Sensor-derived Measures Research Articles

Sensor-Derived Measures of Motor and Cognitive Functions in People With Multiple Sclerosis Using Unsupervised Smartphone-Based Assessments: Proof-of-Concept Study.

Smartphones and wearables are revolutionizing the assessment of cognitive and motor function in neurological disorders, allowing for objective, frequent, and remote data collection. However, these assessments typically provide a plethora of sensor-derived measures (SDMs), and selecting the most suitable measure for a given context of use is a challenging, often overlooked problem. This analysis aims to develop and apply an SDM selection framework, including automated data quality checks and the evaluation of statistical properties, to identify robust SDMs that describe the cognitive and motor function of people with multiple sclerosis (MS). The proposed framework was applied to data from a cross-sectional study involving 85 people with MS and 68 healthy participants who underwent in-clinic supervised and remote unsupervised smartphone-based assessments. The assessment provided high-quality recordings from cognitive, manual dexterity, and mobility tests, from which 47 SDMs, based on established literature, were extracted using previously developed and publicly available algorithms. These SDMs were first separately and then jointly screened for bias and normality by 2 expert assessors. Selected SDMs were then analyzed to establish their reliability, using an intraclass correlation coefficient and minimal detectable change at 95% CI. The convergence of selected SDMs with in-clinic MS functional measures and patient-reported outcomes was also evaluated. A total of 16 (34%) of the 47 SDMs passed the selection framework. All selected SDMs demonstrated moderate-to-good reliability in remote settings (intraclass correlation coefficient 0.5-0.85; minimal detectable change at 95% CI 19%-35%). Selected SDMs extracted from the smartphone-based cognitive test demonstrated good-to-excellent correlation (Spearman correlation coefficient, |ρ|>0.75) with the in-clinic Symbol Digit Modalities Test and fair correlation with Expanded Disability Status Scale (EDSS) scores (0.25≤|ρ|<0.5). SDMs extracted from the manual dexterity tests showed either fair correlation (0.25≤|ρ|<0.5) or were not correlated (|ρ|<0.25) with the in-clinic 9-hole peg test and EDSS scores. Most selected SDMs from mobility tests showed fair correlation with the in-clinic timed 25-foot walk test and fair to moderate-to-good correlation (0.5<|ρ|≤0.75) with EDSS scores. SDM correlations with relevant patient-reported outcomes varied by functional domain, ranging from not correlated (cognitive test SDMs) to good-to-excellent correlation (|ρ|>0.75) for mobility test SDMs. Overall, correlations were similar when smartphone-based tests were performed in a clinic or remotely. Reported results highlight that smartphone-based assessments are suitable tools to remotely obtain high-quality SDMs of cognitive and motor function in people with MS. The presented SDM selection framework promises to increase the interpretability and standardization of smartphone-based SDMs in people with MS, paving the way for their future use in interventional trials.

393 The role of on-animal sensors in understanding feed intake, behavior, and performance of grazing livestock

Abstract Intake by grazing animals is difficult to reliably measure in the field, particularly in more diverse grazing systems where pastures vary greatly across time and space in resource availability, which in turn leads to greater variation in animal time budgets and intake patterns. Advances in remote livestock monitoring (e.g., on-animal sensors, walk -over-weighing), and advanced analytics such as machine learning algorithms can contribute to the development of robust, adaptable tools for better understanding of animal performance and behavior in grazing systems. Many existing tools for predicting livestock production require estimates of feed intake, and while estimates based on forage sward characteristics have been developed and used for temperate, relatively homogenous pastures, they are less well defined for more diverse rangelands. These diverse pastures are more difficult to characterize due to their greater variation in quantity and quality; consequently, animal selectivity is greater in more variable pastures. However, such feedback loops between pasture diversity and animal behavior may not yet be adequately represented in biophysical models. On-animal sensors such as accelerometers and GPS devices can be used to develop new ways of assessing relative intake by providing accurate estimates of animal location and behavior profiles, such as the use of machine learning algorithms to detect how much time is spent grazing, walking, ruminating, or resting. Measurements of animal behavior could then be combined with other animal-based methods such as walk-over-weighing and fecal NIR to improve estimates of intake and production for a wide range of extensive grazing environments. Sensor-derived measurements of animal movement could also be used to improve estimates of the energetic costs of grazing, thereby improving estimates of energy available for growth. As an example, data on recent activity and paddock use from on-animal sensors could be entered into a model to estimate current feeding requirements, then combined with weather and pasture quality forecasts. The ensuing baseline could then be used to explore the potential variability of these projections and generate a range for possible expected performance over the next month or season. This approach could be repeated over time, and animal performance and behavior measures used to update model estimates and improve forward projections. These methods could also be used in conjunction with estimates of animal energy requirements to provide real-time prediction of relative feed intake, which would provide a step-change in modelling livestock production in extensive grazing systems. For these approaches to be successful, additional calibration data are needed across a wide variety of environments and species, and the tools must be cost-effective to implement. In summary, on-animal measurements provide an adaptable, data-driven approach that could be integrated with existing tools to improve our understanding of feed intake, behavior, and performance of grazing animals.

Smartphone-Based Assessment of Mobility and Manual Dexterity in Adult People with Spinal Muscular Atrophy.

More responsive, reliable, and clinically valid endpoints of disability are essential to reduce size, duration, and burden of clinical trials in adult persons with spinal muscular atrophy (aPwSMA). The aim is to investigate the feasibility of smartphone-based assessments in aPwSMA and provide evidence on the reliability and construct validity of sensor-derived measures (SDMs) of mobility and manual dexterity collected remotely in aPwSMA. Data were collected from 59 aPwSMA (23 walkers, 20 sitters and 16 non-sitters) and 30 age-matched healthy controls (HC). SDMs were extracted from five smartphone-based tests capturing mobility and manual dexterity, which were administered in-clinic and remotely in daily life for four weeks. Reliability (Intraclass Correlation Coefficients, ICC) and construct validity (ability to discriminate between HC and aPwSMA and correlations with Revised Upper Limb Module, RULM and Hammersmith Functional Scale - Expanded HFMSE) were quantified for all SDMs. The smartphone-based assessments proved feasible, with 92.1% average adherence in aPwSMA. The SDMs allowed to reliably assess both mobility and dexterity (ICC > 0.75 for 14/22 SDMs). Twenty-one out of 22 SDMs significantly discriminated between HC and aPwSMA. The highest correlations with the RULM were observed for SDMs from the manual dexterity tests in both non-sitters (Typing, ρ= 0.78) and sitters (Pinching, ρ= 0.75). In walkers, the highest correlation was between mobility tests and HFMSE (5 U-Turns, ρ= 0.79). This exploratory study provides preliminary evidence for the usability of smartphone-based assessments of mobility and manual dexterity in aPwSMA when deployed remotely in participants' daily life. Reliability and construct validity of SDMs remotely collected in real-life was demonstrated, which is a pre-requisite for their use in longitudinal trials. Additionally, three novel smartphone-based performance outcome assessments were successfully established for aPwSMA. Upon further validation of responsiveness to interventions, this technology holds potential to increase the efficiency of clinical trials in aPwSMA.

Relationship Between Running Biomechanics and Core Temperature Across a Competitive Road Race.

Outdoor races introduce environmental stressors to runners, and core temperature changes may influence runners' movement patterns. This study assessed changes and determined relationships between sensor-derived running biomechanics and core temperature among runners across an 11.27-km road race. Core temperatures would increase significantly across the race, related to changes in spatiotemporal biomechanical measures. Cross-sectional cohort study. Level 3. Twenty runners (9 female, 11 male; age, 48 ± 12 years; height, 169.7 ± 9.1 cm; mass, 71.3 ± 13.4 kg) enrolled in the 2022 Falmouth Road Race were recruited. Participants used lightweight technologies (ingestible thermistors and wearable sensors) to monitor core temperature and running biomechanics throughout the race. Timestamps were used to align sensor-derived measures for 7 race segments. Observations were labeled as core temperatures generally within normal limits (<38°C) or at elevated core temperatures (≥38°C). Multivariate repeated measures analyses of variance were used to assess changes in sensor-derived measures across the race, with Bonferroni post hoc comparisons for significant findings. Pearson's r correlations were used to assess the relationship between running biomechanics and core temperature measures. Eighteen participants developed hyperthermic core temperatures (39.0°C ± 0.5°C); core temperatures increased significantly across the race (P < 0.01). Kinetic measures obtained from the accelerometers, including shock, impact, and braking g, all significantly increased across the race (P < 0.01); other sensor-derived biomechanical measures did not change significantly. Core temperatures were weakly associated with biomechanics (|r range|, 0.02-0.16). Core temperatures and kinetics increased significantly across a race, yet these outcomes were not strongly correlated. The observed kinetic changes may have been attributed to fatigue-related influences over the race. Clinicians may not expect changes in biomechanical movement patterns to signal thermal responses during outdoor running in a singular event.

DISPEL: A Python Framework for Developing Measures From Digital Health Technologies.

Goal: This paper introduces DISPEL, a Python framework to facilitate development of sensor-derived measures (SDMs) from data collected with digital health technologies in the context of therapeutic development for neurodegenerative diseases. Methods: Modularity, integrability and flexibility were achieved adopting an object-oriented architecture for data modelling and SDM extraction, which also allowed standardizing SDM generation, naming, storage, and documentation. Additionally, a functionality was designed to implement systematic flagging of missing data and unexpected user behaviors, both frequent in unsupervised monitoring. Results: DISPEL is available under MIT license. It already supports formats from different data providers and allows traceable end-to-end processing from raw data collected with wearables and smartphones to structured SDM datasets. Novel and literature-based signal processing approaches currently allow to extract SDMs from 16 structured tests (including six questionnaires), assessing overall disability and quality of life, and measuring performance outcomes of cognition, manual dexterity, and mobility. Conclusion: DISPEL supports SDM development for clinical trials by providing a production-grade Python framework and a large set of already implemented SDMs. While the framework has already been refined based on clinical trials' data, ad-hoc validation of the provided algorithms in their specific context of use is recommended to the users.

P72 Sensor-derived measurements of upper and lower extremity function in people with type II and III SMA

P72 Sensor-derived measurements of upper and lower extremity function in people with type II and III SMA

Unlocking the black box of geriatric physiotherapy : Quantification of physical activity and walking parameters during inpatient geriatric rehabilitation therapy sessions.

Physiotherapy and occupational therapy are currently described using the duration of treatment (days or weeks), the frequency of therapy sessions (on adaily or 3-5days per week basis) and considering the duration of asession (e.g., 30or 45 min). The content is often poorly defined and the intensity is rarely reported. Using digital technology some of these shortcomings can be overcome. The cumulative parameters of walking and activity sessions, the duration of walking, the time spent in an upright or lying/sitting position and the number of steps can now be analyzed. In this study, we examined the parameters during non-treatment periods and therapy time in patients recovering from fragility fractures. The study is asecondary data analysis of atrial that examined the improvement of physical activity (PA) and self-efficacy of fragility fracture patients. Changes in mobility parameters were measured using the ActivPal3 sensor during the 1st and 3rd weeks of rehabilitation and 104 patients were analyzed (mean age 82.5years). Parameters included the time during supervised treatment, the mean number of steps, cumulative time in an upright position and walking duration, the number of walking intervals of > 10 s and sit to stand transfers. Patients received 3-4 therapy sessions adding up to 90-120 min per day. More than 50% of the daily walking activities were achieved in these sessions until discharge. With this amount of therapeutic input most parameters meaningfully improved from baseline to the second measurement. The number of steps increased by 30%, the mean time in an upright position increased by 26% and the mean time spent walking increased by 49%. The sensor-derived measurements describe the amount of walking activity administered during the supervised therapy sessions. This could be used as astarting point for future trials to improve the outcomes or as astandard of process evaluation for clinical services.

Validation of a Unique Boxing Monitoring System.

Much development work and scientific research has been conducted in recent years in the field of detecting human activity and the measurement of biomechanical performance parameters using portable sensor technologies, so-called wearable systems. Despite the fact that boxers participating in one of the most vigorous and complex disciplines of all sports, it is one of the disciplines where no noteworthy, advanced performance analytic tools are used for training or for competition purposes worldwide. This research aimed to develop and validate a comprehensive punch performance sensor system for the measurement and analysis of biomechanical parameters in the sport of boxing. A comprehensive validation study on linear regression was conducted following the development of the sensor system, between the gold standard of a Kistler force plate and Vicon motion capture system, to compare sensor-derived measurements with the gold standard-derived measurements. The developed sensor system demonstrated high accuracies ranging from R2 = 0.97 to R2 = 0.99 for punch force, acceleration, velocity and punch-time data. The validation experiments conducted demonstrated the significant accuracy of the sensor-derived measurements for predicting boxing-specific biomechanical movement parameters while punching in field use. Thus, this paper presents a unique sensor system for comprehensive measurements of biomechanical parameters using the developed mobile measurement system in the field of combat sports

Development of digital measures for nighttime scratch and sleep using wrist-worn wearable devices

Patients with atopic dermatitis experience increased nocturnal pruritus which leads to scratching and sleep disturbances that significantly contribute to poor quality of life. Objective measurements of nighttime scratching and sleep quantity can help assess the efficacy of an intervention. Wearable sensors can provide novel, objective measures of nighttime scratching and sleep; however, many current approaches were not designed for passive, unsupervised monitoring during daily life. In this work, we present the development and analytical validation of a method that sequentially processes epochs of sample-level accelerometer data from a wrist-worn device to provide continuous digital measures of nighttime scratching and sleep quantity. This approach uses heuristic and machine learning algorithms in a hierarchical paradigm by first determining when the patient intends to sleep, then detecting sleep–wake states along with scratching episodes, and lastly deriving objective measures of both sleep and scratch. Leveraging reference data collected in a sleep laboratory (NCT ID: NCT03490877), results show that sensor-derived measures of total sleep opportunity (TSO; time when patient intends to sleep) and total sleep time (TST) correlate well with reference polysomnography data (TSO: r = 0.72, p < 0.001; TST: r = 0.76, p < 0.001; N = 32). Log transformed sensor derived measures of total scratching duration achieve strong agreement with reference annotated video recordings (r = 0.82, p < 0.001; N = 25). These results support the use of wearable sensors for objective, continuous measurement of nighttime scratching and sleep during daily life.

Augmenting Clinical Outcome Measures of Gait and Balance with a Single Inertial Sensor in Age-Ranged Healthy Adults.

Gait and balance impairments are linked with reduced mobility and increased risk of falling. Wearable sensing technologies, such as inertial measurement units (IMUs), may augment clinical assessments by providing continuous, high-resolution data. This study tested and validated the utility of a single IMU to quantify gait and balance features during routine clinical outcome tests, and evaluated changes in sensor-derived measurements with age, sex, height, and weight. Age-ranged, healthy individuals (N = 49, 20–70 years) wore a lower back IMU during the 10 m walk test (10MWT), Timed Up and Go (TUG), and Berg Balance Scale (BBS). Spatiotemporal gait parameters computed from the sensor data were validated against gold standard measures, demonstrating excellent agreement for stance time, step time, gait velocity, and step count (intraclass correlation (ICC) > 0.90). There was good agreement for swing time (ICC = 0.78) and moderate agreement for step length (ICC = 0.68). A total of 184 features were calculated from the acceleration and angular velocity signals across these tests, 36 of which had significant correlations with age. This approach was also demonstrated for an individual with stroke, providing higher resolution information about balance, gait, and mobility than the clinical test scores alone. Leveraging mobility data from wireless, wearable sensors can help clinicians and patients more objectively pinpoint impairments, track progression, and set personalized goals during and after rehabilitation.

Inertial Sensor Technology Can Capture Changes in Dynamic Balance Control during the Y Balance Test

Introduction: The Y Balance Test (YBT) is one of the most commonly utilised clinical dynamic balance assessments. Research has demonstrated the utility of the YBT in identifying balance deficits in individuals following lower limb injury. However, quantifying dynamic balance based on reach distances alone fails to provide potentially important information related to the quality of movement control and choice of movement strategy during the reaching action. The addition of an inertial sensor to capture more detailed motion data may allow for the inexpensive, accessible quantification of dynamic balance control during the YBT reach excursions. As such, the aim of this study was to compare baseline and fatigued dynamic balance control, using reach distances and 95EV (95% ellipsoid volume), and evaluate the ability of 95EV to capture alterations in dynamic balance control, which are not detected by YBT reach distances. Methods: As part of this descriptive laboratory study, 15 healthy participants completed repeated YBTs at 20, 10, and 0 min prior to and following a modified 60-s Wingate test that was used to introduce a short-term reduction in dynamic balance capability. Dynamic balance was assessed using the standard normalised reach distance method, while dynamic balance control during the reach attempts was simultaneously measured by means of the 95EV derived from an inertial sensor, worn at the level of the 4th lumbar vertebra. Results: Intraclass correlation coefficients for the inertial sensor-derived measures ranged from 0.76 to 0.92, demonstrating strong intrasession test-retest reliability. Statistically significant alterations (p < 0.05) in both reach distance and the inertial sensor-derived 95EV measure were observed immediately post-fatigue. However, reach distance deficits returned to baseline levels within 10 min, while 95EV remained significantly increased (p < 0.05) beyond 20 min for all 3 reach distances. Conclusion: These findings demonstrate the ability of an inertial sensor-derived measure to quantify alterations in dynamic balance control, which are not captured by traditional reach distances alone. This suggests that the addition of an inertial sensor to the YBT may provide clinicians and researchers with an accessible means to capture subtle alterations in motor function in the clinical setting.

Feasibility of large-scale deployment of multiple wearable sensors in Parkinson's disease.

Wearable devices can capture objective day-to-day data about Parkinson’s Disease (PD). This study aims to assess the feasibility of implementing wearable technology to collect data from multiple sensors during the daily lives of PD patients. The Parkinson@home study is an observational, two-cohort (North America, NAM; The Netherlands, NL) study. To recruit participants, different strategies were used between sites. Main enrolment criteria were self-reported diagnosis of PD, possession of a smartphone and age≥18 years. Participants used the Fox Wearable Companion app on a smartwatch and smartphone for a minimum of 6 weeks (NAM) or 13 weeks (NL). Sensor-derived measures estimated information about movement. Additionally, medication intake and symptoms were collected via self-reports in the app. A total of 953 participants were included (NL: 304, NAM: 649). Enrolment rate was 88% in the NL (n = 304) and 51% (n = 649) in NAM. Overall, 84% (n = 805) of participants contributed sensor data. Participants were compliant for 68% (16.3 hours/participant/day) of the study period in NL and for 62% (14.8 hours/participant/day) in NAM. Daily accelerometer data collection decreased 23% in the NL after 13 weeks, and 27% in NAM after 6 weeks. Data contribution was not affected by demographics, clinical characteristics or attitude towards technology, but was by the platform usability score in the NL (χ2 (2) = 32.014, p<0.001), and self-reported depression in NAM (χ2(2) = 6.397, p = .04). The Parkinson@home study shows that it is feasible to collect objective data using multiple wearable sensors in PD during daily life in a large cohort.

Objective Assessment of Fall Risk in Parkinson's Disease Using a Body-Fixed Sensor Worn for 3 Days

BackgroundPatients with Parkinson's disease (PD) suffer from a high fall risk. Previous approaches for evaluating fall risk are based on self-report or testing at a given time point and may, therefore, be insufficient to optimally capture fall risk. We tested, for the first time, whether metrics derived from 3 day continuous recordings are associated with fall risk in PD.Methods and Materials107 patients (Hoehn & Yahr Stage: 2.6±0.7) wore a small, body-fixed sensor (3D accelerometer) on lower back for 3 days. Walking quantity (e.g., steps per 3-days) and quality (e.g., frequency-derived measures of gait variability) were determined. Subjects were classified as fallers or non-fallers based on fall history. Subjects were also followed for one year to evaluate predictors of the transition from non-faller to faller.ResultsThe 3 day acceleration derived measures were significantly different in fallers and non-fallers and were significantly correlated with previously validated measures of fall risk. Walking quantity was similar in the two groups. In contrast, the fallers walked with higher step-to-step variability, e.g., anterior-posterior width of the dominant frequency was larger (p = 0.012) in the fallers (0.78±0.17 Hz) compared to the non-fallers (0.71±0.07 Hz). Among subjects who reported no falls in the year prior to testing, sensor-derived measures predicted the time to first fall (p = 0.0034), whereas many traditional measures did not. Cox regression analysis showed that anterior-posterior width was significantly (p = 0.0039) associated with time to fall during the follow-up period, even after adjusting for traditional measures.Conclusions/SignificanceThese findings indicate that a body-fixed sensor worn continuously can evaluate fall risk in PD. This sensor-based approach was able to identify transition from non-faller to faller, whereas many traditional metrics were not successful. This approach may facilitate earlier detection of fall risk and may in the future, help reduce high costs associated with falls.

Comparison of an inertial sensor system with a stationary force plate for evaluation of horses with bilateral forelimb lameness

To assess the analytic sensitivity of an inertial sensor system for detection of the more severely affected forelimb in horses with bilateral lameness. 18 adult horses with forelimb lameness. Horses were fitted with inertial sensors and evaluated for lameness with a stationary force plate as they were trotted in a straight line. Inertial sensor-derived measurements for vertical head movement asymmetry (HMA) and vector sum (VS) of maximum and minimum head height differences between right and left halves of the stride were used to predict differences in mean peak vertical force (PVF) as a percentage of body weight between the right and left forelimbs. Repeatability was compared by calculation of the intraclass correlation coefficient (ICC) for each variable. Correct classification percentages for the lamer forelimb were determined by use of a stationary force plate as the standard. SEs of the prediction of difference in PVF between the right and left forelimbs from HMA and VS were 6.1% and 5.2%, respectively. Head movement asymmetry (ICC, 0.72) was less repeatable than PVF (ICC, 0.86) and VS (ICC, 0.84). Associations were positive and significant between HMA (R(2) = 0.73) and VS (R(2) = 0.81) and the difference in PVF between the right and left forelimbs. Correct classification percentages for HMA and VS for detecting the lamer forelimb were 83.3% and 77.8%, respectively. Results suggested that an inertial sensor system to measure vertical asymmetry (HMA and VS) due to forelimb lameness in horses trotting in a straight line has adequate analytic sensitivity for clinical use. Additional studies are required to assess specificity of the system.

Perception and characterization of materials using signal processing techniques

In this paper, we develop a methodology and a conceptual framework in which manipulations are undertaken for perceiving and characterizing materials. Within this framework, we distinguish different materials (unknown environments) by actively contacting and testing them, and by analyzing the resulting sounds using a microphone. For this implementation, we identify sensor-derived measures that are diagnostic of a material's properties, and use these measures to categorize the objects (or unknown environments) in their different material class. The parameter of characterization is the internal angle of friction of the materials. This parameter is determined by the relation of strain and stress properties. Using this theoretical approach and the experimental results, we conclude that the statement of shape-invariance of materials is critical and invalid in real cases.