Abstract. In this paper we propose an efficient method for denoising and extracting fiducial point (FP) of ECG signals. The method is based on a nonlinear dynamic model which uses Gaussian functions to model ECG waveforms. For estimating the model parameters, we use an extended Kalman filter (EKF). In this framework called EKF25, all the parameters of Gaussian functions as well as the ECG waveforms (P-wave, QRS complex and T-wave) in the ECG dynamical model, are considered as state variables. In this paper, the dynamic time warping method is used to estimate the nonlinear ECG phase observation. We compare this new approach with linear phase observation models. Using linear and nonlinear EKF25 for ECG denoising and nonlinear EKF25 for fiducial point extraction and ECG interval analysis are the main contributions of this paper. Performance comparison with other EKF-based techniques shows that the proposed method results in higher output SNR with an average SNR improvement of 12 dB for an input SNR of -8 dB. To evaluate the FP extraction performance, we compare the proposed method with a method based on partially collapsed Gibbs sampler and an established EKF-based method. The mean absolute error and the root mean square error of all FPs, across all databases are 14 msec and 22 msec, respectively, for our proposed method, with an advantage when using a nonlinear phase observation. These errors are significantly smaller than errors obtained with other methods. For ECG interval analysis, with an absolute mean error and a root mean square error of about 22 msec and 29 msec, the proposed method achieves better accuracy and smaller variability with respect to other methods.

In this study, we aimed to assess the association between development of cardiac injury and short-term mortality as well as poor in-hospital outcomes in hospitalized patients with COVID-19. In this prospective, single-center study, we enrolled hospitalized patients with laboratory-confirmed COVID-19 and highly suspicious patients with compatible chest computed tomography features. Cardiac injury was defined as a rise of serum high sensitivity cardiac Troponin-I level above 99th percentile (men: > 26 ng/mL, women: > 11 ng/mL). A total of 386 hospitalized patients with COVID-19 were included. Cardiac injury was present among 115 (29.8%) of the study population. The development of cardiac injury was significantly associated with a higher in-hospital mortality rate compared to those with normal troponin levels (40.9% vs 11.1%, p value < 0.001). It was shown that patients with cardiac injury had a significantly lower survival rate after a median follow-up of 18 days from symptom onset ( p log-rank < 0.001). It was further demonstrated in the multivariable analysis that cardiac injury could possibly increase the risk of short-term mortality in hospitalized patients with COVID-19 (HR = 1.811, p -value = 0.023). Additionally, preexisting cardiovascular disease, malignancy, blood oxygen saturation < 90%, leukocytosis, and lymphopenia at presentation were independently associated with a greater risk of developing cardiac injury. Development of cardiac injury in hospitalized patients with COVID-19 was significantly associated with higher rates of in-hospital mortality and poor in-hospital outcomes. Additionally, it was shown that development of cardiac injury was associated with a lower short-term survival rate compared to patients without myocardial damage and could independently increase the risk of short-term mortality by nearly two-fold. Electronic supplementary material The online version of this article (10.1007/s11739-020-02466-1) contains supplementary material, which is available to authorized users.

In this paper, we propose a novel method for extracting fiducial points (FPs) of electrocardiogram (ECG) signals. We propose the use of multi hidden Markov model (MultiHMM) as opposed to the traditional use of Classic HMM. In the MultiHMM method, each segment of an ECG beat is represented by a separate ergodic continuous density HMM. Each HMM has different state number and is trained separately. In the test step, the log-likelihood of two consecutive HMMs is compared and a path is estimated, which shows the correspondence of each part of the ECG signal to the HMM with the maximum log-likelihood. Fiducial points are estimated from the obtained path. For performance evaluation, the Physionet QT database and a Swine ECG database are used and the proposed method is compared with the Classic HMM and a method based on partially collapsed Gibbs sampler (PCGS). In our evaluation using the QT database, we also compare the results with low-pass differentiation, hybrid feature extraction algorithm, a method based on the wavelet transform and three HMM-based approaches. For the Swine database, the root mean square error (RMSE) values, across all FPs for MultiHMM, Classic HMM and PCGS methods are 13, 21 and 40ms, respectively and the MultiHMM exhibits smaller error variability than other methods. For the QT database, RMSE values for MultiHMM, Classic HMM, Wavelet and PCGS methods are 10, 17, 26 and 38ms, respectively. Our results demonstrate that our proposed MultiHMM approach outperforms other benchmark methods that exist in the literature; therefore can be used in practical ECG fiducial point extraction.