An overview of sex-related differences in respiratory function and their possible clinical implicationshttp://ow.ly/106m30jqOSW

In the future, diagnostic devices will be able to monitor a patient’s physiological or biochemical parameters continuously, under natural physiological conditions and in any environment through wearable biomedical sensors. Together with apps that capture and interpret data, and integrated enterprise and cloud data repositories, the networks of wearable devices and body area networks will constitute the healthcare’s Internet of Things. In this review, four main areas of interest for respiratory healthcare are described: pulse oximetry, pulmonary ventilation, activity tracking and air quality assessment. Although several issues still need to be solved, smart wearable technologies will provide unique opportunities for the future or personalised respiratory medicine.

Several wearable devices for physiological and activity monitoring are found on the market, but most of them only allow spot measurements. However, the continuous detection of physiological parameters without any constriction in time or space would be useful in several fields such as healthcare, fitness, and work. This can be achieved with the application of textile technologies for sensorized garments, where the sensors are completely embedded in the fabric. The complete integration of sensors in the fabric leads to several manufacturing techniques that allow dealing with both the technological challenges entailed by the physiological parameters under investigation, and the basic requirements of a garment such as perspiration, washability, and comfort. This review is intended to provide a detailed description of the textile technologies in terms of materials and manufacturing processes employed in the production of sensorized fabrics. The focus is pointed at the technical challenges and the advanced solutions introduced with respect to conventional sensors for recording different physiological parameters, and some interesting textile implementations for the acquisition of biopotentials, respiratory parameters, temperature and sweat are proposed. In the last section, an overview of the main garments on the market is depicted, also exploring some relevant projects under development.

Human activity recognition (HAR) using smartphones provides significant healthcare guidance for telemedicine and long-term treatment. Machine learning and deep learning (DL) techniques are widely utilized for the scientific study of the statistical models of human behaviors. However, the performance of existing HAR platforms is limited by complex physical activity. In this article, we proposed an adaptive recognition and real-time monitoring system for human activities (Ada-HAR), which is expected to identify more human motions in dynamic situations. The Ada-HAR framework introduces an unsupervised online learning algorithm that is independent of the number of class constraints. Furthermore, the adopted hierarchical clustering and classification algorithms label and classify 12 activities (five dynamics, six statics, and a series of transitions) autonomously. Finally, practical experiments have been performed to validate the effectiveness and robustness of the proposed algorithms. Compared with the methods mentioned in the literature, the results show that the DL-based classifier obtains a higher recognition rate ( $\text{95.15\%}$ , waist, and $\text{92.20\%}$ , pocket). The decision-tree-based classifier is the fastest method for modal evolution. Finally, the Ada-HAR system can monitor human activity in real time, regardless of the direction of the smartphone.

Background: Dynamic hyperinflation of the lungs impairs exercise performance in chronic obstructive pulmonary disease (COPD). However, it is unclear which patients are affected by dynamic hyperinflation and how the respiratory muscles respond to the change in lung volume. Methods: Using optoelectronic plethysmography, total and regional chest wall volumes were measured non-invasively in 20 stable patients with COPD (mean (SD) forced expiratory volume in 1 second 43.6 (11.6)% predicted) and dynamic hyperinflation was tracked breath by breath to test if this was the mechanism of exercise limitation. Resting ventilation, breathing pattern, symptoms, rib cage and abdominal volumes were recorded at rest and during symptom limited cycle ergometry. Pleural, abdominal, and transdiaphragmatic pressures were measured in eight patients. Results: End expiratory chest wall volume increased by a mean (SE) of 592 (80) ml in 12 patients (hyperinflators) but decreased by 462 (103) ml in eight (euvolumics). During exercise, tidal volume increased in euvolumic patients by reducing end expiratory abdominal volume while in hyperinflators tidal volume increased by increasing end inspiratory abdominal and rib cage volumes. The maximal abdominal pressure was 22.1 (9.0) cm H₂O in euvolumic patients and 7.6 (2.6) cm H₂O in hyperinflators. Euvolumic patients were as breathless as hyperinflators but exercised for less time and reached lower maximum workloads (p<0.05) despite having better spirometric parameters and a greater expiratory flow reserve. Conclusions: Dynamic hyperinflation is not the only mechanism limiting exercise performance in patients with stable COPD. Accurate measurement of chest wall volume can identify the different patterns of respiratory muscle activation during exercise.

This study aims to understand breathing patterns during daily activities by developing a wearable respiratory and activity monitoring (WRAM) system. A novel multimodal fusion architecture is proposed to calculate the respiratory and exercise parameters and simultaneously identify human actions. A hybrid hierarchical classification (HHC) algorithm combining deep learning and threshold-based methods is presented to distinguish 15 complex activities for accuracy enhancement and fast computation. A series of signal processing algorithms are utilized and integrated to calculate breathing and motion indices. The designed wireless communication structure achieves the interactions among chest bands, mobile devices, and the data processing center. The advantage of the proposed HHC method is evaluated by comparing the average accuracy (97.22\%) and predictive time (0.0094s) with machine learning and deep learning approaches. The nine breathing patterns during 15 activities were analyzed by investigating the data from 12 subjects. With 12 hours of naturalistic data collected from one participant, the WRAM system reports the breathing and exercise performance within the identified motions. The demonstration shows the ability of the WRAM system to monitor multiple users' breathing and exercise status in real-time. The present system demonstrates the usefulness of the framework of breathing pattern monitoring during daily activities, which may be potentially used in healthcare. The proposed multimodal based WRAM system offers new insights into the breathing function of exercise in action and presents a novel approach for precision medicine and health state monitoring.