Multi-Label Cardiac Abnormality Classification from Electrocardiogram Using Deep Convolutional Neural Networks

Wickramasinghe, Nima L.; Athif, Mohamed

doi:10.23919/cinc53138.2021.9662787

Cited by 11 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An interesting choice to check would be building one model that always works on 12 input signals (12-leads) and zeroing signals for not used leads, as was proposed in Nejedly et al (2021). Also worth testing is using an additional hand-picked feature vector, as in (Nejedly et al 2021, Wickramasinghe andAthif 2021).…”

Section: Discussionmentioning

confidence: 99%

Comparison of neural basis expansion analysis for interpretable time series (N-BEATS) and recurrent neural networks for heart dysfunction classification

2022

View full text Add to dashboard Cite

Objective: The primary purpose of this work is to analyze the ability of N-BEATS architecture for the problem of prediction and classification of electrocar- diogram (ECG) signals. To achieve this, performance comparison with various types of other SotA (state-of-the-art) recurrent neural network architectures commonly used for such problems is conducted. Approach: Four architectures (N-BEATS, LSTM, LSTM with peepholes, GRU) were tested for performance and dimension reduction problems for different number of leads (2, 3, 4, 6, 12), both in variants consisting of blended branches, allowing retaining ac- curacy while reducing the computational capacity needed. The analysis was performed on datasets and using metrics from Challenges in Cardiology (CinC) 2021 competition. Main results: Best results were achieved for LSTM with peepholes, then LSTM, GRU and the worst for N-BEATS (challenge metrics respectively: 0.42, 0.40, 0.39, 0.35; for times: 0.0395 s, 0.0036 s, 0.0027 s, 0.0002 s). Commonly used LSTM outperforms N- BEATS in terms of multi-label classification, data set resilience, and obtained challenge metrics. Still, N-BEATS can obtain acceptable results for 2 lead classification (metric of 0.35 for N-BEATS and 0.38 for other networks) and outperforms other solutions in terms of complexity and speed. Significance: This paper features a novel approach of using the N-BEATS, which was previously used only for forecasting, to classify ECG signals with success. While N- BEATS multi-label classification capacity is lower than LSTM, its speed obtaining results with a reduced number of leads (faster by one to two degrees of magnitude) allows for arrhythmias detection and classification while using off-the-shelf wearable devices (Holter monitors, sport bands, etc.)

show abstract

Section: Discussionmentioning

confidence: 99%

Comparison of neural basis expansion analysis for interpretable time series (N-BEATS) and recurrent neural networks for heart dysfunction classification

2022

View full text Add to dashboard Cite

show abstract

“…These are the methods that are developed in a similar way to that of our proposed algorithm. The proposed algorithm is also compared with the Challenge's top entrants, who have developed their algorithm using end-to-end deep learning techniques (Han et al 2021, Nejedly et al 2021, Wickramasinghe and Athif 2021.…”

Section: Discussionmentioning

confidence: 99%

“…Similar to Challenge 2020, 90% of the participants of the 2021 PhysioNet Challenge employed deep neural networks. Given this, one of the top entrants to the Challenge employed two convolutional neural networks to perform the multi-label classification using the pre-processed ECG signals and fast Fourier transformed ECG signals as inputs (Wickramasinghe and Athif 2021). Similarly, the first rank entrant of the Challenge developed a method using ResNet deep neural network architecture for classification with a multi-head attention mechanism (Nejedly et al 2021).…”

Section: Introductionmentioning

confidence: 99%

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

“…Finally, we removed the signal segments beyond the first 15 s if they were available. Hence, we used short ECG segments and avoided big differences in the lasting time of the dataset samples, as previously done in Xiaoyu et al (2021), Wickramasinghe and Athif (2021), Aublin et al (2021).…”

Section: Signal Preprocessingmentioning

confidence: 99%

From 12 to 1 ECG lead: multiple cardiac condition detection mixing a hybrid machine learning approach with a one-versus-rest classification strategy

et al. 2022

View full text Add to dashboard Cite

Objective. Detecting different cardiac diseases using a single or reduced number of leads is still challenging. This work aims to provide and validate an automated method able to classify ECG recordings. Performance using complete 12-lead systems, reduced lead sets, and single-lead ECGs is evaluated and compared. Approach. Seven different databases with 12-lead ECGs were provided during the PhysioNet/Computing in Cardiology Challenge 2021, where 88 253 annotated samples associated with none, one, or several cardiac conditions among 26 different classes were released for training, whereas 42 896 hidden samples were used for testing. After signal preprocessing, 81 features per ECG-lead were extracted, mainly based on heart rate variability, QRST patterns and spectral domain. Next, a One-versus-Rest classification approach made of independent binary classifiers for each cardiac condition was trained. This strategy allowed each ECG to be classified as belonging to none, one or several classes. For each class, a classification model among two binary supervised classifiers and one hybrid unsupervised-supervised classification system was selected. Finally, we performed a 3-fold cross-validation to assess the system’s performance. Main results. Our classifiers received scores of 0.39, 0.38, 0.39, 0.38, and 0.37 for the 12, 6, 4, 3 and 2-lead versions of the hidden test set with the Challenge evaluation metric ( C M ). Also, we obtained a mean G -score of 0.80, 0.78, 0.79, 0.79, 0.77 and 0.74 for the 12, 6, 4, 3, 2 and 1-lead subsets with the public training set during our 3-fold cross-validation. Significance. We proposed and tested a machine learning approach focused on flexibility for identifying multiple cardiac conditions using one or more ECG leads. Our minimal-lead approach may be beneficial for novel portable or wearable ECG devices used as screening tools, as it can also detect multiple and concurrent cardiac conditions.

show abstract

Multi-Label Cardiac Abnormality Classification from Electrocardiogram Using Deep Convolutional Neural Networks

Cited by 11 publications

References 7 publications

Comparison of neural basis expansion analysis for interpretable time series (N-BEATS) and recurrent neural networks for heart dysfunction classification

Comparison of neural basis expansion analysis for interpretable time series (N-BEATS) and recurrent neural networks for heart dysfunction classification

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

From 12 to 1 ECG lead: multiple cardiac condition detection mixing a hybrid machine learning approach with a one-versus-rest classification strategy

Contact Info

Product

Resources

About