Many works in recent years have been focused on developing a portable and less expensive system for diagnosing patients with obstructive sleep apnea (OSA), instead of using the inconvenient and expensive polysomnography (PSG). This study proposes a sleep apnea detection system based on a one-dimensional (1D) deep convolutional neural network (CNN) model using the single-lead 1D electrocardiogram (ECG) signals. The proposed CNN model consists of 10 identical CNN-based feature extraction layers, a flattened layer, 4 identical classification layers mainly composed of fully connected networks, and a softmax classification layer. Thirty-five released and thirty-five withheld ECG recordings from the MIT PhysioNet Apnea-ECG Database were applied to train the proposed CNN model and validate its accuracy for the detection of the apnea events. The results show that the proposed model achieves 87.9% accuracy, 92.0% specificity, and 81.1% sensitivity for per-minute apnea detection, and 97.1% accuracy, 100% specificity, and 95.7% sensitivity for per-recording classification. The proposed model improves the accuracy of sleep apnea detection in comparison with several feature-engineering-based and feature-learning-based approaches.

Accurate QRS detection is an important first step for almost all automatic electrocardiogram (ECG) analyzing systems. However, QRS detection is difficult, not only because of the wide variety of ECG waveforms but also because of the interferences caused by various types of noise. This study proposes an improved QRS complex detection algorithm based on a four-level biorthogonal spline wavelet transform. A noise evaluation method is proposed to quantify the noise amount and to select a lower-noise wavelet detail signal instead of removing high-frequency components in the preprocessing stage. The QRS peaks can be detected by the extremum pairs in the selected wavelet detail signal and the proposed decision rules. The results show the high accuracy of the proposed algorithm, which achieves a 0.25% detection error rate, 99.84% sensitivity, and 99.92% positive prediction value, evaluated using the MIT-BIT arrhythmia database. The proposed algorithm improves the accuracy of QRS detection in comparison with several wavelet-based and non-wavelet-based approaches.

A variety of feature extraction and classification approaches have been proposed using electrocardiogram (ECG) and ECG-derived signals for improving the performance of detecting apnea events and diagnosing patients with obstructive sleep apnea (OSA). The purpose of this study is to further evaluate whether the reduction of lower frequency P and T waves can increase the accuracy of the detection of apnea events. This study proposed filter bank decomposition to decompose the ECG signal into 15 subband signals, and a one-dimensional (1D) convolutional neural network (CNN) model independently cooperating with each subband to extract and classify the features of the given subband signal. One-minute ECG signals obtained from the MIT PhysioNet Apnea-ECG database were used to train the CNN models and test the accuracy of detecting apnea events for different subbands. The results show that the use of the newly selected subject-independent datasets can avoid the overestimation of the accuracy of the apnea event detection and can test the difference in the accuracy of different subbands. The frequency band of 31.25–37.5 Hz can achieve 100% per-recording accuracy with 85.8% per-minute accuracy using the newly selected subject-independent datasets and is recommended as a promising subband of ECG signals that can cooperate with the proposed 1D CNN model for the diagnosis of OSA.

Aims: Although the beneficial effect of sacubitril/valsartan (SAC/VAL) compared to enalapril was consistent across ischaemic cardiomyopathy (ICM) and non-ischaemic cardiomyopathy (NICM) groups, the PARADIGM-HF study did not analyse the effect of ventricular remodelling on patients with different aetiologies, which may affect clinical treatment outcomes. This study aimed to compare left ventricular ejection fraction (LVEF) following SAC/VAL treatment and its association with clinical outcomes. Methods and results: A total of 1576 patients were analysed. Patients were grouped by LVEF changes following SAC/VAL treatment for 8-month period. LVEF improvement ≥15% was defined as ‘significant improvement’, and <5% or worse was classified as ‘lack of improvement’. The primary outcome was a composite of cardiovascular death and unplanned hospitalization for heart failure. Patients with NICM had lower baseline LVEF but improvement was significantly greater comparing to those with ICM (baseline 28.0 ± 7.7% vs. 30.1 ± 7.1%, P < 0.001, LVEF increase of 11.1 ± 12.6% vs. 6.7 ± 10.2%, P < 0.001). The effect of functional improvement of SAC/VAL on NICM patients showed bimodal distribution. Primary endpoints were inversely associated with LVEF changes in NICM patients: adjusted hazard ratio was 0.42 [95% confidence interval (CI) 0.31–0.58, P < 0.001] for NICM patients with significant improvement, and was 1.73 (95% CI 1.38–2.16, P < 0.001) for NICM patients but lack of improvement. Primary endpoints of ICM patients did not demonstrate an association with LVEF changes. Conclusion: Patients with NICM had higher degree of LVEF improvement than those with ICM following SAC/VAL treatment, and significant improvement of LVEF in NICM patients indicates favourable outcome.

Aims: Sacubitril/valsartan (SAC/VAL) has been used in patients with heart failure and reduced ejection fraction (HFrEF), and cardiac resynchronization therapy (CRT) could benefit the HFrEF patients with wide QRS durations. This study aimed to evaluate the clinical impacts of SAC/VAL on reverse cardiac remodelling in CRT-eligible and CRT-ineligible HFrEF patients with different QRS durations. Methods and results: The TAROT-HF study was a multicentre, observational study enrolling patients who initiated SAC/VAL from 10 hospitals since 2017. Patients with baseline left ventricular ejection fraction (LVEF) ≤ 35% were classified into two groups: (i) Group 1: CRT-eligible group, patients with left bundle branch block (LBBB) morphology plus QRS duration ≥130 ms or non-LBBB morphology plus QRS duration ≥150 ms; and (ii) Group 2: CRT-ineligible group. Propensity score matching was performed to adjust for confounders, and 1168 patients were analysed. Baseline characteristics were comparable between the two groups. The improvements in LVEF and left ventricular end-systolic volume index (LVESVi) were more significant in Group 2 than in Group 1 after 1 year SAC/VAL treatment (LVEF: 8.4% ± 11.3% vs. 4.5% ± 8.1%, P < 0.001; change percentages in LVESVi: −14.4% ± 25.9% vs. −9.6% ± 23.1%, P = 0.004). LVEF improving to ≥50% in Groups 1 and 2 constituted 5.2% and 20.2% after 1 year SAC/VAL treatment (P < 0.001). Multivariate analyses showed that wide QRS durations were negatively associated with the reverse cardiac remodelling in these HFrEF patients with SAC/VAL treatment. Conclusion: Despite SAC/VAL treatment, wide QRS durations are associated with lower degrees of left ventricular improvement than narrow ones in the HFrEF patients. Optimal intervention timing for the CRT-eligible patients requires further investigation.