Enhancement of accuracy and reproducibility of parametric modeling for estimating abnormal intra-QRS potentials in signal-averaged electrocardiograms

Lin, Chun‐Cheng

doi:10.1016/j.medengphy.2007.10.001

Cited by 8 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, looking at all the combinations of AQR parameters, we obtained a maximum TPA of 95.8% with 100% specificity and 90% sensitivity by taking a linear combination of 60 AQRs. This performance is higher than results of prior studies at 78.8%, 90.2% (but only 43.8% sensitivity) and 88.9% obtained using a DCT-domain parametric modeling approach [11,12,24], as well as the 83.3% achieved using a finite-impulse-response linear prediction model [14]. …”

Section: Discussioncontrasting

confidence: 65%

“…In this study, the maximum TPA among all the individual AQR parameters was 83.3%, including the X, Y and Z cases. These results are superior to those achieved by a DCT-domain parametric modeling approach with 75.8%, 78.0% and 75% [11,12,24], as well as the 79.2% obtained using a finite-impulse-response linear prediction modeling approach [14]. Furthermore, looking at all the combinations of AQR parameters, we obtained a maximum TPA of 95.8% with 100% specificity and 90% sensitivity by taking a linear combination of 60 AQRs.…”

Section: Discussionmentioning

confidence: 59%

“…A study [24] clearly indicated that the superposition of a normal QRS complex simulated by a low order ARMA(6, 6) parametric model, and an AIQP simulated as a white noise, in low frequency does reduce the accuracy and the reproducibility of AIQP estimates. Additionally, practical applications show reduced estimate accuracy owing to the high frequency components contained in a normal QRS complex [13,14].…”

Section: Discussionmentioning

confidence: 99%

“…UIQP refers to a collection of signals with abrupt slope changes distributed over a QRS complex, possibly including a sharp QRS waveform and a rapidly varying AIQP, and can be detected at locations where slope discontinuities occur by the prediction error of a linear prediction model. The main difference between the UIQP and AIQP analyses is that the UIQP analysis is to detect the slope changes induced by the AIQP [13,14], while the AIQP analysis is to extract the AIQP waveform [11,12,24]. As previously presented [11,12,24], a parametric modeling approach is based on the combination of multiple ARMA(2, 2) models, such that a QRS complex of interest can be analyzed in the DCT domain and AIQP can be estimated by means of modeling residuals.…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Analysis of Abnormal Intra-QRS Potentials in Signal-Averaged Electrocardiograms Using a Radial Basis Function Neural Network

Lin

2016

Sensors

Self Cite

View full text Add to dashboard Cite

Abnormal intra-QRS potentials (AIQPs) are commonly observed in patients at high risk for ventricular tachycardia. We present a method for approximating a measured QRS complex using a non-linear neural network with all radial basis functions having the same smoothness. We extracted the high frequency, but low amplitude intra-QRS potentials using the approximation error to identify possible ventricular tachycardia. With a specified number of neurons, we performed an orthogonal least squares algorithm to determine the center of each Gaussian radial basis function. We found that the AIQP estimation error arising from part of the normal QRS complex could cause clinicians to misjudge patients with ventricular tachycardia. Our results also show that it is possible to correct this misjudgment by combining multiple AIQP parameters estimated using various spread parameters and numbers of neurons. Clinical trials demonstrate that higher AIQP-to-QRS ratios in the X, Y and Z leads are visible in patients with ventricular tachycardia than in normal subjects. A linear combination of 60 AIQP-to-QRS ratios can achieve 100% specificity, 90% sensitivity, and 95.8% total prediction accuracy for diagnosing ventricular tachycardia.

show abstract