Search

BackgroundThe application of telemedicine in home pulmonary rehabilitation interventions for the management of patients with chronic obstructive pulmonary disease (COPD) has achieved promising results. ObjectiveThis study aimed to develop a WeChat official account (Pulmonary Internet Explorer Rehabilitation [PeR]) based on social media. It further evaluated the effect of PeR on the quality of life, symptoms, and exercise self-efficacy of patients with COPD. MethodsThe functional modules of PeR were developed by a multidisciplinary team according to the electronic health–enhanced chronic care model (eCCM) components. A total of 106 patients were randomly selected (53 in the PeR group and 53 in the outpatient face-to-face group [FtF]). Pulmonary rehabilitation intervention was conducted for 3 months, and the outcome was observed for 3 months. The primary outcome was patient quality of life measured with the COPD assessment test (CAT). The secondary outcomes were evaluated using the modified Medical Research Council scale (mMRC), exercise self-regulatory efficacy scale (Ex-SRES), and St George’s Respiratory Questionnaire (SGRQ). ResultsThe intention-to-treat analysis was used in the study. A total of 94 participants completed the 6-month pulmonary rehabilitation program. No statistically significant differences were observed in CAT (F1,3=7.78, P=.001), Ex-SRES (F1,3=21.91, P

Introduction: Tele-pulmonary rehabilitation is increasingly advocated but cannot completely substitute for in-person services for chronic conditions. Adherence to Pulmonary rehabilitation (PR) remains low in chronic obstructive pulmonary disease (COPD) patients. Shared decision-making (SDM) promotes patients' participation in PR decisions and helps patients and healthcare providers to jointly make decisions that patients are informed and aligned with patient preferences and values, which are critical for patient adherence to PR. Objective: This study aimed to develop a hybrid in-person and virtual model of home-based PR services for older COPD patients and study the effectiveness of the patient decision aid (PDA)-supported recurring SDM intervention on patient adherence to PR, rehabilitation outcomes, and decision-related outcomes, as well as to explore the mechanisms of the intervention on PR adherence. Methods: A total of 78 older COPD patients were randomly assigned to the PR group (n = 39) or PDA-PR group (n = 39). Both groups were conducted hybrid in-person and virtual PR intervention for 3 months. The primary outcomes were patients' quality of life and PR adherence. The secondary outcomes were dyspnea symptoms, exercise self-efficacy, knowledge, and decision-related outcomes. Results: A total of 72 participants completed the 3-month PR program. There were statistically significant differences in PR adherence (p = 0.033), COPD assessment test (CAT) scores (p = 0.016), PR knowledge (p < 0.001), decision self-efficacy (p < 0.001), decision conflict (p < 0.001), and decision regret scores (p = 0.027) between the two groups. The modified Medical Research Council Dyspnoea scale (mMRC) score was significantly decreased only in PDA-PR group (p = 0.011). No statistically significant differences were observed in St George's Respiratory Questionnaire (SGRQ) score (p = 0.078), Exercise Self-Regulatory Efficacy Scale (Ex-SRES) score (p = 0.29) and COPD knowledge (p = 0.086) between the two groups. PR value score had a significant effect on adherence to PR (p = 0.007) and CAT score (p = 0.028). Conclusions: PDA supported recurring SDM intervention was helpful in maintaining older COPD patients' PR adherence and had advantages in improving quality of life, enhancing PR knowledge, decision self-efficacy, and reducing decision conflict and decision regret, but did not improve SGRQ and Ex-SRES. PR value score influenced patients' rehabilitation adherence and quality of life. Trial Registration: Chinese Clinical Trial Registry (ChiCTR): ChiCTR1900028563; http://apps.who.int/trialsearch/default.aspx. [ABSTRACT FROM AUTHOR]

This study investigated the effects of different exercise interventions on cardiopulmonary function in male tobacco-dependent college students. Forty-five male tobacco-dependent college students were recruited as the tobacco-dependent (TB) group, and 45 non-tobacco-dependent college students were recruited as the control group. The TB group was randomly assigned to three subgroups: non-exercise (NE), high-intensity interval training (HIIT), and moderate-intensity continuous training (MICT). The HIIT and MICT groups underwent a 10-week exercise training, while the NE group received no intervention. Cardiac parameters, including maximal oxygen uptake (VO2max), heart rate max (HRmax), and heart rate reserve (HRR), and pulmonary indicators, including forced vital capacity (FVC), forced expiratory volume in one second (FEV1), vital capacity (VC), maximum ventilation volume (MVV), and peak expiratory flow (PEF) were investigated. The results showed that the TB group had significantly lower cardiopulmonary function than the control group. The degree of tobacco dependence was negatively correlated with VO2max, FVC, FEV1, FEV1/FVC, and MVV. Furthermore, both HIIT and MICT training improved cardiopulmonary function. HIIT training exhibited superior efficacy compared to MICT in improving HRmax, HRR, FVC, FEV1, FEV1/FVC, and PEF. In conclusion, tobacco dependence adversely affects cardiopulmonary function in male college students. Both HIIT and MICT effectively improved cardiopulmonary function, with HIIT showing superior efficacy. [ABSTRACT FROM AUTHOR]

Accurately estimating the Remaining Useful Life (RUL) of lithium-ion batteries is crucial for maintaining the safe and stable operation of rechargeable battery management systems. However, this task is often challenging due to the complex temporal dynamics. Recently, attention-based networks, such as Transformers and Informer, have been the popular architecture in time series forecasting. Despite their effectiveness, these models with abundant parameters necessitate substantial training time to unravel temporal patterns. To tackle these challenges, we propose a straightforward MLP-Mixer-based architecture named "Intra–Inter Patch Mixer" (IIP-Mixer), which leverages the strengths of multilayer perceptron (MLP) models to capture both local and global temporal patterns in time series data. Specifically, it extracts information using an MLP and performs mixing operations along both intra-patch and inter-patch dimensions for battery RUL prediction. The proposed IIP-Mixer comprises parallel dual-head mixer layers: the intra-patch mixing MLP, capturing local temporal patterns in the short-term period, and the inter-patch mixing MLP, capturing global temporal patterns in the long-term period. Notably, to address the varying importance of features in RUL prediction, we introduce a weighted loss function in the MLP-Mixer-based architecture, marking the first time such an approach has been employed. Our experiments demonstrate that IIP-Mixer achieves competitive performance in battery RUL prediction, outperforming other popular time series frameworks, such as Informer and DLinear, with relative reductions in mean absolute error (MAE) of 24% and 10%, respectively. [ABSTRACT FROM AUTHOR]

Hyperautomation can automate complex business processes, reduce human intervention and improve business operational efficiency. Recommendation systems (RS) facilitate hyperautomation greatly. However, these systems require a large amount of user data to train their machine learning (ML) models and hence user data privacy has received great attention. In this paper, we propose a decentralized federated learning framework with privacy-preserving for RS. In our framework, users train the private and public parameters locally but share the public parameters only. Extensive experiments verify that our approach is accurate and can well preserve privacy. This study is helpful for providing privacy preserving in hyperautomation. [ABSTRACT FROM AUTHOR]