Automatic Classification of Full- and Reduced-Lead Electrocardiograms Using Morphological Feature Extraction

Hammer, Alexander; Scherpf, Matthieu; Ernst, Hannes; Weiss, Jonas; Schwensow, Daniel; Schmidt, Martin

doi:10.23919/cinc53138.2021.9662797

Cited by 5 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is noteworthy from the above discussion and table 5 that our proposed method has outperformed that of (Krivenko et al 2021) with respect to Challenge score and time-complexity for all ECG lead configurations. However, the algorithm of (Hammer et al 2021) has demonstrated relatively better performance in some of the ECG lead configurations in terms of Challenge score at the cost of increased time-complexity which is almost four-fold that of the proposed methodology.…”

Section: Discussionmentioning

confidence: 95%

“…Then, concatenation is done to feature from each lead in order to obtain the final vector of features. In another study by (Hammer et al 2021), template delineation was applied to each ECG lead corresponding to the template's fiducial points to obtain information on the ECG waveform morphology. They extracted beat intervals and amplitude values from the template, QT interval, and HR variability-based features along with signal quality indices in their method.…”

Section: Discussionmentioning

confidence: 99%

“…One of the participants of this Challenge developed 27 independent XGBoost model-based binary classifiers using various clinical features (Krivenko et al 2021). In another study, template delineation was applied to each ECG lead corresponding to the template's fiducial points to obtain different morphological features used to train the decision tree ensemble classifier (Hammer et al 2021). In this paper, as a follow-up entry to this Challenge, we have developed an improved multi-label classification scheme for 12-lead ECG data.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Application of Fourier-Bessel expansion and LSTM on multi-lead ECG for cardiac abnormalities identification

Sawant¹,

Patidar²

2022

Physiol. Meas.

View full text Add to dashboard Cite

Objective: The availability of online electrocardiogram (ECG) repositories can aid researchers in developing automated cardiac abnormality diagnostic systems. Using such ECG repositories, this study aims to develop an algorithm that can assist physicians in diagnosing cardiac abnormalities. Approach: The PhysioNet/CinC 2021 Challenge has opened the venues for creating benchmark algorithms using standard and relatively diverse 12-lead ECG datasets. This work attempts to create a new machine learning approach for identifying common cardiac abnormalities using an ensemble-based classification with two models resulting from two different feature sets. The first feature set extracts RR variability based information by deploying Fourier-Bessel (FB) expansion. The second feature set is composed of time- and frequency-domains-based hand-crafted features. Two long short-term memory (LSTM)-based classifiers are trained using these two feature sets as input to categorize ECG signals. Predictions from these two models are fused to arrive at a final medical decision that improves the multi-label classification of the given ECG signals into twenty-six categories. \\ Main results: We participated in the George B. Moody Physionet Challenge 2021 as team 'Medics', and the proposed methodology was evaluated for all five lead combinations. The challenge scoring metrics obtained on the test data for twelve-, six-, four-, three-, and two-leads combinations are 0.360, 0.368, 0.376, 0.323, and 0.381, respectively. The proposed methodology was ranked 11th among all the follow-up entries of the Challenge. Significance: The obtained results of the proposed method justify the use of an ensemble classifier developed using the extracted feature sets for devising a diagnostic system for detecting and identifying common cardiac problems.

show abstract

Section: Discussionmentioning

confidence: 95%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Fourier-Bessel expansion and LSTM on multi-lead ECG for cardiac abnormalities identification

Sawant¹,

Patidar²

2022

Physiol. Meas.

View full text Add to dashboard Cite

show abstract

“…All ECGs were high-pass and notch filtered at 0.05 Hz and 60 Hz, respectively, with previous zero-padding to avoid boundary effects. In filtered ECGs, noisy parts were detected [7] and ignored for QRS detection [8] with subsequent QRS correction, based on amplitude heights and signs as well as peak-to-peak and peak-to-signal edge distances [9].…”

Section: Preprocessingmentioning

confidence: 99%

Towards the Prediction of Atrial Fibrillation Based on Interpretable ECG Features

Hammer¹,

Malberg²,

Schmidt"³

2022

Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

Atrial fibrillation (AF) is our society's most common cardiac arrhythmic disease, leading to increased morbidity and mortality. Predicting AF episodes during sinus rhythm based on electrocardiograms (ECGs) allows timely interventions. It is known, that changes in selected ECG morphology features are a predictor for the onset of AF, but no systematic investigation of different ECG features' temporal changes has been performed so far. We split sinus rhythm episodes of 60 minutes preceding AF from the MIT-BIH AF database into segments of 5 minutes with 50% overlap (n = 644) and calculated 155 features of different domains per segment. Logistic regression analyses between the segments preceding AF and others revealed the most significant effects for segments ending 5 minutes before AF onset, with PQ interval slope (p < 0.01), PQ interval correlation (p < 0.05), and median RR time (p < 0.05) being the most relevant features. A decision tree ensemble, trained with all features, achieved an accuracy of 0.87 when distinguishing 8 segment clusters. Our results confirm expected changes in ECG features (e.g., PQ interval) before AF episodes, indicating impaired atrial excitation, and show that the combination of interpretable features is sufficient to discriminate at different points in time before AF onset. For advanced analyses, more extensive databases should be included.

show abstract

“…We parameterized xECGArch for the application of AF detection in this paper. To achieve transferability from clinical application to home setting and thus reach a larger target group, we focused on single-lead ECGs [34,35]. Within xECGArch, we leverage global average pooling layers for signal analysis by independent CNNs…”

Section: Introductionmentioning

confidence: 99%

xECGArch: A trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features

Goettling,

Hammer,

Malberg

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Deep learning-based methods have demonstrated high classification performance in the detection of cardiovascular diseases from electrocardiograms (ECGs). However, their blackbox character and the associated lack of interpretability limit their clinical applicability. To overcome existing limitations, we present a novel deep learning architecture for interpretable ECG analysis (xECGArch). For the first time, short- and long-term features are analyzed by two independent convolutional neural networks (CNNs) and combined into an ensemble, which is extended by methods of explainable artificial intelligence (xAI) to whiten the blackbox. To demonstrate the trustworthiness of xECGArch, perturbation analysis was used to compare 13 different xAI methods. We parameterized xECGArch for atrial fibrillation (AF) detection using four public ECG databases (n = 9,854 ECGs) and achieved an F1 score of 95.43 % in AF versus non-AF classification on an unseen ECG test dataset. A systematic comparison of xAI methods showed that deep Taylor decomposition provided the most trustworthy explanations (+24 % compared to the second-best approach). xECGArch can account for short- and long-term features corresponding to clinical features of morphology and rhythm, respectively. Further research will focus on the relationship between xECGArch features and clinical features, which may help in medical applications for diagnosis and therapy.

show abstract

Automatic Classification of Full- and Reduced-Lead Electrocardiograms Using Morphological Feature Extraction

Cited by 5 publications

References 11 publications

Application of Fourier-Bessel expansion and LSTM on multi-lead ECG for cardiac abnormalities identification

Application of Fourier-Bessel expansion and LSTM on multi-lead ECG for cardiac abnormalities identification

Towards the Prediction of Atrial Fibrillation Based on Interpretable ECG Features

xECGArch: A trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features

Contact Info

Product

Resources

About