A systematical evaluation work was performed on ten widely used and high-efficient QRS detection algorithms in this study, aiming at verifying their performances and usefulness in different application situations. Four experiments were carried on six internationally recognized databases. Firstly, in the test of high-quality ECG database versus low-quality ECG database, for high signal quality database, all ten QRS detection algorithms had very high detection accuracy (F1 >99%), whereas the F1 results decrease significantly for the poor signal-quality ECG signals (all 95% except RS slope algorithm with 94.24% on normal ECG database and 94.44% on arrhythmia database). Thirdly, for the paced rhythm ECG database, all ten algorithms were immune to the paced beats (>94%) except the RS slope method, which only output a low F1 result of 78.99%. At last, the detection accuracies had obvious decreases when dealing with the dynamic telehealth ECG signals (all <80%) except OKB algorithm with 80.43%. Furthermore, the time costs from analyzing a 10 s ECG segment were given as the quantitative index of the computational complexity. All ten algorithms had high numerical efficiency (all <4 ms) except RS slope (94.07 ms) and sixth power algorithms (8.25 ms). And OKB algorithm had the highest numerical efficiency (1.54 ms).

The classification of heartbeats is an important method for cardiac arrhythmia analysis. This study proposes a novel heartbeat classification method using hybrid time-frequency analysis and transfer learning based on ResNet-101. The proposed method has the following major advantages over the afore-mentioned methods: it avoids the need for manual features extraction in the traditional machine learning method, and it utilizes 2-D time-frequency diagrams which provide not only frequency and energy information but also preserve the morphological characteristic within the ECG recordings, and it owns enough deep to make better use of performance of CNN. The method deploys a hybrid time-frequency analysis of the Hilbert transform (HT) and the Wigner-Ville distribution (WVD) to transform 1-D ECG recordings into 2-D time-frequency diagrams which were then fed into a transfer learning classifier based on ResNet-101 for two classification tasks (i.e., 5 heartbeat categories assigned by the ANSI/AAMI standard (i.e., N, V, S, Q and F) and 14 original beat kinds of the MIT/BIH arrhythmia database). For 5 heartbeat categories classification, the results show the F1-score of N, V, S, Q and F categories are F$_{N}$ 0.9899, F$_{V}$ 0.9845, F$_{S}$ 0.9376, F$_{Q}$ 0.9968, F$_{F}$ 0.8889, respectively, and the overall F1-score is 0.9595 using the combination data balancing. The results show the average values for accuracy, sensitivity, specificity, predictive value and F1-score on test set for 14 beat kinds the MIT-BIH arrhythmia database are 99.75%, 91.36%, 99.85%, 90.81% and 0.9016, respectively. Compared with other methods, the proposed method can yield more accurate results.

Entropy provides a valuable tool for quantifying the regularity of physiological time series and provides important insights for understanding the underlying mechanisms of the cardiovascular system. Before any entropy calculation, certain common parameters need to be initialized: embedding dimension m, tolerance threshold r and time series length N. However, no specific guideline exists on how to determine the appropriate parameter values for distinguishing congestive heart failure (CHF) from normal sinus rhythm (NSR) subjects in clinical application. In the present study, a thorough analysis on the selection of appropriate values of m, r and N for sample entropy (SampEn) and recently proposed fuzzy measure entropy (FuzzyMEn) is presented for distinguishing two group subjects. 44 long-term NRS and 29 long-term CHF RR interval recordings from http://www.physionet.org were used as the non-pathological and pathological data respectively. Extreme (>2 s) and abnormal heartbeat RR intervals were firstly removed from each RR recording and then the recording was segmented with a non-overlapping segment length N of 300 and 1000, respectively. SampEn and FuzzyMEn were performed for each RR segment under different parameter combinations: m of 1, 2, 3 and 4, and r of 0.10, 0.15, 0.20 and 0.25 respectively. The statistical significance between NSR and CHF groups under each combination of m, r and N was observed. The results demonstrated that the selection of m, r and N plays a critical role in determining the SampEn and FuzzyMEn outputs. Compared with SampEn, FuzzyMEn shows a better regularity when selecting the parameters m and r. In addition, FuzzyMEn shows a better relative consistency for distinguishing the two groups, that is, the results of FuzzyMEn in the NSR group were consistently lower than those in the CHF group while SampEn were not. The selections of m of 2 and 3 and r of 0.10 and 0.15 for SampEn and the selections of m of 1 and 2 whenever r (herein, r_L = r_G = r) are for FuzzyMEn (in addition to setting n_L = 3 and n_G = 2) were recommended to yield the fine classification results for the NSR and CHF groups.

Atrial fibrillation (AF) is a serious cardiovascular disease with the phenomenon of beating irregularly. It is the major cause of variety of heart diseases, such as myocardial infarction. Automatic AF beat detection is still a challenging task which needs further exploration. A new framework, which combines modified frequency slice wavelet transform (MFSWT) and convolutional neural networks (CNNs), was proposed for automatic AF beat identification. MFSWT was used to transform 1 s electrocardiogram (ECG) segments to time-frequency images, and then, the images were fed into a 12-layer CNN for feature extraction and AF/non-AF beat classification. The results on the MIT-BIH Atrial Fibrillation Database showed that a mean accuracy (Acc) of 81.07% from 5-fold cross validation is achieved for the test data. The corresponding sensitivity (Se), specificity (Sp), and the area under the ROC curve (AUC) results are 74.96%, 86.41%, and 0.88, respectively. When excluding an extremely poor signal quality ECG recording in the test data, a mean Acc of 84.85% is achieved, with the corresponding Se, Sp, and AUC values of 79.05%, 89.99%, and 0.92. This study indicates that it is possible to accurately identify AF or non-AF ECGs from a short-term signal episode.