification using artificial neural networks

Discussion

Member takes

Implication

Structured PICO

Cite This Study

ECG rhythm classification using artificial neural networks

Discussion

Member takes

Implication

Structured PICO

Cite This Study

Also Consider

Also Consider