It is estimated that globally 425 million subjects have moderate to severe obstructive sleep apnea (OSA). The accurate prediction of sleep apnea events can offer insight into the development of treatment therapies. However, research related to this prediction is currently limited. We developed a covert framework for the prediction of sleep apnea events based on low-frequency breathing-induced vibrations obtained from piezoelectric sensors. A CNN-transformer network was utilized to efficiently extract local and global features from respiratory vibration signals for accurate prediction. Our study involved overnight recordings of 105 subjects. In five-fold cross-validation, we achieved an accuracy of 85.9% and an F1 score of 85.8%, which are 3.5% and 5.3% higher than the best-performed classical model, respectively. Additionally, in leave-one-out cross-validation, 2.3% and 3.8% improvements are observed, respectively. Our proposed CNN-transformer model is effective in the prediction of sleep apnea events. Our framework can thus provide a new perspective for improving OSA treatment modes and clinical management.

A sample-to-result ddPCR platform based on a microfluidic chip with a dual-function flow-focusing structure enabling droplet generation via forward flow and droplet readout via reflux by rotating the rotary valve was developed.

Sensors based on the magnetoelastic (ME) effect have been developed for various applications, such as food safety, immunoassays, and health monitoring. A major obstacle to the widespread adoption of ME sensors is the poor understanding of the electrical impedances that constitute the system and how these impedances are influenced by surface loadings. Herein, we derive a lumped-element model to approximately predict the near-resonance electrical behavior of an ME sensor simultaneously loaded with a mass layer and a semi-infinite Newtonian liquid. For more extensive applicability, a hybrid model, combining a modified Butterworth-Van Dyke (mBVD) model and a transmission line model, is derived for the first time to predict the response of the ME sensor under various surface conditions, including rigid solids, fluids, viscoelastic media, or any combinations thereof. The theoretical models are experimentally verified for accuracy and used to quantitatively analyze the mass, viscosity, and modulus of loadings by extracting the electrical parameters. This modeling work is crucial for the development of ME sensors in various applications and for providing insights into the physical mechanisms of advanced devices.