Objective: Currently, BP measurement devices are mainly cuff-based which are not portable or convenient for users. To simplify the measurement of BP, this article proposed a new framework for noninvasive BP estimation using single-channel PPG signals. Methods: Various PPG features that may be related to BP were extracted and a filter-wrapper collaborated feature selection method was used for rejecting irrelevant and redundant features. The features that maximize the correlation with BP were finally selected as the BP-oriented IFS, and a new LASSO-LSTM model was designed to estimate BP from the IFS. Results: Experiments were conducted on a public dataset and a self-collected clinical dataset, respectively. Results demonstrated that the proposed method is superior to previously reported methods in the literature, giving a mean absolute error of 4.95 mmHg for SBP and 3.15 mmHg for DBP which complies with the standard of the AAMI. Conclusion: The proposed filter-wrapper collaborated feature selection method could effectively reject weak correlation and redundant features, and the designed LASSO-LSTM model is capable of learning complicated nonlinear relations between the selected IFS and BP. The proposed method shows improved accuracy of noninvasive BP estimation.

Myocardial injury has been deemed as a major cause of heart diseases including myocarditis and coronary heart disease, which have brought multiple mortalities globally. Long non-coding RNAs (lncRNAs) are widely recognized in diverse diseases. However, the role of circular RNA HIPK2 (circ-HIPK2) remains unclear in myocardial injury induced by H₂O₂. We attempted to investigate the probable role of circ-HIPK2 in myocardial injury induced by H₂O₂. This study discovered that the treatment of H₂O₂ inhibited cell proliferation but boosted cell apoptosis and autophagy. ATG101 was upregulated in primary mouse neonatal cardiomyocytes under H₂O₂ treatment. ATG101 knockdown promoted proliferation and limited apoptosis by attenuating autophagy in H₂O₂-injured mouse neonatal cardiomyocytes. Furthermore, miR-485-5p was validated to combine with ATG101 and circ-HIPK2, and circ-HIPK2 positively regulated ATG101 expression by sponging miR-485-5p. At last, silenced circ-HIPK2 mediated the promotion of cell proliferation, and repression of cell apoptosis was restored by ATG101 amplification. In a word, circ-HIPK2 facilitates autophagy to accelerate cell apoptosis and cell death in H₂O₂-caused myocardial oxidative injury through the miR-485-5p/ATG101 pathway, indicating a novel therapeutic target point for patients with myocardial injury.

Atrial fibrillation (AF) is the most common arrhythmia, but an estimated 30% of patients with AF are unaware of their conditions. The purpose of this work is to design a model for AF screening from facial videos, with a focus on addressing typical motion disturbances in our real life, such as head movements and expression changes. This model detects a pulse signal from the skin color changes in a facial video by a convolution neural network, incorporating a phase-driven attention mechanism to suppress motion signals in the space domain. It then encodes the pulse signal into discriminative features for AF classification by a coding neural network, using a de-noise coding strategy to improve the robustness of the features to motion signals in the time domain. The proposed model was tested on a dataset containing 1200 samples of 100 AF patients and 100 non-AF subjects. Experimental results demonstrated that VidAF had significant robustness to facial motions, predicting clean pulse signals with the mean absolute error of inter-pulse intervals less than 100 milliseconds. Besides, the model achieved promising performance in AF identification, showing an accuracy of more than 90% in multiple challenging scenarios. VidAF provides a more convenient and cost-effective approach for opportunistic AF screening in the community.

Background: For hemodynamically stable patients with ST-segment elevation myocardial infarction (STEMI) who missed the reperfusion window, optimal timing for delayed revascularization remains controversial. Methods: We investigated 7,698 consecutive patients without cardiogenic shock, serious heart failure, or thrombolysis who underwent delayed stenting (12 hours to 28 days after STEMI) at multiple centers in China. The patients were divided according to delayed PCI timing into very early (12–72 hours), early (3–7 days), intermediate (7–14 days) and late (14–28 days) groups. The primary outcome was in-hospital rate of major adverse cardiovascular events (MACE); secondary outcomes were in-hospital rates of all bleeding events, heart failure and sudden cardiac arrest (SCA). All endpoint events were a composite of the primary and secondary endpoints. Results: In-hospital MACE rate was similar among groups (P=0.588). Patients who underwent late vs. very early, early and intermediate delayed PCI had higher in-hospital rates of secondary events (13% vs. 8.0%, 8.1% and 0.3%, P<0.001) and heart failure (11.8% vs. 6.2%, 6.3% and 7.6%, P<0.001, respectively). For all in-hospital events, the late vs. intermediate group was at higher risk (OR =1.26, 95% CI: 1.02 to 1.56, P=0.029); and in subgroup analysis, patients with Killip class II or III heart failure had similar rates (OR =1.02, 95% CI: 0.74 to 1.40, P=0.908); while women (OR =1.67, 95% CI: 1.07 to 2.62, P=0.024), and smokers (OR =1.46, 95% CI: 1.05 to 2.02, P=0.023) had higher rates. Conclusions: Late delayed PCI (14–28 days) after STEMI was associated with a higher incidence of in-hospital adverse events particularly in women and smokers but not with Killip class II–III heart failure, which might allow medical treatment to improve function.