Obstructive sleep apnea (OSA) is a high-incidence disease that is seriously harmful and potentially dangerous. The objective of this study was to develop a noncontact sleep audio signal-based method for diagnosing potential OSA patients, aiming to provide a more convenient diagnostic approach compared to the traditional polysomnography (PSG) testing.The study employed a shifted window transformer model to detect snoring audio signals from whole-night sleep audio. First, a snoring detection model was trained on large-scale audio datasets. Subsequently, the deep feature statistical metrics of the detected snore audio were used to train a random forest classifier for OSA patient diagnosis.Using a self-collected dataset of 305 potential OSA patients, the proposed snore shifted-window transformer method (SST) achieved an accuracy of 85.9%, a sensitivity of 85.3%, and a precision of 85.6% in OSA patient classification. These values surpassed the state-of-the-art method by 9.7%, 10.7%, and 7.9%, respectively.The experimental results demonstrated that SST significantly improved the noncontact audio-based OSA diagnosis performance. The study's findings suggest a promising self-diagnosis method for potential OSA patients, potentially reducing the need for invasive and inconvenient diagnostic procedures.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1088/1361-6579/ad262b | DOI Listing |
J Hypertens
December 2024
Department of Hemotology.
Objective: Anemia, obstructive sleep apnea (OSA), and hypertension are common social health problems. They are interconnected. This study assessed the independent association of anemia and OSA with hypertension and the interaction between anemia and OSA on hypertension in the US population.
View Article and Find Full Text PDFInt J Biol Macromol
January 2025
State Key Laboratory of Heavy Oil Processing and Centre for Bioengineering and Biotechnology, China University of Petroleum (East China), Qingdao, Shandong, People's Republic of China. Electronic address:
Combining polymer and surfactant in one agent namely polymeric surfactants with both high viscosity and surface activity has become a viable alternative for the traditional enhanced oil recovery (EOR) processes. With the purpose of developing new polymeric surfactants, the biopolymer flooding agent sphingan WL gum was modified by octenyl succinic anhydride (OSA) through the esterification reaction. The effects of molecular weight (MW) of WL and the OSA: WL ratio on the properties of the products were investigated.
View Article and Find Full Text PDFAppl Psychol Health Well Being
February 2025
Center for Studies of Psychological Application, South China Normal University, Guangzhou, 510631, People's Republic of China.
Prior research has predominantly examined the relations between online social activities (OSA) and mental health among adolescents and adults, with comparatively less emphasis placed on children, particularly concerning positive indicators of subjective health, such as well-being. The relations between OSA and well-being are likely intricate and necessitate meticulously designed methodologies to investigate the associations and their underlying mechanisms. This longitudinal study employed the random intercept cross-lagged panel models to explore the dynamic relations between OSA and well-being, considering peer relationship problems as a potential mediator and extraversion as a moderator of the associations, while distinguishing between- and within-person effects.
View Article and Find Full Text PDFFASEB J
January 2025
Department of Respiratory and Critical Care Medicine, Tianjin Medical University General Hospital, Tianjin, China.
Obstructive sleep apnea (OSA) is increasingly recognized for its link to idiopathic pulmonary fibrosis (IPF), though the underlying mechanisms remain poorly understood. Histone lysine demethylase 6B (KDM6B) may either prevent or promote organ fibrosis, but its specific role in IPF is yet to be clarified. This study aimed to investigate the function and mechanisms of KDM6B in IPF and the exacerbating effects of OSA.
View Article and Find Full Text PDFJ Clin Neurol
January 2025
Department of Brain and Cognitive Engineering, Korea University, Seoul, Korea.
Background And Purpose: Obstructive sleep apnea (OSA) is associated with an increased risk of adverse outcomes, including mortality. Machine-learning algorithms have shown potential in predicting clinical outcomes in patients with OSA. This study aimed to develop and evaluate a machine-learning algorithm for predicting 10- and 15-year all-cause mortality in patients with OSA.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!