It is well known that electrocardiogram heartbeats are substantial for cardiac disease diagnosis. In this paper, the best time scale was investigated to recognize congestive heart failure (CHF) based on heart rate variability (HRV) measures. The classifications were performed on seven different time scales with a support vector machine classifier. Nine HRV measures, including three time-domain measures, three frequency-domain measures, and three nonlinear-domain measures, were taken as feature vectors for classifier on each time scale. A total of 83 subjects with RR intervals were analyzed, of which 54 cases were normal and 29 patients were suffering from CHF in PhysioNet databases. The classifying results using tenfold cross-validation method achieved the best performance of a sensitivity, specificity, and accuracy of 86.7%, 98.3%, and 94.4%, respectively, on the 2-h time scale. Moreover, by introducing only three nonstandard HRV features extracted from the trends of HRV measures on time scales, it achieved a better performance of a sensitivity of 93.3%, specificity of 98.3%, and an accuracy of 96.7%. The impressive performance of discrimination power on the 2-h time scale and the trends of HRV measures on time scales indicate that multiple time scales play significant roles in detecting CHF and can be valuable in expressing useful knowledge in medicine. INDEX TERMS Electrocardiogram (ECG), heart rate variability (HRV), congestive heart failure (CHF), multiple time scales, support vector machine (SVM).

Background. The T wave represents ECG repolarization, whose detection is required during myocardial ischemia, and the first significant change in the ECG signal is being observed in the ST segment followed by changes in other waves like P wave and QRS complex. To offer guidance in clinical diagnosis, decision-making, and daily mobile ECG monitoring, the T wave needs to be detected firstly. Recently, the sliding area-based method has received an increasing amount of attention due to its robustness and low computational burden. However, the parameter setting of the search window’s boundaries in this method is not adaptive. Therefore, in this study, we proposed an improved sliding window area method with more adaptive parameter setting for T wave detection. Methods. Firstly, k-means clustering was used in the annotated MIT QT database to generate three piecewise functions for delineating the relationship between the RR interval and the interval from the R peak to the T wave onset and that between the RR interval and the interval from the R peak to the T wave offset. Then, the grid search technique combined with 5-fold cross validation was used to select the suitable parameters’ combination for the sliding window area method. Results. With respect to onset detection in the QT database, F1 improved from 54.70% to 70.46% and 54.05% to 72.94% for the first and second electrocardiogram (ECG) channels, respectively. For offset detection, F1 also improved in both channels as it did in the European ST-T database. Conclusions. F1 results from the improved algorithm version were higher than those from the traditional method, indicating a potentially useful application for the proposed method in ECG monitoring.

No abstract