Wrist-worn Sensor Research Articles

Free-living core body temperature monitoring using a wrist-worn sensor after COVID-19 booster vaccination: a pilot study

Core body temperature (CBT) is a key vital sign and fever is an important indicator of disease. In the past decade, there has been growing interest for vital sign monitoring technology that may be embedded in wearable devices, and the COVID-19 pandemic has highlighted the need for remote patient monitoring systems. While wrist-worn sensors allow continuous assessment of heart rate and oxygen saturation, reliable measurement of CBT at the wrist remains challenging. In this study, CBT was measured continuously in a free-living setting using a novel technology worn at the wrist and compared to reference core body temperature measurements, i.e., CBT values acquired with an ingestible temperature-sensing pill. Fifty individuals who received the COVID-19 booster vaccination were included. The datasets of 33 individuals were used to develop the CBT prediction algorithm, and the algorithm was then validated on the datasets of 17 participants. Mean observation time was 26.4 h and CBT > 38.0 °C occurred in 66% of the participants. CBT predicted by the wrist-worn sensor showed good correlation to the reference CBT (r = 0.72). Bland–Altman statistics showed an average bias of 0.11 °C of CBT predicted by the wrist-worn device compared to reference CBT, and limits of agreement were − 0.67 to + 0.93 °C, which is comparable to the bias and limits of agreement of commonly used tympanic membrane thermometers. The small size of the components needed for this technology would allow its integration into a variety of wearable monitoring systems assessing other vital signs and at the same time allowing maximal freedom of movement to the user.

CARWatch – A smartphone application for improving the accuracy of cortisol awakening response sampling

BackgroundMany studies investigating the cortisol awakening response (CAR) suffer from low adherence to the study protocol as well as from the lack of precise and objective methods for assessing the awakening and saliva sampling times which leads to measurement bias on CAR quantification. MethodsTo address this issue, we have developed “CARWatch”, a smartphone application that aims to enable low-cost and objective assessment of saliva sampling times as well as to concurrently increase protocol adherence. As proof-of-concept study, we assessed the CAR of N = 117 healthy participants (24.2 ± 8.7 years, 79.5% female) on two consecutive days. During the study, we recorded awakening times (AW) using self-reports, the CARWatch application, and a wrist-worn sensor, and saliva sampling times (ST) using self-reports and the CARWatch application. Using combinations of different AW and ST modalities, we derived different reporting strategies and compared the reported time information to a Naive sampling strategy assuming an ideal sampling schedule. Additionally, we compared the AUCI, computed using information from different reporting strategies, against each other to demonstrate the effect of inaccurate sampling on the CAR. ResultsThe use of CARWatch led to a more consistent sampling behavior and reduced sampling delay compared to self-reported saliva sampling times. Additionally, we observed that inaccurate saliva sampling times, as resulting from self-reports, were associated with an underestimation of CAR measures. Our findings also revealed potential error sources for inaccuracies in self-reported sampling times and showed that CARWatch can help in better identifying, and possibly excluding, sampling outliers that would remain undiscovered by self-reported sampling. ConclusionThe results from our proof-of-concept study demonstrated that CARWatch can be used to objectively record saliva sampling times. Further, it suggests its potential of increasing protocol adherence and sampling accuracy in CAR studies and might help to reduce inconsistencies in CAR literature resulting from inaccurate saliva sampling. For that reason, we published CARWatch and all necessary tools under an open-source license, making it freely accessible to every researcher.

The Accuracy of Wrist-Worn Photoplethysmogram-Measured Heart and Respiratory Rates in Abdominal Surgery Patients: Observational Prospective Clinical Validation Study.

Postoperative deterioration is often preceded by abnormal vital parameters. Therefore, vital parameters of postoperative patients are routinely measured by nursing staff. Wrist-worn sensors could potentially provide an alternative tool for the measurement of vital parameters in low-acuity settings. These devices would allow more frequent or even continuous measurements of vital parameters without relying on time-consuming manual measurements, provided their accuracy in this clinical population is established. This study aimed to assess the accuracy of heart rate (HR) and respiratory rate (RR) measures obtained via a wearable photoplethysmography (PPG) wristband in a cohort of postoperative patients. The accuracy of the wrist-worn PPG sensor was assessed in 62 post-abdominal surgery patients (mean age 55, SD 15 years; median BMI 34, IQR 25-40 kg/m2). The wearable obtained HR and RR measurements were compared to those of the reference monitor in the postanesthesia or intensive care unit. Bland-Altman and Clarke error grid analyses were performed to determine agreement and clinical accuracy. Data were collected for a median of 1.2 hours per patient. With a coverage of 94% for HR and 34% for RR, the device was able to provide accurate measurements for the large majority of the measurements as 98% and 93% of the measurements were within 5 bpm or 3 rpm of the reference signal. Additionally, 100% of the HR and 98% of the RR measurements were clinically acceptable on Clarke error grid analysis. The wrist-worn PPG device is able to provide measurements of HR and RR that can be seen as sufficiently accurate for clinical applications. Considering the coverage, the device was able to continuously monitor HR and report RR when measurements of sufficient quality were obtained. ClinicalTrials.gov NCT03923127; https://www.clinicaltrials.gov/ct2/show/NCT03923127.

Designing compact features for remote stroke rehabilitation monitoring using wearable accelerometers

Stroke is known as a major global health problem, and for stroke survivors it is key to monitor the recovery levels. However, traditional stroke rehabilitation assessment methods (such as the popular clinical assessment) can be subjective and expensive, and it is also less convenient for patients to visit clinics in a high frequency. To address this issue, in this work based on wearable sensing and machine learning techniques, we develop an automated system that can predict the assessment score in an objective manner. With wrist-worn sensors, accelerometer data is collected from 59 stroke survivors in free-living environments for a duration of 8 weeks, and we map the week-wise accelerometer data (3 days per week) to the assessment score by developing signal processing and predictive model pipeline. To achieve this, we propose two types of new features, which can encode the rehabilitation information from both paralysed and non-paralysed sides while suppressing the high-level noises such as irrelevant daily activities. Based on the proposed features, we further develop the longitudinal mixed-effects model with Gaussian process prior (LMGP), which can model the random effects caused by different subjects and time slots (during the 8 weeks). Comprehensive experiments are conducted to evaluate our system on both acute and chronic patients, and the promising results suggest its effectiveness.

Predicting Emotion with Biosignals: A Comparison of Classification and Regression Models for Estimating Valence and Arousal Level Using Wearable Sensors.

This study aims to predict emotions using biosignals collected via wrist-worn sensor and evaluate the performance of different prediction models. Two dimensions of emotions were considered: valence and arousal. The data collected by the sensor were used in conjunction with target values obtained from questionnaires. A variety of classification and regression models were compared, including Long Short-Term Memory (LSTM) models. Additionally, the effects of different normalization methods and the impact of using different sensors were studied, and the way in which the results differed between the study subjects was analyzed. The results revealed that regression models generally performed better than classification models, with LSTM regression models achieving the best results. The normalization method called baseline reduction was found to be the most effective, and when used with an LSTM-based regression model it achieved high accuracy in detecting valence (mean square error = 0.43 and R2-score = 0.71) and arousal (mean square error = 0.59 and R2-score = 0.81). Moreover, it was found that even if all biosignals were not used in the training phase, reliable models could be obtained; in fact, for certain study subjects the best results were obtained using only a few of the sensors.

Stress Detection Using Frequency Spectrum Analysis of Wrist-Measured Electrodermal Activity

The article deals with the detection of stress using the electrodermal activity (EDA) signal measured at the wrist. We present an approach for feature extraction from EDA. The approach uses frequency spectrum analysis in multiple frequency bands. We evaluate the proposed approach using the 4 Hz EDA signal measured at the wrist in the publicly available Wearable Stress and Affect Detection (WESAD) dataset. Seven existing approaches to stress detection using EDA signals measured by wrist-worn sensors are analysed and the reported results are compared with ours. The proposed approach represents an improvement in accuracy over the other techniques studied. Moreover, we focus on time to detection (TTD) and show that our approach is able to outperform competing techniques, with fewer data points. The proposed feature extraction is computationally inexpensive, thus the presented approach is suitable for use in real-world wearable applications where both short response times and high detection performance are important. We report both binary (stress vs. no stress) as well as three-class (baseline/stress/amusement) results.

Dual-Task Upper Extremity Motor Performance Measured by Video Processing as Cognitive-Motor Markers for Older Adults

Introduction: The use of dual-task model such as dual-task gait has been extensively studied to assess cognitive-motor performance among older adults. However, space restriction and safety factor limit its applications in remote assessment. To address the gap, we propose a video processing-based approach to remotely quantify cognitive-motor performance using a 20-s repetitive elbow flexion-extension test with dual-task condition, called video-based motoric-cognitive meter (MCM). Methods: Eighteen older participants (age: 78.6 ± 6.5 years) who were clinically diagnosed as having either mild cognitive impairment or dementia were included in this study. Participants were asked to perform 20-s repetitive elbow flexion-extension exercise with a memory exercise by counting backward from a two-digit number. During the test, all movements of the forearm were recorded by a video camera. As a comparator, a validated wrist-worn sensor was used, which allowed quantifying upper extremity kinematics. Results: The results showed a good agreement (r ≥ 0.530 and ICC2,1 ≥ 0.681) between the derived dual-task upper extremity motor performance from the proposed video-based MCM and a clinically validated sensor-based MCM. We also observed moderate correlations (r ≥ 0.496) between some measures of video-based MCM (flexion time, extension time, and flexion-extension time) and clinical cognitive scale (Mini-Mental State Examination [MMSE]). Additionally, some measures of dual-task upper extremity motor performance (speed, flexion time, extension time, and flexion-extension time) were associated with dual-task gait speed (r ≥ 0.557), which has been found to be correlated with cognitive impairment. Lastly, the selected dual-task motor performance metric (flexion time) was sensitive to predict MMSE scores in linear regression analyses with statistical significance (adjusted R2 = 0.306, p = 0.025). Conclusion: This study proposes a video processing-based approach to analyze dual-task upper extremity motor performance from a simple and convenient upper extremity function test. The results indicate concurrent validity of the proposed video-based MCM compared with the sensor-based MCM, and associations between dual-task upper extremity motor performance and clinically validated cognitive markers (MMSE scores and dual-task gait). Future studies are warranted to explore sensitivity of this solution to promote remote assessment of cognitive-motor performance among older adults in telehealth applications.

Hand Gesture Recognition From Wrist-Worn Camera for Human–Machine Interaction

In this work, we study the ability to use hand gestures for human-machine interaction from wrist-worn sensors. Towards this goal, we design a wrist-worn prototype to capture RGB video stream of hand gestures. Then we built a new wrist-worn gesture dataset (named WiGes) with various subjects in interaction with home appliances in different environments. To the best of our knowledge, this is the first benchmark released for studying hand gestures from a wrist-worn camera. We then evaluate various CNN models for vision-based recognition. Furthermore, we deeply analyze the models that produce the best trade-off between accuracy, memory requirement, and computational cost. We point out that among studied architectures, MoviNet produces the highest accuracy. Then, we introduce a new MoviNet-based two-stream architecture that takes both RGB and optical flow into account. Our proposed architecture increases the Top-1 accuracy by 1.36% and 3.67% according to two evaluation protocols. Our dataset, baselines, and proposed model analysis give instructive recommendations for human-machine interaction using hand-held devices.

Deep Neural Network-based Video Processing to Obtain Upper-Extremity Motor Performance Toward Assessment of Cognitive and Motor Function.

Dementia is an increasing global health challenge. Motoric Cognitive Risk Syndrome (MCR) is a predementia stage that can be used to predict future occurrence of dementia. Traditionally, gait speed and subjective memory complaints are used to identify old adults with MCR. Our previous studies indicated that dual-task upper-extremity motor performance (DTUEMP) quantified by a single wrist-worn sensor was correlated with both motor and cognitive function. Therefore, the DTUEMP had a potential to be used in the diagnosis of MCR. Instead of using inertial sensors to capture kinematic data of upper-extremity movements, here we proposed a deep neural network-based video processing model to obtain DTUEMP metrics from a 20-second repetitive elbow flexion-extension test under dual-task condition. In details, we used a deep residual neural network to obtain joint coordinate set of the elbow and wrist in each frame, and then used optical flow method to correct the joint coordinates generated by the neural network. The coordinate sets of all frames in a video recording are used to generate angle sequence which represents rotation angle of the line between the wrist and elbow. Then, the DTUEMP metrics (the mean and SD of flexion and extension phase) are derived from angle sequence. Multi-task learning (MTL) is used to assess cognitive and motor function represented by MMSE and TUG scores based on DTUEMP metrics, with single-task learning (STL) linear model as a benchmark. The results showed a good agreement (r ≥ 0.80 and ICC ≥ 0.58) between the derived DTUEMP metrics from our proposed model and the ones from clinically validated sensor processing model. We also found that there were correlations with statistical significance (p < 0.05) between some of video-derived DTUEMP metrics (i.e. the mean of flexion time and extension time) and clinical cognitive scale (Mini-Mental State Examination, MMSE). Additionally, some of video-derived DTUEMP metrics (i.e. the mean and standard deviation of flexion time and extension time) was also associated with the scores of timed-up and go (TUG) which is a gold standard to measure functional mobility. Mean absolute percentage error (MAPE) of MTL surpassed that of STL (For MMSE, MTL: 18.63%, STL: 23.18%. For TUG, MTL: 17.88%, STL: 22.53%). The experiments with different light conditions and shot angles verified the robustness of our proposed video processing model to extract DTUEMP metrics in potentially various home environments (r ≥ 0.58 and ICC ≥ 0.71). This study shows possibility of replacing sensor processing model with video processing model for analyzing the DTUEMP and a promising future to adjuvant diagnosis of MCR via a mobile platform.

Classifying tasks performed by electrical line workers using a wrist-worn sensor: A data analytic approach.

Electrical line workers (ELWs) experience harsh environments, characterized by long shifts, remote operations, and potentially risky tasks. Wearables present an opportunity for unobtrusive monitoring of productivity and safety. A prerequisite to monitoring is the automated identification of the tasks being performed. Human activity recognition has been widely used for classification for activities of daily living. However, the literature is limited for electrical line maintenance/repair tasks due to task variety and complexity. We investigated how features can be engineered from a single wrist-worn accelerometer for the purpose of classifying ELW tasks. Specifically, three classifiers were investigated across three feature sets (time, frequency, and time-frequency) and two window lengths (4 and 10 seconds) to identify ten common ELW tasks. Based on data from 37 participants in a lab environment, two application scenarios were evaluated: (a) intra-subject, where individualized models were trained and deployed for each worker; and (b) inter-subject, where data was pooled to train a general model that can be deployed for new workers. Accuracies ≥ 93% were achieved for both scenarios, and increased to ≥96% with 10-second windows. Overall and class-specific feature importance were computed, and the impact of those features on the obtained predictions were explained. This work will contribute to the future risk mitigation of ELWs using wearables.

A Comparison of Wrist- Versus Hip-Worn ActiGraph Sensors for Assessing Physical Activity in Adults: A Systematic Review

Introduction: Wrist-worn accelerometer has gained popularity recently in commercial and research use for physical activity tracking. Yet, no consensus exists for standardized wrist-worn data processing, and physical activity data derived from wrist-worn accelerometer cannot be directly compared with data derived from the historically used hip-worn accelerometer. In this work, through a systematic review, we aim to identify and analyze discrepancies between wrist-worn versus hip-worn ActiGraph accelerometers in measuring adult physical activity. Methods: A systematic review was conducted on studies involving free-living data comparison between hip- and wrist-worn ActiGraph accelerometers among adult users. We assessed the population, study protocols, data processing criteria (axis, epoch, wear-time correction, etc.), and outcome measures (step count, sedentary activity time, moderate-to-vigorous physical activity, etc.). Step count and activity count discrepancy were analyzed using meta-analysis, while meta-analysis was not attempted for others due to heterogeneous data processing criteria among the studies. Results: We screened 235 studies with 19 studies qualifying for inclusion in the systematic review. Through meta-analysis, the wrist-worn sensor recorded, on average, 3,537 steps/day more than the hip-worn sensor. Regarding sedentary activity time and moderate-to-vigorous physical activity estimation, the wrist sensor consistently overestimates moderate-to-vigorous physical activity time while underestimating sedentary activity time, with discrepancies ranging from a dozen minutes to several hours. Discussions: Our findings quantified the substantial discrepancies between wrist and hip sensors. It calls attention to the need for a cautious approach to interpreting data from different wear locations. These results may also serve as a reference for data comparisons among studies using different sensor locations.

Effectiveness of smart wrist wearables for distinguishing physical and cognitive demands

Wrist-worn wearables, with sensors to measure physiological responses such as heart rate variability (HRV) and electrodermal activity (EDA), have been increasing and have the potential to be used for continuous monitoring. These devices have been used to detect responses in workers’ physical and cognitive demands; however, the accuracy of wrist wearables for distinguishing these demands is unknown, especially since many every day and work activities frequently require motion. The objective of this study was to evaluate the effectiveness of a wrist-worn wearable in measuring physiological changes during different demand conditions. Participants (n = 20 college students) completed a multi-factor laboratory study that considered task (cognitive/physical), difficulty (easy/hard), and motion (motion/no motion). N-back tasks and stationary bike tasks were used to represent cognitive and physical demands, respectively. Metrics of HRV and EDA were measured using reference-standard devices and a validated wrist-wearable. Significant differences between task, motion, and difficulty were observed from HRV measurements from the reference-standard and wrist-worn devices. Wrist wearables are sensitive to detecting workplace demands and may be used as an alternative to reference-standard sensors for continuous health and activity monitoring for worker health and wellness. Findings in this study can provide guidelines on task and conditions that affect the use and interpretation of wrist-worn devices for measuring cognitive and physical demands in healthcare systems. HIGHLIGHTS Applications for noninvasive, wrist-worn sensors can be used for continuous health and exercise monitoring HRV and EDA metrics obtained from wrist-worn device are sensitivity in detecting changes in task, difficulty, and motion HRV metric from wrist-worn device had agreement with reference-standard device Wrist-wearables has potential for ubiquitous health monitoring of individuals

Population analysis of mortality risk: Predictive models from passive monitors using motion sensors for 100,000 UK Biobank participants.

Many studies have utilized physical activity for predicting mortality risk, using measures such as participant walk tests and self-reported walking pace. The rise of passive monitors to measure participant activity without requiring specific actions opens the possibility for population level analysis. We have developed novel technology for this predictive health monitoring, using limited sensor inputs. In previous studies, we validated these models in clinical experiments with carried smartphones, using only their embedded accelerometers as motion sensors. Using smartphones as passive monitors for population measurement is critically important for health equity, since they are already ubiquitous in high-income countries and increasingly common in low-income countries. Our current study simulates smartphone data by extracting walking window inputs from wrist worn sensors. To analyze a population at national scale, we studied 100,000 participants in the UK Biobank who wore activity monitors with motion sensors for 1 week. This national cohort is demographically representative of the UK population, and this dataset represents the largest such available sensor record. We characterized participant motion during normal activities, including daily living equivalent of timed walk tests. We then compute walking intensity from sensor data, as input to survival analysis. Simulating passive smartphone monitoring, we validated predictive models using only sensors and demographics. This resulted in C-index of 0.76 for 1-year risk decreasing to 0.73 for 5-year. A minimum set of sensor features achieves C-index of 0.72 for 5-year risk, which is similar accuracy to other studies using methods not achievable with smartphone sensors. The smallest minimum model uses average acceleration, which has predictive value independent of demographics of age and sex, similar to physical measures of gait speed. Our results show passive measures with motion sensors can achieve similar accuracy to active measures of gait speed and walk pace, which utilize physical walk tests and self-reported questionnaires.

Classification of functional and non-functional arm use by inertial measurement units in individuals with upper limb impairment after stroke.

Background: Arm use metrics derived from wrist-mounted movement sensors are widely used to quantify the upper limb performance in real-life conditions of individuals with stroke throughout motor recovery. The calculation of real-world use metrics, such as arm use duration and laterality preferences, relies on accurately identifying functional movements. Hence, classifying upper limb activity into functional and non-functional classes is paramount. Acceleration thresholds are conventionally used to distinguish these classes. However, these methods are challenged by the high inter and intra-individual variability of movement patterns. In this study, we developed and validated a machine learning classifier for this task and compared it to methods using conventional and optimal thresholds. Methods: Individuals after stroke were video-recorded in their home environment performing semi-naturalistic daily tasks while wearing wrist-mounted inertial measurement units. Data were labeled frame-by-frame following the Taxonomy of Functional Upper Limb Motion definitions, excluding whole-body movements, and sequenced into 1-s epochs. Actigraph counts were computed, and an optimal threshold for functional movement was determined by receiver operating characteristic curve analyses on group and individual levels. A logistic regression classifier was trained on the same labels using time and frequency domain features. Performance measures were compared between all classification methods. Results: Video data (6.5 h) of 14 individuals with mild-to-severe upper limb impairment were labeled. Optimal activity count thresholds were ≥20.1 for the affected side and ≥38.6 for the unaffected side and showed high predictive power with an area under the curve (95% CI) of 0.88 (0.87,0.89) and 0.86 (0.85, 0.87), respectively. A classification accuracy of around 80% was equivalent to the optimal threshold and machine learning methods and outperformed the conventional threshold by ∼10%. Optimal thresholds and machine learning methods showed superior specificity (75–82%) to conventional thresholds (58–66%) across unilateral and bilateral activities. Conclusion: This work compares the validity of methods classifying stroke survivors’ real-life arm activities measured by wrist-worn sensors excluding whole-body movements. The determined optimal thresholds and machine learning classifiers achieved an equivalent accuracy and higher specificity than conventional thresholds. Our open-sourced classifier or optimal thresholds should be used to specify the intensity and duration of arm use.

Gait Detection from a Wrist-Worn Sensor Using Machine Learning Methods: A Daily Living Study in Older Adults and People with Parkinson's Disease.

Remote assessment of the gait of older adults (OAs) during daily living using wrist-worn sensors has the potential to augment clinical care and mobility research. However, hand movements can degrade gait detection from wrist-sensor recordings. To address this challenge, we developed an anomaly detection algorithm and compared its performance to four previously published gait detection algorithms. Multiday accelerometer recordings from a wrist-worn and lower-back sensor (i.e., the “gold-standard” reference) were obtained in 30 OAs, 60% with Parkinson’s disease (PD). The area under the receiver operator curve (AUC) and the area under the precision–recall curve (AUPRC) were used to evaluate the performance of the algorithms. The anomaly detection algorithm obtained AUCs of 0.80 and 0.74 for OAs and PD, respectively, but AUPRCs of 0.23 and 0.31 for OAs and PD, respectively. The best performing detection algorithm, a deep convolutional neural network (DCNN), exhibited high AUCs (i.e., 0.94 for OAs and 0.89 for PD) but lower AUPRCs (i.e., 0.66 for OAs and 0.60 for PD), indicating trade-offs between precision and recall. When choosing a classification threshold of 0.9 (i.e., opting for high precision) for the DCNN algorithm, strong correlations (r > 0.8) were observed between daily living walking time estimates based on the lower-back (reference) sensor and the wrist sensor. Further, gait quality measures were significantly different in OAs and PD compared to healthy adults. These results demonstrate that daily living gait can be quantified using a wrist-worn sensor.

The Application of Digital Frailty Screening to Triage Nonhealing and Complex Wounds.

We investigated the association between the complexity of diabetic foot ulcers (DFUs) and frailty. Individuals (n = 38) with Grade 2 Wagner DFU were classified into 3 groups based on the Society for Vascular Surgery risk-stratification for major limb amputation as Stage 1 at very low risk (n = 19), Stage 2 at low risk (n = 9), and Stage 3 to 4 at moderate-to-high risk (n = 10) of major limb amputation. Frailty status was objectively assessed using a validated digital frailty meter (FM). The FM works by quantifying weakness, slowness, rigidity, and exhaustion over a 20-second repetitive elbow flexion-extension exercise using a wrist-worn sensor. FM generates a frailty index (FI) ranging from 0 to 1; higher values indicate progressively greater severity of frailty. Skin perfusion pressure (SPP), albumin, and tissue oxygenation level (SatO2) were also measured. One-way analysis of variance (ANOVA) was used to identify group effect for wound complexity. Pearson's correlation coefficient was used to assess the associations with frailty and clinical endpoints. Frailty index was higher in Stage 3 and 4 as compared to Stage 1 (d = 1.4, P < .01) and Stage 2 (d = 1.2, P < .01). Among assessed frailty phenotypes, exhaustion was correlated with SPP (r = -0.63, P < .01) and albumin (r = -0.5, P < .01). Digital biomarkers of frailty may predict complexity of DFU and thus triage individuals who can be treated more simply in their primary clinic versus higher risk patients who require prompt referral to multidisciplinary, more complex care.

Using Wearable Inertial Sensors to Estimate Clinical Scores of Upper Limb Movement Quality in Stroke.

Neurorehabilitation is progressively shifting from purely in-clinic treatment to therapy that is provided in both clinical and home-based settings. This transition generates a pressing need for assessments that can be performed across the entire continuum of care, a need that might be accommodated by application of wearable sensors. A first step toward ubiquitous assessments is to augment validated and well-understood standard clinical tests. This route has been pursued for the assessment of motor functioning, which in clinical research and practice is observation-based and requires specially trained personnel. In our study, 21 patients performed movement tasks of the Action Research Arm Test (ARAT), one of the most widely used clinical tests of upper limb motor functioning, while trained evaluators scored each task on pre-defined criteria. We collected data with just two wrist-worn inertial sensors to guarantee applicability across the continuum of care and used machine learning algorithms to estimate the ARAT task scores from sensor-derived features. Tasks scores were classified with approximately 80% accuracy. Linear regression between summed clinical task scores (across all tasks per patient) and estimates of sum task scores yielded a good fit (R 2 = 0.93; range reported in previous studies: 0.61–0.97). Estimates of the sum scores showed a mean absolute error of 2.9 points, 5.1% of the total score, which is smaller than the minimally detectable change and minimally clinically important difference of the ARAT when rated by a trained evaluator. We conclude that it is feasible to obtain accurate estimates of ARAT scores with just two wrist worn sensors. The approach enables administration of the ARAT in an objective, minimally supervised or remote fashion and provides the basis for a widespread use of wearable sensors in neurorehabilitation.

Long–Short Ensemble Network for Bipolar Manic-Euthymic State Recognition Based on Wrist-Worn Sensors

Manic episodes of bipolar disorder can lead to uncritical behavior and delusional psychosis, often with destructive consequences for those affected and their surroundings. Early detection and intervention of a manic episode are crucial to prevent escalation, hospital admission, and premature death. However, people with bipolar disorder may not recognize that they are experiencing a manic episode and symptoms, such as euphoria and increased productivity can also deter affected individuals from seeking help. This work proposes to perform user-independent, automatic mood-state detection based on actigraphy and electrodermal activity acquired from a wrist-worn device during mania and after recovery (euthymia). This article proposes a new deep learning-based ensemble method leveraging long (20 h) and short (5 min) time intervals to discriminate between the mood states. When tested on 47 bipolar patients, the proposed classification scheme achieves an average accuracy of 91.59% in euthymic/manic mood-state recognition.

Night-time cardiac metrics from a wearable sensor predict intensity of next-day chronic pain

Chronic pain is devastating and its measurement is elusive, making intervention difficult for sufferers and practitioners alike. The present study explores the possibility of tracking fluctuations in pain over time with wearable sensors of heart-based metrics. We measured mean heart rate and heart rate variability with a wrist-worn sensor in persons with and without chronic pain for one month. Mixed model regressions were used to test the associations, revealing that heart rate measured at night was predictive of pain intensity on the next day in participants with chronic pain (p < .05), but not in healthy controls (p > .05). The results suggest that cardiac biometrics can predict pain intensity in primary chronic pain conditions.

Influence of Study Composition on the Efficacy of Sleep Detection Using Actigraphy.

Wearable actigraphy sensors have been useful tools for unobtrusive monitoring of sleep. The influence of the composition and characteristics of study groups such as normal sleep versus sleep disorders affecting the efficacy of sleep assessment using actigraphy has not been fully examined. In this study, we present multi-variate sleep models using actigraphy features obtained from wrist-worn sensors and evaluate the efficacy of sleep detection compared to the overnight polysomnography from two unique datasets: overnight actigraphy recordings in a control population of young healthy individuals (n=31) and 24-hour actigraphy recordings in a more heterogeneous population (n=27) comprised of normal and abnormal sleepers. We evaluate the performance of actigraphy derived logistic regression (LR) and random forest (RF) sleep models for both intra-dataset and inter-dataset training and cross-validation. Both the LR and RF sleep models for the healthy sleep dataset show an area under the receiver operating characteristic (AUROC) of 0.85±0.02 in the control sleep dataset among 50 random splits of training and testing evaluations. We find the AUROC performance from the heterogeneous sleep dataset involving sleep disorders to be relatively lower as 0.74±0.05 and 0.80±0.03 for LR and RF sleep models, respectively. Optimal sleep models trained using heterogeneous datasets perform very well when tested with the normal sleep dataset producing accuracy of ∼92%. Our study supports that using a more diverse training set benefits the sleep classifier model to be more generalizable for both healthy and abnormal sleepers.