The purpose of this study was to test whether a machine learning model can accurately predict VO2 across different exercise intensities by combining muscle oxygen (MO2) with heart rate (HR). Twenty young highly trained athletes performed the following tests: a ramp incremental exercise, three submaximal constant intensity exercises, and three severe intensity exhaustive exercises. A Machine Learning model was trained to predict VO2, with model inputs including heart rate, MO2 in the left (LM) and right legs (RM). All models demonstrated equivalent results, with the accuracy of predicting VO2 at different exercise intensities varying among different models. The LM+RM+HR model performed the best across all intensities, with low bias in predicted VO2 for all intensity exercises (0.08 ml/kg/min, 95% limits of agreement: -5.64 to 5.81), and a very strong correlation (r = 0.94, p < 0.001) with measured VO2. Furthermore, the accuracy of predicting VO2 using LM+HR or RM+HR was higher than using LM+RM, and higher than the accuracy of predicting VO2 using LM, RM, or HR alone. This study demonstrates the potential of a machine learning model combining MO2 and HR to predict VO2 with minimal bias, achieving accurate predictions of VO2 for different intensity levels of exercise.

BACKGROUND: Fall detection is of great significance in safeguarding human health. By monitoring the motion data, a fall detection system (FDS) can detect a fall accident. Recently, wearable sensors-based FDSs have become the mainstream of research, which can be categorized into threshold-based FDSs using experience, machine learning-based FDSs using manual feature extraction, and deep learning (DL)-based FDSs using automatic feature extraction. However, most FDSs focus on the global information of sensor data, neglecting the fact that different segments of the data contribute variably to fall detection. This shortcoming makes it challenging for FDSs to accurately distinguish between similar human motion patterns of actual falls and fall-like actions, leading to a decrease in detection accuracy.
OBJECTIVE: This study aims to develop and validate a DL framework to accurately detect falls using acceleration and gyroscope data from wearable sensors. We aim to explore the essential contributing features extracted from sensor data to distinguish falls from activities of daily life. The significance of this study lies in reforming the FDS by designing a weighted feature representation using DL methods to effectively differentiate between fall events and fall-like activities.
METHODS: Based on the 3-axis acceleration and gyroscope data, we proposed a new DL architecture, the dual-stream convolutional neural network self-attention (DSCS) model. Unlike previous studies, the used architecture can extract global feature information from acceleration and gyroscope data. Additionally, we incorporated a self-attention module to assign different weights to the original feature vector, enabling the model to learn the contribution effect of the sensor data and enhance classification accuracy. The proposed model was trained and tested on 2 public data sets: SisFall and MobiFall. In addition, 10 participants were recruited to carry out practical validation of the DSCS model. A total of 1700 trials were performed to test the generalization ability of the model.
RESULTS: The fall detection accuracy of the DSCS model was 99.32% (recall=99.15%; precision=98.58%) and 99.65% (recall=100%; precision=98.39%) on the test sets of SisFall and MobiFall, respectively. In the ablation experiment, we compared the DSCS model with state-of-the-art machine learning and DL models. On the SisFall data set, the DSCS model achieved the second-best accuracy; on the MobiFall data set, the DSCS model achieved the best accuracy, recall, and precision. In practical validation, the accuracy of the DSCS model was 96.41% (recall=95.12%; specificity=97.55%).
CONCLUSIONS: This study demonstrates that the DSCS model can significantly improve the accuracy of fall detection on 2 publicly available data sets and performs robustly in practical validation.

UNASSIGNED: Scoliosis is a multifaceted three-dimensional deformity that significantly affects patients\' balance function and walking process. While existing research primarily focuses on spatial and temporal parameters of walking and trunk/pelvic kinematics asymmetry, there remains controversy regarding the symmetry and regularity of bilateral lower limb gait. This study aims to investigate the symmetry and regularity of bilateral lower limb gait and examine the balance control strategy of the head during walking in patients with idiopathic scoliosis.
UNASSIGNED: The study involved 17 patients with idiopathic scoliosis of Lenke 1 and Lenke 5 classifications, along with 17 healthy subjects for comparison. Three-dimensional accelerometers were attached to the head and L5 spinous process of each participant, and three-dimensional motion acceleration signals were collected during a 10-meter walking test. Analysis of the collected acceleration signals involved calculating five variables related to the symmetry and regularity of walking: root mean square (RMS) of the acceleration signal, harmonic ratio (HR), step regularity, stride regularity, and gait symmetry.
UNASSIGNED: Our analysis reveals that, during the walking process, the three-dimensional motion acceleration signals acquired from the lumbar region of patients diagnosed with idiopathic scoliosis exhibit noteworthy disparities in the RMS of the vertical axis (RMS-VT) and the HR of the vertical axis (HR-VT) when compared to the corresponding values in the healthy control (RMS-VT: 1.6 ± 0.41 vs. 3 ± 0.47, P < 0.05; HR-VT: 3 ± 0.72 vs. 3.9 ± 0.71, P < 0.05). Additionally, the motion acceleration signals of the head in three-dimensional space, including the RMS in the anterior-posterior and vertical axis, the HR-VT, and the values of step regularity in both anterior-posterior and vertical axis, as well as the values of stride regularity in all three axes, are all significantly lower than those in the healthy control group (P < 0.05).
UNASSIGNED: The findings of the analysis suggest that the application of three-dimensional accelerometer sensors proves efficacious and convenient for scrutinizing the symmetry and regularity of walking in individuals with idiopathic scoliosis. Distinctive irregularities in gait symmetry and regularity manifest in patients with idiopathic scoliosis, particularly within the antero-posterior and vertical direction. Moreover, the dynamic balance control strategy of the head in three-dimensional space among patients with idiopathic scoliosis exhibits a relatively conservative nature when compared to healthy individuals.

Freezing of Gait (FOG) is a noticeable symptom of Parkinson\'s disease, like being stuck in place and increasing the risk of falls. The wearable multi-channel sensor system is an efficient method to predict and monitor the FOG, thus warning the wearer to avoid falls and improving the quality of life. However, the existing approaches for the prediction of FOG mainly focus on a single sensor system and cannot handle the interference between multi-channel wearable sensors. Hence, we propose a novel multi-channel time-series neural network (MCT-Net) approach to merge multi-channel gait features into a comprehensive prediction framework, alerting patients to FOG symptoms in advance. Owing to the causal distributed convolution, MCT-Net is a real-time method available to give optimal prediction earlier and implemented in remote devices. Moreover, intra-channel and inter-channel transformers of MCT-Net extract and integrate different sensor position features into a unified deep learning model. Compared with four other state-of-the-art FOG prediction baselines, the proposed MCT-Net obtains 96.21% in accuracy and 80.46% in F1-score on average 2 s before FOG occurrence, demonstrating the superiority of MCT-Net.

Wearable electronic sensors have recently attracted tremendous attention in applications such as personal health monitoring, human movement detection, and sensory skins as they offer a promising alternative to counterparts made from traditional metallic conductors and bulky metallic conductors. However, the real-world use of most wearable sensors is often hindered by their limited stretchability and sensitivity, and ultimately, their difficulty to integrate into textiles. To overcome these limitations, wearable sensors can incorporate flexible conductive fibers as electrically active components. In this study, we adopt a scalable wet-spinning approach to directly produce flexible and conductive fibers from aqueous mixtures of Ti3C2Tx MXene and natural rubber (NR). The electrical conductivity and stretchability of these fibers were tuned by varying their MXene loading, enabling knittability into textiles for wearable sensors. As individual filaments, these MXene/NR fibers exhibit suitable conductivity dependence on strain variations, making them ideal for motivating sensors. Meanwhile, textiles from knitted MXene/NR fibers demonstrate great stability as capacitive touch sensors. Collectively, we believe that these elastic and conductive MXene/NR-based fibers and textiles are promising candidates for wearable sensors and smart textiles.

Pursuing high-performance conductive hydrogels is still hot topic in development of advanced flexible wearable devices. Herein, a tough, self-healing, adhesive double network (DN) conductive hydrogel (named as OSA-(Gelatin/PAM)-Ca, O-(G/P)-Ca) was prepared by bridging gelatin and polyacrylamide network with functionalized polysaccharide (oxidized sodium alginate, OSA) through Schiff base reaction. Thanks to the presence of multiple interactions (Schiff base bond, hydrogen bond, and metal coordination) within the network, the prepared hydrogel showed outstanding mechanical properties (tensile strain of 2800 % and stress of 630 kPa), high conductivity (0.72 S/m), repeatable adhesion performance and excellent self-healing ability (83.6 %/79.0 % of the original tensile strain/stress after self-healing). Moreover, the hydrogel-based sensor exhibited high strain sensitivity (GF = 3.66) and fast response time (<0.5 s), which can be used to monitor a wide range of human physiological signals. Based on this, excellent compression sensitivity (GF = 0.41 kPa-1 in the range of 90-120 kPa), a three-dimensional (3D) array of flexible sensor was designed to monitor the intensity of pressure and spatial force distribution. In addition, a gel-based wearable sensor was accurately classified and recognized ten types of gestures, achieving an accuracy rate of >96.33 % both before and after self-healing under three machine learning models (the decision tree, SVM, and KNN). This paper provides a simple method to prepare tough and self-healing conductive hydrogel as flexible multifunctional sensor devices for versatile applications in fields such as healthcare monitoring, human-computer interaction, and artificial intelligence.

Skiing technique and performance improvements are crucial for athletes and enthusiasts alike. This study presents SnowMotion, a digital human motion training assistance platform that addresses the key challenges of reliability, real-time analysis, usability, and cost in current motion monitoring techniques for skiing. SnowMotion utilizes wearable sensors fixed at five key positions on the skier\'s body to achieve high-precision kinematic data monitoring. The monitored data are processed and analyzed in real time through the SnowMotion app, generating a panoramic digital human image and reproducing the skiing motion. Validation tests demonstrated high motion capture accuracy (cc > 0.95) and reliability compared to the Vicon system, with a mean error of 5.033 and a root-mean-square error of less than 12.50 for typical skiing movements. SnowMotion provides new ideas for technical advancement and training innovation in alpine skiing, enabling coaches and athletes to analyze movement details, identify deficiencies, and develop targeted training plans. The system is expected to contribute to popularization, training, and competition in alpine skiing, injecting new vitality into this challenging sport.

Hydrogel bioelectronics has been widely used in wearable sensors, electronic skin, human-machine interfaces, and implantable tissue-electrode interfaces, providing great convenience for human health, safety, and education. The generation of electronic waste from bioelectronic devices jeopardizes human health and the natural environment. The development of degradable and recyclable hydrogels is recognized as a paradigm for realizing the next generation of environmentally friendly and sustainable bioelectronics. This review first summarizes the wide range of applications for bioelectronics, including wearable and implantable devices. Then, the employment of natural and synthetic polymers in hydrogel bioelectronics is discussed in terms of degradability and recyclability. Finally, this work provides constructive thoughts and perspectives on the current challenges toward hydrogel bioelectronics, providing valuable insights and guidance for the future evolution of sustainable hydrogel bioelectronics.

Nanomaterials based therapeutics transform the ways of disease prevention, diagnosis and treatment with increasing sophistications in nanotechnology at a breakneck pace, but very few could reach to the clinic due to inconsistencies in preclinical studies followed by regulatory hinderances. To tackle this, integrating the nanomedicine discovery with digital medicine provide technologies as tools of specific biological activity measurement. Hence, overcome the redundancies in nanomedicine discovery by the on-site data acquisition and analytics through integrating intelligent sensors and artificial intelligence (AI) or machine learning (ML). Integrated AI/ML wearable sensors directly gather clinically relevant biochemical information from the subject\'s body and process data for physicians to make right clinical decision(s) in a time and cost-effective way. This review summarizes insights and recommend the infusion of actionable big data computation enabled sensors in burgeoning field of nanomedicine at academia, research institutes, and pharmaceutical industries, with a potential of clinical translation. Furthermore, many blind spots are present in modern clinically relevant computation, one of which could prevent ML-guided low-cost new nanomedicine development from being successfully translated into the clinic was also discussed.

The current generation of wearable sensors often experiences signal interference and external corrosion, leading to device degradation and failure. To address these challenges, the biomimetic superhydrophobic approach has been developed, which offers self-cleaning, low adhesion, corrosion resistance, anti-interference, and other properties. Such surfaces possess hierarchical nanostructures and low surface energy, resulting in a smaller contact area with the skin or external environment. Liquid droplets can even become suspended outside the flexible electronics, reducing the risk of pollution and signal interference, which contributes to the long-term stability of the device in complex environments. Additionally, the coupling of superhydrophobic surfaces and flexible electronics can potentially enhance the device performance due to their large specific surface area and low surface energy. However, the fragility of layered textures in various scenarios and the lack of standardized evaluation and testing methods limit the industrial production of superhydrophobic wearable sensors. This review provides an overview of recent research on superhydrophobic flexible wearable sensors, including the fabrication methodology, evaluation, and specific application targets. The processing, performance, and characteristics of superhydrophobic surfaces are discussed, as well as the working mechanisms and potential challenges of superhydrophobic flexible electronics. Moreover, evaluation strategies for application-oriented superhydrophobic surfaces are presented.