Our results show that sparse coding is an effective way to define spectral features of the cardiac cycle and its sub-cycles for the purpose of classification. In addition, we demonstrate that sparse coding can be combined with additional feature extraction methods to improve classification accuracy.

No abstract

Objective: The objective of this paper is to provide an algorithm for accurate, automated detection of atrial fibrillation (AF) from ECG signals. Four types of ECG signals are considered: normal signals, signals representing symptoms of AF, other signals, and noisy signals. This paper represents follow-up work to the authors’ entry in the 2017 PhysioNet Challenge as reported in the 2017 Computing in Cardiology Conference. Approach: Our approach involves extracting features from the ECG waveform and training a machine learning classifier. In feature extraction, we calculate several statistical features related to the ECG signal and fiduciary points. We also used a disciplined method of feature selection to reduce the dimensionality of the feature space. We also employ sparse coding as an unsupervised feature extraction tool. The classifier we use is a decision tree-based ensemble learning classifier. Main results: When applied to the hidden test data reserved by the PhysioNet Challenge organizers, our classifier reports F1 scores of 0.91, 0.78, and 0.71 for the Normal, AF, and Other classes, respectively. The overall test score is 0.80, and is obtained by averaging the F1 scores for these three classes. Significance: This work demonstrates that feature selection and ensemble learning can be used to improve the performance of ECG-based classification of AF.

This work represents an entry to the 2020 PhysioNET Computing in Cardiology Challenge for the team named "Whitaker's Lab." The algorithm we developed can be divided into three main components: feature extraction, dimensionality reduction, and classification. In the feature extraction stage, we process the provided 12-lead ECG signals to determine various features. We consider 12 timedomain statistical features per lead, as well as sparse coding features obtained from frequency information that is extracted from each ECG lead. After computing the features, we reduce the dimensionality of the statistical features using principal component analysis in an attempt to ease the computational requirements of the classifier. After feature extraction and dimensionality reduction, we classify each 12-lead ECG signal using a random forest classifier. The classifier is trained using a cross-validated grid search algorithm to help select hyperparameters. In an attempt to avoid overfitting, the classifier and unsupervised feature extraction algorithms are trained on disjoint subsets of the Challenge data. We were unable to rank and score in the test set, but using a holdout portion of the training set we achieved a validation score of -0.744. This result is likely to be over-optimistic.

Introduction: The aim of the Physionet/CinC Challenge 2017 is to automatically classify atrial fibrillation (AF) from a short single lead ECG recording. The Challenge provides 8,528 labeled ECG recordings; each recording was labeled as normal, AF, other, or noisy. In addition, the Challenge provides sample code which includes an R-peak detector and a simple classifier.Algorithm: We use an ensemble of features extracted from the ECG signals to create a four-class support vector machine (SVM) classifier. Included in the feature set are statistics obtained from the ECG signal, its spectrum, and the RR-intervals. In addition, we learn a 32-element sparse coding dictionary on the sorted RR-intervals of the ECG signals. Using the dictionary, we calculate a sparse coefficient vector for each training sample and put these through a soft-margin linear SVM. The soft-margin scores are used as additional features in the final classifier.Results: Our algorithm achieves cross-validated F1 scores of 0.874, 0.756, and 0.689 (for normal, AF, and other files, respectively), resulting in a final crossvalidated challenge score of 0.773. The score when tested on a subset of the unknown data is 0.78 (with F1 scores of 0.88, 0.80, 0.65). The official challenge score was 0.77.Conclusions: We developed an algorithm to classify ECG recordings as normal, AF, other, or noisy. Our results show that sparse coding is an effective way to define discriminating features from a list of sorted RR-intervals. In addition, these sparse codes complement more commonly used features in the classification task. Further work will attempt to increase the accuracy of the algorithm by exploring other features and classifiers while still using sparse coding as an unsupervised feature extractor.