Electronic Skin: Opportunities and Challenges in Convergence with Machine Learning.

Recent advancements in soft electronic skin (e-skin) have led to the development of human-like devices that reproduce the skin's functions and physical attributes. These devices are being explored for applications in robotic prostheses as well as for collecting biopotentials for disease diagnosis and treatment, as exemplified by biomedical e-skins. More recently, machine learning (ML) has been utilized to enhance device control accuracy and data processing efficiency. The convergence of e-skin technologies with ML is promoting their translation into clinical practice, especially in healthcare. This review highlights the latest developments in ML-reinforced e-skin devices for robotic prostheses and biomedical instrumentations. We first describe technological breakthroughs in state-of-the-art e-skin devices, emphasizing technologies that achieve skin-like properties. We then introduce ML methods adopted for control optimization and pattern recognition, followed by practical applications that converge the two technologies. Lastly, we briefly discuss the challenges this interdisciplinary research encounters in its clinical and industrial transition.

Effect of Grade and Surface Type on Peak Tibial Acceleration in Trained Distance Runners.

Runners experience repeated impact forces during training, and the culmination of these forces can contribute to overuse injuries. The purpose of this study was to compare peak vertical tibial acceleration (TA) in trained distance runners on 3 surface types (grass, asphalt, and concrete) and 3 grades (incline, decline, and level). During visit 1, subjects completed a 1-mile time trial to determine their pace for all running trials: 80% (5%) of the average time trial velocity. During visit 2, subjects were outfitted with a skin-mounted accelerometer and performed 18 separate running trials during which peak TA was assessed during the stance phase. Each subject ran 2 trials for each condition with 2 minutes of rest between trials. Peak TA was different between decline (8.04 [0.12] g) and incline running (7.31 [0.35] g; P = .020). On the level grade, peak TA was greater during grass (8.22 [1.22] g) compared with concrete (7.47 [1.65] g; P = .017). On the incline grade, grass (7.68 [1.44] g) resulted in higher peak TA than asphalt (6.99 [1.69] g; P = .030). These results suggest that under certain grade conditions grass may result in higher TA compared with either concrete or asphalt.

Assessment of Stability of MIMU Probes to Skin-Marker-Based Anatomical Reference Frames During Locomotion Tasks: Effect of Different Locations on the Lower Limb.

Soft tissue artefacts (STAs) undermine the validity of skin-mounted approaches to measure skeletal kinematics. Magneto-inertial measurement units (MIMU) gained popularity due to their low cost and ease of use. Although the reliability of different protocols for marker-based joint kinematics estimation has been widely reported, there are still no indications on where to place MIMU to minimize STA. This study aims to find the most stable positions for MIMU placement, among four positions on the thigh, four on the shank, and three on the foot. Stability was investigated by measuring MIMU movements against an anatomical reference frame, defined according to a standard marker-based approach. To this aim, markers were attached both on the case of each MIMU (technical frame) and on bony landmarks (anatomical frame). For each MIMU, the nine angles between each versor of the technical frame with each versor of the corresponding anatomical frame were computed. The maximum standard deviation of these angles was assumed as the instability index of MIMU-body coupling. Six healthy subjects were asked to perform barefoot gait, step negotiation, and sit-to-stand. Results showed that (1) in the thigh, the frontal position was the most stable in all tasks, especially in gait; (2) in the shank, the proximal position is the least stable, (3) lateral or medial calcaneus and foot dorsum positions showed equivalent stability performances. Further studies should be done before generalizing these conclusions to different motor tasks and MIMU-body fixation methods. The above results are of interest for both MIMU-based gait analysis and rehabilitation approaches using wearable sensors-based biofeedback.

Stretchable, Self-Healing, and Skin-Mounted Active Sensor for Multipoint Muscle Function Assessment.

Assessment of muscle function is an essential indicator for estimating elderly health, evaluating motor function, and instructing rehabilitation training, which also sets urgent requirements for mechanical sensors with superior quantification, accuracy, and reliability. To overcome the rigidity and vulnerability of traditional metallic electrodes, we synthesize an ionic hydrogel with large deformation tolerance and fast self-healing ability. And we propose a stretchable, self-healing, and skin-mounted (Triple S) active sensor (TSAS) based on the principles of electrostatic induction and electrostatic coupling. The skin modulus-matched TSAS provides outstanding sensing properties: maximum output voltage of 78.44 V, minimal detection limit of 0.2 mN, fast response time of 1.03 ms, high signal-to-noise ratio and excellent long-term service stability. In training of arm muscle, the functional signals of biceps and triceps brachii muscles as well as the joint dexterity of bending angle can be acquired simultaneously through TSAS. The signal can also be sent wirelessly to a terminal for analysis. With the characteristics of high sensitivity, reliability, convenience, and low-cost, TSAS shows its potential to be the next-generation procedure for real-time assessment of muscle function and rehabilitation training.

Flexible Wearable Sensors for Cardiovascular Health Monitoring.

Cardiovascular diseases account for the highest mortality globally, but recent advances in wearable technologies may potentially change how these illnesses are diagnosed and managed. In particular, continuous monitoring of cardiovascular vital signs for early intervention is highly desired. To this end, flexible wearable sensors that can be comfortably worn over long durations are gaining significant attention. In this review, advanced flexible wearable sensors for monitoring cardiovascular vital signals are outlined and discussed. Specifically, the functional materials, configurations, mechanisms, and recent advances of these flexible sensors for heart rate, blood pressure, blood oxygen saturation, and blood glucose monitoring are highlighted. Different mechanisms in bioelectric, mechano-electric, optoelectric, and ultrasonic wearable sensors are presented to monitor cardiovascular vital signs from different body locations. Present challenges, possible strategies, and future directions of these wearable sensors are also discussed. With rapid development, these flexible wearable sensors will potentially be applicable for both medical diagnosis and daily healthcare use in tackling cardiovascular diseases.

Precision of determining bone pose and marker position in the foot and lower leg from computed tomography scans: How low can we go in radiation dose?

Computed tomography (CT) imaging can be used to determine bone pose, sometimes combined with skin-mounted markers. For this specific application, a lower radiation dose than the conventional clinical dose might suffice. This study aims to determine how lowering the radiation dose of a CT-scan of the ankle and foot affects the precision of detecting bone pose and marker position. Radiation dose is proportional to tube charge. Hence, an adult cadaveric leg was scanned 10 times at four different tube charges (150, 75, 50 and 20 mAs) with a Philips Brilliance 64 CT scanner. Precision of detecting bone and marker position at 50 mAs was not significantly different from 75 mAs and from the clinically used 150 mAs, but higher than 20 mAs. Furthermore, no differences of the precision in detecting bone orientation were found. These results indicate that the radiation dose can be reduced by a factor 3 compared to the clinically usual radiation dose, without affecting the precision of detecting bone pose and marker position in the foot and ankle.

Directional bias of soft-tissue artifacts on the acromion during recording of 3D scapular kinematics.

Scapular kinematics during sports performances can be recorded using skin-mounted trackers attached to the skin overlying the acromion for continuous data collection without restricting natural motions of the subject relative to medical imaging analyses limiting its use for wide-range or high-speed motions. This study aimed to describe the existence of a directional bias in the translational and rotational errors of skin-mounted trackers using a 3D magnetic resonance imaging (3D-MRI) protocol. 3D-MRI scans of the healthy right shoulders of 19 males were acquired in 12 arm positions. The relative transformation of the scapular configuration determined to be the measurement error, as recorded by the configuration of the small cuboid imitating a skin-mounted tracker relative to the actual scapular configuration measured by the voxel-based registration. These measurement errors were expressed with either positive or negative values to describe the bias. Overall translational errors in the lateral, anterior, and superior directions were 3.7 ±â€¯8.4 mm, 9.5 ±â€¯6.4 mm, and 6.2 ±â€¯4.6 mm, respectively. Overall rotational errors in protraction, upward rotation, and posterior tilt were 7.8 ±â€¯8.4°, 0.2 ±â€¯7.4°, and - 4.0 ±â€¯7.5°, respectively. The skin-mounted tracker displayed a high probability of displacement in antero-superior (93% and 91%) directions and rotates in a protracting manner (82%) relative to the position of the underlying bone with the gradual nature of its change. The existence of the directional bias with its gradual change suggests a statistical predictability in measurement errors, which can be used to predict accurate scapular translation and rotation.