Dataset Information

Accurate deep neural network model to detect cardiac arrhythmia on more than 10,000 individual subject ECG records.

ABSTRACT:

Background and objective

Cardiac arrhythmia, which is an abnormal heart rhythm, is a common clinical problem in cardiology. Detection of arrhythmia on an extended duration electrocardiogram (ECG) is done based on initial algorithmic software screening, with final visual validation by cardiologists. It is a time consuming and subjective process. Therefore, fully automated computer-assisted detection systems with a high degree of accuracy have an essential role in this task. In this study, we proposed an effective deep neural network (DNN) model to detect different rhythm classes from a new ECG database.

Methods

Our DNN model was designed for high performance on all ECG leads. The proposed model, which included both representation learning and sequence learning tasks, showed promising results on all 12-lead inputs. Convolutional layers and sub-sampling layers were used in the representation learning phase. The sequence learning part involved a long short-term memory (LSTM) unit after representation of learning layers.

Results

We performed two different class scenarios, including reduced rhythms (seven rhythm types) and merged rhythms (four rhythm types) according to the records from the database. Our trained DNN model achieved 92.24% and 96.13% accuracies for the reduced and merged rhythm classes, respectively.

Conclusion

Recently, deep learning algorithms have been found to be useful because of their high performance. The main challenge is the scarcity of appropriate training and testing resources because model performance is dependent on the quality and quantity of case samples. In this study, we used a new public arrhythmia database comprising more than 10,000 records. We constructed an efficient DNN model for automated detection of arrhythmia using these records.

SUBMITTER: Yildirim O

PROVIDER: S-EPMC7477611 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Accurate deep neural network model to detect cardiac arrhythmia on more than 10,000 individual subject ECG records.

Yildirim Ozal O Talo Muhammed M Ciaccio Edward J EJ Tan Ru San RS Acharya U Rajendra UR

Computer methods and programs in biomedicine 20200908

<h4>Background and objective</h4>Cardiac arrhythmia, which is an abnormal heart rhythm, is a common clinical problem in cardiology. Detection of arrhythmia on an extended duration electrocardiogram (ECG) is done based on initial algorithmic software screening, with final visual validation by cardiologists. It is a time consuming and subjective process. Therefore, fully automated computer-assisted detection systems with a high degree of accuracy have an essential role in this task. In this study, ...[more]

PMID: 32932129

Similar Datasets

Project description:BackgroundCardiac arrhythmias in exercising horses are the focus of much interest, both in terms of what is considered normal and potential associations with poor performance and sudden cardiac death. One barrier to performing large-scale studies is the lack of an easily applicable device, to allow recording of large numbers of high-quality exercising electrocardiograms (ECGs). The EquimetreTM is a new wearable device which records a single lead ECG, amongst other parameters. Validation of such wearable devices is essential before further studies are undertaken.ObjectivesTo evaluate the quality of ECG using the EquimetreTM and compare arrhythmia detection during exercise with the reference TelevetTM system.Study designProspective blinded clinical study.MethodsSimultaneous ECGs were recorded with both systems in 49 healthy horses during exercise. High intensity exercise (>40km/h) was performed by 29 racehorses, and lower intensity exercise for the remainder of the racehorses and show jumpers. Tracings were excluded if >10% artefact was present (duration of artefact relative to duration of exercise). For included ECGs, the duration of artefact was recorded and compared. ECGs were evaluated using Kubios premium software. Arrhythmia detection (yes/no) and arrhythmia classification (sinus arrhythmia, narrow complex of similar morphology to the sinus complexes or wide complex with a different morphology) were compared using Cohen's Kappa coefficient.ResultsNine TelevetTM ECGs and 3 EquimetreTM ECGs were excluded due to artefact >10%. TelevetTM ECGs included significantly more artefact during exercise than EquimetreTM ECGs (5% vs. 0.25% p<0.001). Arrhythmia analysis was performed on 38 horses' paired ECGs. The Kappa coefficient was excellent for arrhythmia detection (K=0.97) and arrhythmia classification (K=0.93).Main limitationsRelatively low numbers of horses with arrhythmias (n=21) were included. The ECG recordings only provided one lead, making arrhythmia classification challenging in some cases.ConclusionsThe Equimetre device provides a reliable ECG for arrhythmia detection during exercise. This system may be useful clinically and for future large-scale investigations into the occurrence and significance of exercising arrhythmias.

Project description:Accurate evaluation of SNP effects is important for genome wide association studies and for genomic prediction. The genetic architecture of quantitative traits differs widely, with some traits exhibiting few if any quantitative trait loci (QTL) with large effects, while other traits have one or several easily detectable QTL with large effects.Body weight in broilers and egg weight in layers are two examples of traits that have QTL of large effect. A commonly used method for genome wide association studies is to fit a mixture model such as BayesB that assumes some known proportion of SNP effects are zero. In contrast, the most commonly used method for genomic prediction is known as GBLUP, which involves fitting an animal model to phenotypic data with the variance-covariance or genomic relationship matrix among the animals being determined by genome wide SNP genotypes. Genotypes at each SNP are typically weighted equally in determining the genomic relationship matrix for GBLUP. We used the equivalent marker effects model formulation of GBLUP for this study. We compare these two classes of models using egg weight data collected over 8 generations from 2,324 animals genotyped with a 42 K SNP panel.Using data from the first 7 generations, both BayesB and GBLUP found the largest QTL in a similar well-recognized QTL region, but this QTL was estimated to account for 24 % of genetic variation with BayesB and less than 1 % with GBLUP. When predicting phenotypes in generation 8 BayesB accounted for 36 % of the phenotypic variation and GBLUP for 25 %. When using only data from any one generation, the same QTL was identified with BayesB in all but one generation but never with GBLUP. Predictions of phenotypes in generations 2 to 7 based on only 295 animals from generation 1 accounted for 10 % phenotypic variation with BayesB but only 6 % with GBLUP. Predicting phenotype using only the marker effects in the 1 Mb region that accounted for the largest effect on egg weight from generation 1 data alone accounted for almost 8 % variation using BayesB but had no predictive power with GBLUP.In conclusion, In the presence of large effect QTL, BayesB did a better job of QTL detection and its genomic predictions were more accurate and persistent than those from GBLUP.

Dataset Information

Accurate deep neural network model to detect cardiac arrhythmia on more than 10,000 individual subject ECG records.

Background and objective

Methods

Results

Conclusion

Publications

Accurate deep neural network model to detect cardiac arrhythmia on more than 10,000 individual subject ECG records.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets