Search Results (120)

During the in-hospital optimization of dopaminergic dosage for Parkinson’s disease, drug-induced dyskinesias emerge as a common side effect. Wrist-worn devices present a substantial opportunity for continuous movement recording and the supportive identification of these dyskinesias. To bridge the gap between dyskinesia assessment and machine learning-enabled detection, the recorded information requires meaningful data representations. This study evaluates and compares two distinct representations of sensor data: a task-dependent, semantically grounded approach and automatically extracted large-scale time-series features. Each representation was assessed on public datasets to identify the best-performing machine learning model and subsequently applied to our own collected dataset to assess generalizability. Data representations incorporating semantic knowledge demonstrated comparable or superior performance to reported works, with peak F₁ scores of 0.68. Generalization to our own dataset from clinical practice resulted in an observed F₁ score of 0.53 using both setups. These results highlight the potential of semantic movement data analysis for dyskinesia detection. Dimensionality reduction in accelerometer-based movement data positively impacts performance, and models trained with semantically obtained features avoid overfitting. Expanding cohorts with standardized neurological assessments labeled by medical experts is essential for further improvements. Full article

This paper describes the modelling of Key Health Indicators (KHI) of frail individuals through non-invasive sensors located in their environment and wearable devices. Primary care professionals defined four indicators for daily health monitoring: sleep patterns, excretion control, physical mobility, and caregiver social interaction. A minimally invasive and low-cost sensing architecture was implemented, combining indoor localisation and physical activity tracking through environmental sensors and wrist-worn wearables. The health outcomes are modelled using a knowledge-based framework that integrates knowledge graphs to represent control variables and their relationships with data streams, and fuzzy logic to linguistically define temporal patterns based on expert criteria. The proposed approach was validated in a real-world case study with an older adult living independently in Granada, Spain. Over several days of deployment, the system successfully generated interpretable daily summaries reflecting relevant behavioural patterns, including rest periods, bathroom usage, activity levels, and caregiver proximity. In addition, supervised machine learning models were trained on the indicators derived from the fuzzy logic system, achieving average accuracy and F1 scores of 93% and 92%, respectively. These results confirm the potential of combining expert-informed semantics with data-driven inference to support continuous, explainable health monitoring in ambient assisted living environments. Full article

Background/Objectives: Atrial fibrillation (AF) remains a major risk factor for stroke. It is often asymptomatic and paroxysmal, making it difficult to detect with conventional electrocardiography (ECG). While photoplethysmography (PPG)-based devices like smartwatches have demonstrated efficacy in detecting AF, they are rarely integrated into hospital infrastructure. The study aimed to establish a seamless system for real-time AF screening in hospitalized high-risk patients using a wrist-worn PPG device integrated into a hospital’s data infrastructure. Methods: In this investigator-initiated prospective clinical trial conducted at the University Hospital Basel, patients with a CHA₂DS₂-VASc score ≥ 2 and no history of AF received a wristband equipped with a PPG sensor for continuous monitoring during their hospital stay. The PPG data were automatically transmitted, analyzed, stored, and visualized. Upon detection of an absolute arrhythmia (AA) in the PPG signal, a Holter ECG was administered. Results: The analysis encompassed 346 patients (mean age 72 ± 10 years, 175 females (50.6%), mean CHA₂DS₂-VASc score 3.5 ± 1.3)). The mean monitoring duration was 4.3 ± 4.4 days. AA in the PPG signal was detected in twelve patients (3.5%, CI: 1.5–5.4%), with most cases identified within 24 h (p = 0.004). There was a 1.3 times higher AA burden during the nighttime compared to daytime (p = 0.03). Compliance was high (304/346, 87.9%). No instances of AF were confirmed in the nine patients undergoing Holter ECG. Conclusions: This study successfully pioneered an automated infrastructure for AF screening in hospitalized patients through the use of wrist-worn PPG devices. This implementation allowed for real-time data visualization and intervention in the form of a Holter ECG. The high compliance and early AA detection achieved in this study underscore the potential and relevance of this novel infrastructure in clinical practice. Full article

Background: Wearable sensors are mainly used in Parkinson’s disease (PD) to assess motor symptoms and to aid clinicians in patient management. Inertial measurement units that simultaneously register accelerometric and gyroscope signals have been one of the most studied and practicable methods. The heterogeneity of described methods and clinical settings studied can discourage wearable device use and highlight the need for standardization. This study compares previously proposed accelerometry and gyroscope signal features for tremor assessment measured at the wrist. Methods: An inertial measurement unit registered accelerometry and gyroscope signals at the wrist from 18 PD patients treated with deep brain stimulation (DBS). Measurements were made in DBS on and off states. Signal features for both accelerometry and gyroscope were calculated—mean linear acceleration, mean angular velocity, root mean square, maximal amplitude and power of the 3–7 Hz frequency band. The outcome features were log-transformed and correlated to the Movement Disorder Society Unified Parkinson’s Disease Rating Scale (MDS-UPDRS) item 3.17 using linear regression. Intraclass correlation coefficient (ICC) values were calculated for the signal features. Results: A total of 108 tremor episodes were investigated. All signal features exhibited a strong correlation with the MDS-UPDRS tremor amplitude scale. Tremor ratings showed a stronger correlation with accelerometry (r = 0.964–0.970) than with gyroscope-derived features (r = 0.942–0.956). The best-performing feature was the mean linear acceleration (r = 0.970, R² = 0.940), which also showed high reliability (ICC = 0.921). Conclusions: Different accelerometry and gyroscope signal features are viable in characterizing rest tremor at the wrist. Simpler accelerometry signal features can be preferred in conducting the MDS-UPDRS item 3.17 examination in PD patients with DBS using a wrist-worn inertial measurement unit. Future research to expand the validity and usefulness of wearable technologies in PD is warranted. Full article

Many patients with major depressive disorder (MDD) feel worse in the morning than in the evening. To clarify the differences in morning physiological characteristics between patients with MDD and healthy participants, a wearable device that measures peripheral wrist skin temperature and heart rate (HR) was adopted. The device incorporates a thermopile sensor to measure peripheral wrist skin temperature using infrared radiation emitted from the skin surface. In total, 30 patients diagnosed with MDD and 24 healthy individuals were recruited. From 00:00 to 12:00, participants wore a wrist-worn device on their non-dominant hand. It was discovered that, at 09:00, the average peripheral wrist skin temperature of patients with MDD was significantly lower (by 0.1% [2.9 °C]) than that of healthy individuals. The dramatic decrease in morning (09:00) peripheral wrist skin temperature in patients with MDD can be attributed to their morning sympathetic surge and peripheral vascular contraction. The average HR of patients with MDD was significantly higher (by 1% [17 beats/min]) than that of healthy controls. Regression analysis, including peripheral wrist skin temperature and HR at 09:00, showed 83.3% sensitivity and a negative predictive value of 76.2%. The potential impact of these results appears promising for future preliminary morning MDD screening. Full article

Cognitive rumination, a transdiagnostic symptom across mental health disorders, has traditionally been assessed through self-report measures. However, these measures are limited by their temporal nature and subjective bias. The rise in wearable technologies offers the potential for continuous, real-time monitoring of physiological indicators associated with rumination. This scoping review investigates the current state of research on using wearable technology to detect cognitive rumination. Specifically, we examine the sensors and wearable devices used, physiological biomarkers measured, standard measures of rumination used, and the comparative validity of specific biomarkers in identifying cognitive rumination. The review was performed according to the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines on IEEE, Scopus, PubMed, and PsycInfo databases. Studies that used wearable devices to measure rumination-related physiological responses and biomarkers were included (n = 9); seven studies assessed one biomarker, and two studies assessed two biomarkers. Electrodermal Activity (EDA) sensors capturing skin conductance activity emerged as both the most prevalent sensor (n = 5) and the most comparatively valid biomarker for detecting cognitive rumination via wearable devices. Other commonly investigated biomarkers included electrical brain activity measured through Electroencephalogram (EEG) sensors (n = 2), Heart Rate Variability (HRV) measured using Electrocardiogram (ECG) sensors and heart rate fitness monitors (n = 2), muscle response measured through Electromyography (EMG) sensors (n = 1) and movement measured through an accelerometer (n = 1). The Empatica E4 and Empatica Embrace 2 wrist-worn devices were the most frequently used wearable (n = 3). The Rumination Response Scale (RRS), was the most widely used standard scale for assessing rumination. Experimental induction protocols, often adapted from Nolen-Hoeksema and Morrow’s 1993 rumination induction paradigm, were also widely used. In conclusion, the findings suggest that wearable technology offers promise in capturing real-time physiological responses associated with rumination. However, the field is still developing, and further research is needed to validate these findings and explore the impact of individual traits and contextual factors on the accuracy of rumination detection. Full article

Background: Following shoulder surgery, controlled and protected mobilisation for an appropriate duration is crucial for appropriate recovery. However, methods for objective assessment of sling wear and use in everyday living are currently lacking. In this pilot study, we aim to determine if a sling-embedded triaxial accelerometer and/or wrist-worn sensor can be used to quantify arm posture during sling wear and adherence to sling wear. Methods: Four participants were asked to wear a GENEActiv triaxial accelerometer on their non-dominant wrist for four hours in an office environment, and, for two of those hours, they also wore a sling in which an additional GENEActiv accelerometer was secured. During sling wear, they were asked to move their arm in the sling through a series of pre-specified arm postures. Results: We found that upper arm angle and posture type during sling wear can be predicted from a sling sensor alone (R² = 0.79, p < 0.001 and Cohen’s kappa = 0.886, respectively). The addition of a wrist-worn sensor did not improve performance. The optimisation of an existing non-wear algorithm accurately detected adherence (99.3%). Conclusions: the remote monitoring of sling adherence and the quantification of immobilisation is practical and effective with digital health technology. Full article

This study evaluated the reliability of Fitbit in assessing frailty based on motor and heart rate (HR) parameters through a validated upper extremity function (UEF) test, which involves 20 s of rapid elbow flexion. For motor performance, participants completed six trials of full elbow flexion using their right arm, with and without weight. Fitbit and a commercial motion sensor were worn on the right arm. For HR measurements, an ECG system was placed on the left chest alongside the Fitbit on the left wrist. Motor parameters assessing speed, flexibility, weakness, exhaustion, and HR before, during, and after UEF were measured. A total of 42 participants (age = 22 ± 3) were recruited. For motor parameters, excellent agreement was observed between the wearable sensor and Fitbit, except for flexibility (ICC = 0.87 ± 0.09). For HR parameters, ICC values showed weak agreement between ECG and Fitbit for HR increase and recovery (ICC = 0.24 ± 0.11), while moderate to stronger agreement was seen for mean HR during baseline, task, and post-task (ICC = 0.81 ± 0.13). Fitbit is a reliable tool for assessing frailty through motor parameters and provides reasonably accurate HR estimates during baseline, task, and recovery periods. However, Fitbit’s ability to track rapid HR changes during activity is limited. Full article

Tibia shaft fractures are common lower extremity fractures that can require surgery and rehabilitation. However, patient recovery is often poor, partly due to clinicians’ inability to monitor bone loading, which is critical to stimulating healing. We envision a future of patient care that includes at-home monitoring of tibia loading using pressure-sensing insoles. However, one issue is missing portions of daily loading due to limited insole wear time (e.g., not wearing shoes all day). Here, we introduce a method for overcoming this issue with a wrist-worn fitness tracker that can be worn all day. We developed a model to estimate tibia loading from fitness tracker data and evaluated its accuracy during 10-h remote data collections (N = 8). We found that a fitness tracker, with trained and calibrated models, could effectively supplement insole-based estimates of bone loading. Fitness tracker-based estimates of loading stimulus—the minute-by-minute weighted impulse of tibia loading—showed a strong fit relative to insole-based estimates (R² = 0.74). However, insoles needed to be worn for a minimum amount of time for accurate estimates. We found daily loading stimulus errors less than 5% when insoles were worn at least 25% of the day. These findings suggest that a multi-sensor approach—where insoles are worn intermittently and a fitness tracker is worn continuously throughout the day—could be a viable strategy for long-term, remote monitoring of tibia loading in daily life. Full article

Battery power is crucial for wearable devices as it ensures continuous operation, which is critical for real-time health monitoring and emergency alerts. One solution for long-lasting monitoring is energy harvesting systems. Ensuring a consistent energy supply from variable sources for reliable device performance is a major challenge. Additionally, integrating energy harvesting components without compromising the wearability, comfort, and esthetic design of healthcare devices presents a significant bottleneck. Here, we show that with a meticulous design using small and highly efficient photovoltaic (PV) panels, compact thermoelectric (TEG) modules, and two ultra-low-power BQ25504 DC-DC boost converters, the battery life can increase from 9.31 h to over 18 h. The parallel connection of boost converters at two points of the output allows both energy sources to individually achieve maximum power point tracking (MPPT) during battery charging. We found that under specific conditions such as facing the sun for more than two hours, the device became self-powered. Our results demonstrate the long-term and stable performance of the sensor node with an efficiency of 96%. Given the high-power density of solar cells outdoors, a combination of PV and TEG energy can harvest energy quickly and sufficiently from sunlight and body heat. The small form factor of the harvesting system and the environmental conditions of particular occupations such as the oil and gas industry make it suitable for health monitoring wearables worn on the head, face, or wrist region, targeting outdoor workers. Full article

This study examines the performance of various machine learning (ML) models in predicting Interstitial Glucose (IG) levels using data from wrist-worn wearable sensors. The insights from these predictions can aid in understanding metabolic syndromes and disease states. A public dataset comprising information from the Empatica E4 smart watch, the Dexcom Continuous Glucose Monitor (CGM) measuring IG, and a food log was utilized. The raw data were processed into features, which were then used to train different ML models. This study evaluates the performance of decision tree (DT), support vector machine (SVM), Random Forest (RF), Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Gaussian Naïve Bayes (GNB), lasso cross-validation (LassoCV), Ridge, Elastic Net, and XGBoost models. For classification, IG labels were categorized into high, standard, and low, and the performance of the ML models was assessed using accuracy (40–78%), precision (41–78%), recall (39–77%), F1-score (0.31–0.77), and receiver operating characteristic (ROC) curves. Regression models predicting IG values were evaluated based on R-squared values (−7.84–0.84), mean absolute error (5.54–60.84 mg/dL), root mean square error (9.04–68.07 mg/dL), and visual methods like residual and QQ plots. To assess whether the differences between models were statistically significant, the Friedman test was carried out and was interpreted using the Nemenyi post hoc test. Tree-based models, particularly RF and DT, demonstrated superior accuracy for classification tasks in comparison to other models. For regression, the RF model achieved the lowest RMSE of 9.04 mg/dL with an R-squared value of 0.84, while the GNB model performed the worst, with an RMSE of 68.07 mg/dL. A SHAP analysis identified time from midnight as the most significant predictor. Partial dependence plots revealed complex feature interactions in the RF model, contrasting with the simpler interactions captured by LDA. Full article

Walking is crucial for independence and quality of life. This study leverages wrist-worn sensor data from UK Biobank participants to establish normative daily-life walking data, stratified by age and sex, to provide benchmarks for research and clinical practice. The Watch Walk digital biomarkers were developed, validated, and applied to 92,022 participants aged 45–79 who wore a wrist sensor for at least three days. Normative data were collected for daily-life walking speed, step-time variability, step count, and 17 other gait and sleep biomarkers. Test–retest reliability was calculated, and associations with sex, age, self-reported walking pace, and mobility problems were examined. Population mean maximal and usual walking speeds were 1.49 and 1.15 m/s, respectively. The daily step count was 7749 steps, and step regularity was 65%. Women walked more regularly but slower than men. Walking speed, step count, longest walk duration, and step regularity decreased with age. Walking speed is associated with sex, age, self-reported pace, and mobility problems. Test–retest reliability was good to excellent (ICC ≥ 0.80). This study provides large-scale normative data and benchmarks for wrist-sensor-derived digital gait and sleep biomarkers from real-world data for future research and clinical applications. Full article

As Canada’s population of older adults rises, the need for aging-in-place solutions is growing due to the declining quality of long-term-care homes and long wait times. While the current standards include questionnaire-based assessments for monitoring activities of daily living (ADLs), there is an urgent need for advanced indoor localization technologies that ensure privacy. This study explores the use of Ultra-Wideband (UWB) technology for activity recognition in a mock condo in the Glenrose Rehabilitation Hospital. UWB systems with built-in Inertial Measurement Unit (IMU) sensors were tested, using anchors set up across the condo and a tag worn by patients. We tested various UWB setups, changed the number of anchors, and varied the tag placement (on the wrist or chest). Wrist-worn tags consistently outperformed chest-worn tags, and the nine-anchor configuration yielded the highest accuracy. Machine learning models were developed to classify activities based on UWB and IMU data. Models that included positional data significantly outperformed those that did not. The Random Forest model with a 4 s data window achieved an accuracy of 94%, compared to 79.2% when positional data were excluded. These findings demonstrate that incorporating positional data with IMU sensors is a promising method for effective remote patient monitoring. Full article

The provision of wireless and battery-free power is key to extending the applications of body-worn sensing electronics. This paper investigates the design of an IPT system for a body-worn scenario where the challenges include highly variable coupling, the requirement for the coil/s to be flexible, and close proximity to the body. Variable coupling results in a system that must operate with received powers ranging over orders of magnitude, whilst the use of flexible coils reduces the Q-factor and results in the potential for inductance variation. The human exposure considerations limit both the maximum field strengths that the wearer of a receiver coil might experience and the field strengths that a third party might be exposed to. In this paper, analytical models are used to identify key design variables and to guide the design synthesis of an IPT system for a wrist-worn medical sensor. Practical circuits to drive the transmit coil and to interface the receive coil with the load electronics are described. A prototype system is tested to validate the theoretical analysis, providing power greater than 2 mW to the sensor over a hemispherical region up to 250 mm in radius from the transmit coil. Full article

Metabolic syndrome poses a significant health challenge worldwide, prompting the need for comprehensive strategies integrating physical activity monitoring and energy expenditure. Wearable sensor devices have been used both for energy intake and energy expenditure (EE) estimation. Traditionally, sensors are attached to the hip or wrist. The primary aim of this research is to investigate the use of an eyeglass-mounted wearable energy intake sensor (Automatic Ingestion Monitor v2, AIM-2) for simultaneous recognition of physical activity (PAR) and estimation of steady-state EE as compared to a traditional hip-worn device. Study data were collected from six participants performing six structured activities, with the reference EE measured using indirect calorimetry (COSMED K5) and reported as metabolic equivalents of tasks (METs). Next, a novel deep convolutional neural network-based multitasking model (Multitasking-CNN) was developed for PAR and EE estimation. The Multitasking-CNN was trained with a two-step progressive training approach for higher accuracy, where in the first step the model for PAR was trained, and in the second step the model was fine-tuned for EE estimation. Finally, the performance of Multitasking-CNN on AIM-2 attached to eyeglasses was compared to the ActiGraph GT9X (AG) attached to the right hip. On the AIM-2 data, Multitasking-CNN achieved a maximum of 95% testing accuracy of PAR, a minimum of 0.59 METs mean square error (MSE), and 11% mean absolute percentage error (MAPE) in EE estimation. Conversely, on AG data, the Multitasking-CNN model achieved a maximum of 82% testing accuracy in PAR, a minimum of 0.73 METs MSE, and 13% MAPE in EE estimation. These results suggest the feasibility of using an eyeglass-mounted sensor for both PAR and EE estimation. Full article