A morphology based deep learning model for atrial fibrillation detection using single cycle electrocardiographic samples

Abstract

Background: Deep learning (DL) has shown promising results in improving atrial fibrillation (AF) detection algorithms. However, these models are often criticized because of their "black box" nature. Aim: To develop a morphology based DL model to discriminate AF from sinus rhythm (SR), and to visualize which parts of the ECG are used by the model to derive to the right classification. Methods: We pre-processed raw data of 1469 ECGs in AF or SR, of patients with a history AF. Input data was generated by normalizing all single cycles (SC) of one ECG lead to SC-ECG samples by 1) centralizing the R wave or 2) scaling from R-to-R wave. Different DL models were trained by splitting the data in a training, validation and test set. By using a DL based heat mapping technique we visualized those areas of the ECG used by the classifier to come to the correct classification.Results: The DL model with the best performance was a feedforward neural network trained by SC-ECG samples on a R-to-R wave basis of lead II, resulting in an accuracy of 0.96 and F1-score of 0.94. The onset of the QRS complex proved to be the most relevant area for the model to discriminate AF from SR. Conclusion:The morphology based DL model developed in this study was able to discriminate AF from SR with a very high accuracy. DL model visualization may help clinicians gain insights into which (unrecognized) ECG features are most sensitive to discriminate AF from SR.

Development and Validation of an Automated Algorithm to Detect Atrial Fibrillation Within Stored Intensive Care Unit Continuous Electrocardiographic Data: Observational Study (Preprint)

“…Because of the automated detection of ECG signal, noise, premature beats, and AF, the algorithms can also be adapted and scaled for rapid, real-time identification of AF among patients undergoing continuous ECG monitoring, including critically ill patients with complex ECG waveforms. The AF algorithm based on sample entropy is computationally more efficient than machine learning algorithms that require significant training data, and reports similar accuracy to machine learning methods not subjected to the additional challenge of high premature beat burdens met by the present algorithm among critically ill patients [20][21][22].…”

Development and Validation of an Automated Algorithm to Detect Atrial Fibrillation Within Stored Intensive Care Unit Continuous Electrocardiographic Data: Observational Study

“…Because of the automated detection of ECG signal, noise, premature beats, and AF, the algorithms can also be adapted and scaled for rapid, real-time identification of AF among patients undergoing continuous ECG monitoring, including critically ill patients with complex ECG waveforms. The AF algorithm based on sample entropy is computationally more efficient than machine learning algorithms that require significant training data, and reports similar accuracy to machine learning methods not subjected to the additional challenge of high premature beat burdens met by the present algorithm among critically ill patients [20][21][22]. Furthermore, algorithm development was hypothesis driven, enabling us to understand the relative contributions of premature beats and ECG noise to overall AF detection performance.…”

Opening the black box: interpretability of machine learning algorithms in electrocardiography

“…Other recent studies proposed algorithms for interpreting the decisions of DNNs for automatic ECG classification. For instance, Baalman et al [20] and Mousavi et al [19] implemented attention mechanisms as multi layer feed-forward neural networks. Baalman et al included such a mechanism within a DNN to highlight the samples belonging to a single ECG beat that mostly contributed to the classification.…”

“…Mousavi et al [19] proposed an end-to-end hierarchical attention mechanism model based on attention neural networks: the model is composed of three parts in which each part contains a stacked bidirectional recurrent neural network, followed by an attention model, capable of providing multi-level interpretability considering segments within the heartbeat, the whole heartbeat and the combination of all the heartbeats. Baalman et al [20] built a feedforward neural network to classify ECGs within atrial fibrillation and sinus rhythm along with an attention mechanism. Through the attention mechanism they built a heat map on the input signal to show the areas of the ECG used by the classifier to come to the correct classification.…”