OBJECTIVE: Detection of atrial fibrillation is important for risk stratification of stroke. We developed a novel methodology to classify electrocardiograms (ECGs) to normal, atrial fibrillation and other cardiac dysrhythmias as defined by the PhysioNet Challenge 2017. APPROACH: More specifically, we used piecewise linear splines for the feature selection and a gradient boosting algorithm for the classifier. In the algorithm, the ECG waveform is fitted by a piecewise linear spline, and morphological features relating to the piecewise linear spline coefficients are extracted. XGBoost is used to classify the morphological coefficients and heart rate variability features. MAIN RESULTS: The performance of the algorithm was evaluated by the PhysioNet Challenge database (3658 ECGs classified by experts). Our algorithm achieved an average F 1 score of 81% for a 10-fold cross-validation and also achieved 81% for F 1 score on the independent testing set. This score is similar to the top 9th score (81%) in the official phase of the PhysioNet Challenge 2017. SIGNIFICANCE: Our algorithm presents a good performance on multi-label short ECG classification with selected morphological features.
OBJECTIVE: Detection of atrial fibrillation is important for risk stratification of stroke. We developed a novel methodology to classify electrocardiograms (ECGs) to normal, atrial fibrillation and other cardiac dysrhythmias as defined by the PhysioNet Challenge 2017. APPROACH: More specifically, we used piecewise linear splines for the feature selection and a gradient boosting algorithm for the classifier. In the algorithm, the ECG waveform is fitted by a piecewise linear spline, and morphological features relating to the piecewise linear spline coefficients are extracted. XGBoost is used to classify the morphological coefficients and heart rate variability features. MAIN RESULTS: The performance of the algorithm was evaluated by the PhysioNet Challenge database (3658 ECGs classified by experts). Our algorithm achieved an average F 1 score of 81% for a 10-fold cross-validation and also achieved 81% for F 1 score on the independent testing set. This score is similar to the top 9th score (81%) in the official phase of the PhysioNet Challenge 2017. SIGNIFICANCE: Our algorithm presents a good performance on multi-label short ECG classification with selected morphological features.
Authors: Frederic Commandeur; Piotr J Slomka; Markus Goeller; Xi Chen; Sebastien Cadet; Aryabod Razipour; Priscilla McElhinney; Heidi Gransar; Stephanie Cantu; Robert J H Miller; Alan Rozanski; Stephan Achenbach; Balaji K Tamarappoo; Daniel S Berman; Damini Dey Journal: Cardiovasc Res Date: 2020-12-01 Impact factor: 10.787