Recent years have witnessed tremendous advances in machine learning techniques for wearable sensors and bioelectronics, which play an essential role in real-time sensing data analysis to provide clinical-grade information for personalized healthcare. To this end, supervised learning and unsupervised learning algorithms have emerged as powerful tools, allowing for the detection of complex patterns and relationships in large, high-dimensional data sets. In this Review, we aim to delineate the latest advancements in machine learning for wearable sensors, focusing on key developments in algorithmic techniques, applications, and the challenges intrinsic to this evolving landscape. Additionally, we highlight the potential of machine-learning approaches to enhance the accuracy, reliability, and interpretability of wearable sensor data and discuss the opportunities and limitations of this emerging field. Ultimately, our work aims to provide a roadmap for future research endeavors in this exciting and rapidly evolving area.

BACKGROUND: The diagnosis of Parkinson\'s disease is currently based on clinical evaluation. Despite clinical hallmarks, unfortunately, the error rate is still significant. Low in-vivo diagnostic accuracy of clinical evaluation mainly relies on the lack of quantitative biomarkers for an objective motor performance assessment. Non-invasive technologies, such as wearable sensors, coupled with machine learning algorithms, assess quantitatively and objectively the motor performances, with possible benefits either for in-clinic and at-home settings. We conducted a systematic review of the literature on machine learning algorithms embedded in smart devices in Parkinson\'s disease diagnosis.
METHODS: Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, we searched PubMed for articles published between December, 2007 and July, 2023, using a search string combining \"Parkinson\'s disease\" AND (\"healthy\" or \"control\") AND \"diagnosis\", within the Groups and Outcome domains. Additional search terms included \"Algorithm\", \"Technology\" and \"Performance\".
RESULTS: From 89 identified studies, 47 met the inclusion criteria based on the search string and four additional studies were included based on the Authors\' expertise. Gait emerged as the most common parameter analysed by machine learning models, with Support Vector Machines as the prevalent algorithm. The results suggest promising accuracy with complex algorithms like Random Forest, Support Vector Machines, and K-Nearest Neighbours.
CONCLUSIONS: Despite the promise shown by machine learning algorithms, real-world applications may still face limitations. This review suggests that integrating machine learning with wearable sensors has the potential to improve Parkinson\'s disease diagnosis. These tools could provide clinicians with objective data, potentially aiding in earlier detection.

The proliferation of wearable technology enables the generation of vast amounts of sensor data, offering significant opportunities for advancements in health monitoring, activity recognition, and personalized medicine. However, the complexity and volume of these data present substantial challenges in data modeling and analysis, which have been addressed with approaches spanning time series modeling to deep learning techniques. The latest frontier in this domain is the adoption of large language models (LLMs), such as GPT-4 and Llama, for data analysis, modeling, understanding, and human behavior monitoring through the lens of wearable sensor data. This survey explores the current trends and challenges in applying LLMs for sensor-based human activity recognition and behavior modeling. We discuss the nature of wearable sensor data, the capabilities and limitations of LLMs in modeling them, and their integration with traditional machine learning techniques. We also identify key challenges, including data quality, computational requirements, interpretability, and privacy concerns. By examining case studies and successful applications, we highlight the potential of LLMs in enhancing the analysis and interpretation of wearable sensor data. Finally, we propose future directions for research, emphasizing the need for improved preprocessing techniques, more efficient and scalable models, and interdisciplinary collaboration. This survey aims to provide a comprehensive overview of the intersection between wearable sensor data and LLMs, offering insights into the current state and future prospects of this emerging field.

Quantitative mobility analysis using wearable sensors, while promising as a diagnostic tool for Parkinson\'s disease (PD), is not commonly applied in clinical settings. Major obstacles include uncertainty regarding the best protocol for instrumented mobility testing and subsequent data processing, as well as the added workload and complexity of this multi-step process. To simplify sensor-based mobility testing in diagnosing PD, we analyzed data from 262 PD participants and 50 controls performing several motor tasks wearing a sensor on their lower back containing a triaxial accelerometer and a triaxial gyroscope. Using ensembles of heterogeneous machine learning models incorporating a range of classifiers trained on a set of sensor features, we show that our models effectively differentiate between participants with PD and controls, both for mixed-stage PD (92.6% accuracy) and a group selected for mild PD only (89.4% accuracy). Omitting algorithmic segmentation of complex mobility tasks decreased the diagnostic accuracy of our models, as did the inclusion of kinesiological features. Feature importance analysis revealed that Timed Up and Go (TUG) tasks to contribute the highest-yield predictive features, with only minor decreases in accuracy for models based on cognitive TUG as a single mobility task. Our machine learning approach facilitates major simplification of instrumented mobility testing without compromising predictive performance.

Physical therapy is often essential for complete recovery after injury. However, a significant population of patients fail to adhere to prescribed exercise regimens. Lack of motivation and inconsistent in-person visits to physical therapy are major contributing factors to suboptimal exercise adherence, slowing the recovery process. With the advancement of virtual reality (VR), researchers have developed remote virtual rehabilitation systems with sensors such as inertial measurement units. A functional garment with an integrated wearable sensor can also be used for real-time sensory feedback in VR-based therapeutic exercise and offers affordable remote rehabilitation to patients. Sensors integrated into wearable garments offer the potential for a quantitative range of motion measurements during VR rehabilitation. In this research, we developed and validated a carbon nanocomposite-coated knit fabric-based sensor worn on a compression sleeve that can be integrated with upper-extremity virtual rehabilitation systems. The sensor was created by coating a commercially available weft knitted fabric consisting of polyester, nylon, and elastane fibers. A thin carbon nanotube composite coating applied to the fibers makes the fabric electrically conductive and functions as a piezoresistive sensor. The nanocomposite sensor, which is soft to the touch and breathable, demonstrated high sensitivity to stretching deformations, with an average gauge factor of ~35 in the warp direction of the fabric sensor. Multiple tests are performed with a Kinarm end point robot to validate the sensor for repeatable response with a change in elbow joint angle. A task was also created in a VR environment and replicated by the Kinarm. The wearable sensor can measure the change in elbow angle with more than 90% accuracy while performing these tasks, and the sensor shows a proportional resistance change with varying joint angles while performing different exercises. The potential use of wearable sensors in at-home virtual therapy/exercise was demonstrated using a Meta Quest 2 VR system with a virtual exercise program to show the potential for at-home measurements.

In the context in which severe visual impairment significantly affects human life, this article emphasizes the potential of Artificial Intelligence (AI) and Visible Light Communications (VLC) in developing future assistive technologies. Toward this path, the article summarizes the features of some commercial assistance solutions, and debates the characteristics of VLC and AI, emphasizing their compatibility with blind individuals\' needs. Additionally, this work highlights the AI potential in the efficient early detection of eye diseases. This article also reviews the existing work oriented toward VLC integration in blind persons\' assistive applications, showing the existing progress and emphasizing the high potential associated with VLC use. In the end, this work provides a roadmap toward the development of an integrated AI-based VLC assistance solution for visually impaired people, pointing out the high potential and some of the steps to follow. As far as we know, this is the first comprehensive work which focuses on the integration of AI and VLC technologies in visually impaired persons\' assistance domain.

BACKGROUND: Wearable physiological monitoring devices are promising tools for remote monitoring and early detection of potential health changes of interest. The widespread adoption of such an approach across communities and over long periods of time will require an automated data platform for collecting, processing, and analyzing relevant health information.
OBJECTIVE: In this study, we explore prospective monitoring of individual health through an automated data collection, metrics extraction, and health anomaly analysis pipeline in free-living conditions over a continuous monitoring period of several months with a focus on viral respiratory infections, such as influenza or COVID-19.
METHODS: A total of 59 participants provided smartwatch data and health symptom and illness reports daily over an 8-month window. Physiological and activity data from photoplethysmography sensors, including high-resolution interbeat interval (IBI) and step counts, were uploaded directly from Garmin Fenix 6 smartwatches and processed automatically in the cloud using a stand-alone, open-source analytical engine. Health risk scores were computed based on a deviation in heart rate and heart rate variability metrics from each individual\'s activity-matched baseline values, and scores exceeding a predefined threshold were checked for corresponding symptoms or illness reports. Conversely, reports of viral respiratory illnesses in health survey responses were also checked for corresponding changes in health risk scores to qualitatively assess the risk score as an indicator of acute respiratory health anomalies.
RESULTS: The median average percentage of sensor data provided per day indicating smartwatch wear compliance was 70%, and survey responses indicating health reporting compliance was 46%. A total of 29 elevated health risk scores were detected, of which 12 (41%) had concurrent survey data and indicated a health symptom or illness. A total of 21 influenza or COVID-19 illnesses were reported by study participants; 9 (43%) of these reports had concurrent smartwatch data, of which 6 (67%) had an increase in health risk score.
CONCLUSIONS: We demonstrate a protocol for data collection, extraction of heart rate and heart rate variability metrics, and prospective analysis that is compatible with near real-time health assessment using wearable sensors for continuous monitoring. The modular platform for data collection and analysis allows for a choice of different wearable sensors and algorithms. Here, we demonstrate its implementation in the collection of high-fidelity IBI data from Garmin Fenix 6 smartwatches worn by individuals in free-living conditions, and the prospective, near real-time analysis of the data, culminating in the calculation of health risk scores. To our knowledge, this study demonstrates for the first time the feasibility of measuring high-resolution heart IBI and step count using smartwatches in near real time for respiratory illness detection over a long-term monitoring period in free-living conditions.

Triboelectric nanogenerators (TENG) are promising alternatives for clean energy harvesting. However, the material utilization in the development of TENG relies majorly on polymers derived from non-renewable resources. Therefore, minimizing the carbon footprint associated with such TENG development demands a shift toward usage of sustainable materials. This study pioneers using natural rubber (NR) as a sustainable alternative in TENG development. Infusing graphene in NR, its dielectric constant and tribonegativity are optimized, yielding a remarkable enhancement. The optimized sample exhibits a dielectric constant of 411 (at 103 Hz) and a contact potential difference (CPD) value of 1.85 V. In contrast, the pristine NR sample showed values of 6 and 3.06 V for the dielectric constant and CPD. Simulation and experimental studies fine-tune the TENG\'s performance, demonstrating excellent agreement between theoretical predictions and practical studies. Sensors developed via stencil printing technique possess a remarkably low layer thickness of 270 µm, and boast a power density of 420 mW m-2, a staggering 250% increase over conventional NR. Moreover, the material is pressure sensitive, enabling precise real-time human motion detection, including finger contact, finger bending, neck bending, and arm bending. This versatile sensor offers wireless monitoring, empowering healthcare monitoring based on the Internet of Things.

OBJECTIVE: Discerning the differential contribution of sleep behavior and sleep physiology to the subsequent development of posttraumatic-stress-disorder (PTSD) symptoms following military operational service among combat soldiers.
METHODS: Longitudinal design with three measurement time points: during basic training week (T1), during intensive stressed training week (T2), and following military operational service (T3). Participating soldiers were all from the same unit, ensuring equivalent training schedules and stress exposures. During measurement weeks soldiers completed the Depression Anxiety and Stress Scale (DASS) and the PTSD Checklist for DSM-5 (PCL-5). Sleep physiology (sleep heart-rate) and sleep behavior (duration, efficiency) were monitored continuously in natural settings during T1 and T2 weeks using wearable sensors.
RESULTS: Repeated measures ANOVA revealed a progressive increase in PCL-5 scores from T1 and T2 to T3, suggesting an escalation in PTSD symptom severity following operational service. Hierarchical linear regression analysis uncovered a significant relation between the change in DASS stress scores from T1 to T2 and subsequent PCL-5 scores at T3. Incorporating participants\' sleep heart-rate markedly enhanced the predictive accuracy of the model, with increased sleep heart-rate from T1 to T2 emerging as a significant predictor of elevated PTSD symptoms at T3, above and beyond the contribution of DASS stress scores. Sleep behavior did not add to the accuracy of the model.
CONCLUSIONS: Findings underscore the critical role of sleep physiology, specifically elevated sleep heart-rate following stressful military training, in indicating subsequent PTSD risk following operational service among combat soldiers. These findings may contribute to PTSD prediction and prevention efforts.

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.