RESUMO
Sleep staging is a crucial tool for diagnosing and monitoring sleep disorders, but the standard clinical approach using polysomnography (PSG) in a sleep lab is time-consuming, expensive, uncomfortable, and limited to a single night. Advancements in sensor technology have enabled home sleep monitoring, but existing devices still lack sufficient accuracy to inform clinical decisions. To address this challenge, we propose a deep learning architecture that combines a convolutional neural network and bidirectional long short-term memory to accurately classify sleep stages. By supplementing photoplethysmography (PPG) signals with respiratory sensor inputs, we demonstrated significant improvements in prediction accuracy and Cohen's kappa (k) for 2- (92.7 %; k = 0.768), 3- (80.2 %; k = 0.714), 4- (76.8 %, k = 0.550), and 5-stage (76.7 %, k = 0.616) sleep classification using raw data. This relatively translatable approach, with a less intensive AI model and leveraging only a few, inexpensive sensors, shows promise in accurately staging sleep. This has potential for diagnosing and managing sleep disorders in a more accessible and practical manner, possibly even at home.
Assuntos
Aprendizado Profundo , Fotopletismografia , Processamento de Sinais Assistido por Computador , Fases do Sono , Humanos , Fotopletismografia/métodos , Fases do Sono/fisiologia , Masculino , Feminino , Adulto , Polissonografia/métodos , Respiração , Pessoa de Meia-IdadeRESUMO
Metal matrix composites with near-zero thermal expansion (NZTE) have gained significant popularity in high-precision industries due to their excellent thermal stability and mechanical properties. The incorporation of Mn3Zn0.8Sn0.2N, which possesses outstanding negative thermal expansion properties, effectively suppressed the thermal expansion of titanium. Highly dense Mn3Zn0.8Sn0.2N/Ti composites were obtained by adjusting the fabrication temperature. Both composites fabricated at 650 °C and 700 °C exhibited NZTE. Furthermore, finite element analysis was employed to investigate the effects of thermal stress within the composites on their thermal expansion performance.
RESUMO
Microfluidic devices are traditionally monitored by bulky and expensive off-chip sensors. We have developed a soft piezoresistive sensor capable of measuring micron-level strains that can be easily integrated into devices via soft lithography. We apply this sensor to achieve fast and localized monitoring of pressure, flow, and valve actuation.
Assuntos
Dispositivos Lab-On-A-Chip , MicrofluídicaRESUMO
Current methods for continuous respiration monitoring such as respiratory inductive or optoelectronic plethysmography are limited to clinical or research settings; most wearable systems reported only measures respiration rate. Here we introduce a wearable sensor capable of simultaneously measuring both respiration rate and volume with high fidelity. Our disposable respiration sensor with a Band-Aid© like formfactor can measure both respiration rate and volume by simply measuring the local strain of the ribcage and abdomen during breathing. We demonstrate that both metrics are highly correlated to measurements from a medical grade continuous spirometer on participants at rest. Additionally, we also show that the system is capable of detecting respiration under various ambulatory conditions. Because these low-powered piezo-resistive sensors can be integrated with wireless Bluetooth units, they can be useful in monitoring patients with chronic respiratory diseases in everyday settings.
RESUMO
Purpose: We used acoustic radiation force optical coherence elastography (ARF-OCE) to map out the elasticity of retinal layers in healthy and diseased in vivo rabbit models for the first time. Methods: A healthy rabbit eye was proptosed and imaged using ARF-OCE, by measuring the tissue deformation after an acoustic force is applied. A diseased retinal inflammation model was used to observe the contrast before and after disease formation. Retinal histologic analysis was performed to identify layers of the retina corresponding with the optical images. Results: The general trend of the retinal layer elasticity is increasing stiffness from the ganglion side to the photoreceptor side, with the stiffest layer being the sclera. In a healthy rabbit model, the mechanical properties varied from 3 to 16 kPa for the five layers that were identified via optical imaging and histology (3.09 ± 0.46, 3.82 ± 0.88, 4.53 ± 0.74, 6.59 ± 2.27, 16.11 ± 5.13 kPa). In the diseased model, we have induced optical damage in a live rabbit and observed a change in the stiffness trend in its retina. Conclusions: High sensitivity elasticity maps can be obtained using the ARF-OCE system to differentiate different retinal layers. Subtle changes in the mechanical properties during the onset of diseases, such as retinal degeneration, can be measured and aid in early clinical diagnosis. This study validates our imaging system for the characterization of retinal elasticity for the detection of retinal diseases in vivo.