Classification and Detection of Breathing Patterns with Wearable Sensors and Deep Learning.

Rapid assessment of breathing patterns is important for several emergency medical situations. In this research, we developed a non-invasive breathing analysis system that automatically detects different types of breathing patterns of clinical significance. Accelerometer and gyroscopic data were collected from light-weight wireless sensors placed on the chest and abdomen of 100 normal volunteers who simulated various breathing events (central sleep apnea, coughing, obstructive sleep apnea, sighing, and yawning). We then constructed synthetic datasets by injecting annotated examples of the various patterns into segments of normal breathing. A one-dimensional convolutional neural network was implemented to detect the location of each event in each synthetic dataset and to classify it as belonging to one of the above event types. We achieved a mean F1 score of 92% for normal breathing, 87% for central sleep apnea, 72% for coughing, 51% for obstructive sleep apnea, 57% for sighing, and 63% for yawning. These results demonstrate that using deep learning to analyze chest and abdomen movement data from wearable sensors provides an unobtrusive means of monitoring the breathing pattern. This could have application in a number of critical medical situations such as detecting apneas during sleep at home and monitoring breathing events in mechanically ventilated patients in the intensive care unit.

Chronic exposure to electronic cigarettes results in impaired cardiovascular function in mice.

Proponents for electronic cigarettes (E-cigs) claim that they are a safe alternative to tobacco-based cigarettes; however, little is known about the long-term effects of exposure to E-cig vapor on vascular function. The purpose of this study was to determine the cardiovascular consequences of chronic E-cig exposure. Female mice (C57BL/6 background strain) were randomly assigned to chronic daily exposure to E-cig vapor, standard (3R4F reference) cigarette smoke, or filtered air ( n = 15/group). Respective whole body exposures consisted of four 1-h-exposure time blocks, separated by 30-min intervals of fresh air breaks, resulting in intermittent daily exposure for a total of 4 h/day, 5 days/wk for 8 mo. Noninvasive ultrasonography was used to assess cardiac function and aortic arterial stiffness (AS), measured as pulse wave velocity, at three times points (before, during, and after chronic exposure). Upon completion of the 8-mo exposure, ex vivo wire tension myography and force transduction were used to measure changes in thoracic aortic tension in response to vasoactive-inducing compounds. AS increased 2.5- and 2.8-fold in E-cig- and 3R4F-exposed mice, respectively, compared with air-exposed control mice ( P < 0.05). The maximal aortic relaxation to methacholine was 24% and 33% lower in E-cig- and 3R4F-exposed mice, respectively, than in controls ( P < 0.05). No differences were noted in sodium nitroprusside dilation between the groups. 3R4F exposure altered cardiac function by reducing fractional shortening and ejection fraction after 8 mo ( P < 0.05). A similar, although not statistically significant, tendency was also observed with E-cig exposure ( P < 0.10). Histological and respiratory function data support emphysema-associated changes in 3R4F-exposed, but not E-cig-exposed, mice. Chronic exposure to E-cig vapor accelerates AS, significantly impairs aortic endothelial function, and may lead to impaired cardiac function. The clinical implication from this study is that chronic use of E-cigs, even at relatively low exposure levels, induces cardiovascular dysfunction. NEW & NOTEWORTHY Electronic cigarettes (E-cigs) are marketed as safe, but there has been insufficient long-term exposure to humans to justify these claims. This is the first study to report the long-term in vivo vascular consequences of 8 mo of exposure to E-cig vapor in mice (equivalent to ~25 yr of exposure in humans). We report that E-cig exposure increases arterial stiffness and impairs normal vascular reactivity responses, similar to other risk factors, including cigarette smoking, which contribute to the development of cardiovascular disease.