Single-lead f-wave extraction using diffusion geometry

Malik, John; Reed, Neil; Wang, Chunli; Wu, Hau‐Tieng

doi:10.1088/1361-6579/aa707c

Cited by 22 publications

(22 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We mention that the proposed framework is flexible to study other physiological dynamics but not only for studying the sleep dynamics. For example, its variation has been applied to study f-wave from subjects with atrial fibrillation [37], intra-cranial EEG signal [38], fetal electrocardiogram (ECG) extraction from single lead trans-abdominal maternal ECG signal [39], etc.…”

Section: Fpz-cz+pz-ozmentioning

confidence: 99%

Diffuse to fuse EEG spectra – Intrinsic geometry of sleep dynamics for classification

Liu

Malik

et al. 2020

Biomedical Signal Processing and Control

Self Cite

View full text Add to dashboard Cite

We propose a novel algorithm for sleep dynamics visualization and automatic annotation by applying diffusion geometry based sensor fusion algorithm to fuse spectral information from two electroencephalograms (EEG). The diffusion geometry approach helps organize the nonlinear dynamical structure hidden in the EEG signal. The visualization is achieved by the nonlinear dimension reduction capability of the chosen diffusion geometry algorithms. For the automatic annotation purpose, the support vector machine is trained to predict the sleep stage. The prediction performance is validated on a publicly available benchmark database, Physionet Sleep-EDF [extended] SC * (SC = Sleep Cassette) and ST * (ST = Sleep Telemetry), with the leave-one-subjectout cross validation. When we have a single EEG channel (Fpz-Cz), the overall accuracy, macro F1 and Cohen's kappa achieve 82.72%,75.91% and 76.1% respectively in Sleep-EDF SC * and 78.63%, 73.58% and 69.48% in Sleep-EDF ST * . This performance is compatible with the state-of-the-art results. When we have two EEG channels (Fpz-Cz and Pz-Oz), the overall accuracy, macro F1 and Cohen's kappa achieve 84.44%,78.25% and 78.36% respectively in Sleep-EDF SC * and 79.05%, 74.73% and 70.31% in Sleep-EDF ST * . The results suggest the potential of the proposed algorithm in practical applications.

show abstract

Section: Fpz-cz+pz-ozmentioning

confidence: 99%

Diffuse to fuse EEG spectra – Intrinsic geometry of sleep dynamics for classification

Liu

Malik

et al. 2020

Biomedical Signal Processing and Control

Self Cite

View full text Add to dashboard Cite

show abstract

“…where S indicates that the index is designed for simulated signals. The normalized root mean square error (nRMSE) is another commonly used index (Castells, Rieta, Millet & Zarzoso 2005, Alcaraz & Rieta 2008, Mateo & Rieta 2013, Kheirati Roonizi & Sassi 2017, Malik et al 2017, defined by…”

Section: Performance Indices For Simulated Signalsmentioning

confidence: 99%

“…The modified ventricular residue (mVR) index was introduced with the aim of improving the performance evaluation of extracted signals with low-amplitude f -waves (Malik et al 2017). The index is defined by…”

Section: Performance Indices For Real Signalsmentioning

confidence: 99%

“…Since the QRST complexes overshadow the f waves, it is highly desirable to extract a connected f -wave signal containing more samples for characterization than what is contained in the TQ intervals, especially in short RR intervals which are rather frequent in AF (Sörnmo, Petrėnas, Laguna & Marozas 2018). Different signal processing principles have been explored for f -wave extraction which may be categorized as follows: average beat subtraction and variants (Stridh & Sörnmo 2001, Lemay, Vesin, van Oosterom, Jacquemet & Kappenberger 2007, Dai, Jiang & Li 2013, principal component analysis (Castells, Mora, Rieta, Moratal-Pérez & Millet 2005, Langley, Stridh, Rieta, Millet, Sörnmo & Murray 2006, Alcaraz & Rieta 2008, interpolation and singular spectral analysis (Sassi, Corino & Mainardi 2009), independent component analysis (Rieta, Castells, Sánchez, Zarzoso & Millet 2004, Phlypo, Zarzoso & Lemahieu 2010, adaptive filtering using an echo state network (Petrėnas, Marozas, Sörnmo & Lukosevicius 2012), extended Kalman filtering (Kheirati Roonizi & Sassi 2017), and diffusion geometry (Malik, Reed, Wang & Wu 2017).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reference database and performance evaluation of methods for extraction of atrial fibrillatory waves in the ECG

2019

View full text Add to dashboard Cite

Objective: This study proposes a reference database, composed of a large number of simulated ECG signals in atrial fibrillation (AF), for investigating the performance of methods for extraction of atrial fibrillatory waves (f-waves). Approach: The simulated signals are produced using a recently published and validated model of 12-lead ECGs in AF. The database is composed of eight signal sets which together account for a wide range of characteristics known to represent major challenges in f-wave extraction, including high heart rates, high morphological QRST variability, and the presence of ventricular premature beats. Each set contains 30 5-min signals with different f-wave amplitudes. The database is used for the purpose of investigating the statistical association between different indices, designed either for use with real or simulated signals. Main results: Using the database, which is made available at the Physionet repository of physiological signals, the performance indices unnormalized ventricular residue (uVR), designed for real signals, and the root mean square error, designed for simulated signals, were found to exhibit the strongest association, leading to the recommendation that uVR should be used when characterizing performance in real signals. Significance: The proposed database facilitates the comparison of performance of different f-wave extraction methods and makes it possible to express performance in terms of the error between simulated and extracted f-wave signals.

show abstract

“…Mathematical transformations of ECG data have been used for several years in clinical medicine to analyze f H variability caused by cardiac malfunctions (e.g. John et al, 2017). Furthermore, spectral analysis of interbeat intervals has been used extensively to analyze regulation of cardiac function, for example in ectotherms under conditions that change metabolism using thermal (Seebacher and Franklin, 2004) or hormonal (Little and Seebacher, 2014) treatments.…”

Section: Introductionmentioning

confidence: 99%

An improved method for detecting torpor entrance and arousal in a mammalian hibernator using heart rate data

MacCannell

Jackson

Mathers

et al. 2018

Journal of Experimental Biology

View full text Add to dashboard Cite

We used electrocardiogram (ECG) telemeters to measure the heart rate of hibernating (thirteen-lined ground squirrel). An increase in heart rate from 2.2 to 5 beats min accurately identified arousal from torpor before any change in body temperature was detected. Variability in raw heart rate data was significantly reduced by a forward-backward Butterworth low-pass filter, allowing for discrete differential analysis. A decrease in filtered heart rate to 70% of maximum values in interbout euthermia (from approximately 312 to 235 beats min) accurately detected entrance into torpor bouts. At this point, body temperature had fallen from 36.1°C to only 34.7°C, much higher than the 30°C typically used to identify entrance. Using these heart rate criteria allowed advanced detection of entrance and arousal (detected 51.9 and 76 min earlier, respectively), compared with traditional body temperature criteria. This method will improve our ability to detect biochemical and molecular markers underlying these transition periods, during which many physiological changes occur.

show abstract

Single-lead f-wave extraction using diffusion geometry

Abstract: The clinical potential is shown in the real Holter signal, and we introduce a new score to evaluate the performance of the algorithm.

Cited by 22 publications

References 54 publications

Diffuse to fuse EEG spectra – Intrinsic geometry of sleep dynamics for classification

Diffuse to fuse EEG spectra – Intrinsic geometry of sleep dynamics for classification

Reference database and performance evaluation of methods for extraction of atrial fibrillatory waves in the ECG

An improved method for detecting torpor entrance and arousal in a mammalian hibernator using heart rate data

Contact Info

Product

Resources

About