Accuracy of Sensor-Based Measurement of Clinically Relevant Motor Activities in Daily Life of Children With Mobility Impairments

OBJECTIVE

This study aimed to determine the accuracy of 3 sensor configurations and corresponding algorithms deriving clinically relevant outcomes of everyday life motor activities in children undergoing rehabilitation. These outcomes were identified in 2 preceding studies assessing the needs of pediatric rehabilitation. The first algorithm estimates the duration of lying, sitting, and standing positions and the number of sit-to-stand transitions with data from a trunk and a thigh sensor. The second algorithm detects active and passive wheeling periods with data from a wrist and a wheelchair sensor. The third algorithm detects free and assisted walking periods and estimates the covered altitude change during stair climbing with data from a single ankle sensor and a sensor placed on walking aids.

DESIGN

The participants performed a semi-structured activity circuit while wearing inertial sensors on both wrists, the sternum, and the thigh and shank of the less-affected side. The circuit included watching a movie, playing, cycling, drinking, and moving around between facilities. Video recordings, which 2 independent researchers labeled, served as reference criteria to determine the algorithms' performance.

SETTING

In-patient rehabilitation center.

PARTICIPANTS

Thirty-one children and adolescents with mobility impairments who were able to walk or use a manual wheelchair for household distances (N=31).

INTERVENTIONS

Not applicable.

MAIN OUTCOME MEASURE(S)

The algorithms' activity classification accuracies.

RESULTS

The activity classification accuracy was 97% for the posture detection algorithm, 96% for the wheeling detection algorithm, and 93% for the walking detection algorithm.

CONCLUSION(S)

The 3 sensor configurations and corresponding algorithms presented in this study revealed accurate measurements of everyday life motor activities in children with mobility impairments. To follow-up on this promising results, the sensor systems needs to be tested in long-term measurements outside the clinic before using the system to determine the children's motor performance in their habitual environment for clinical and scientific purposes.

Objective Measurement of Posture and Movement in Young Children Using Wearable Sensors and Customised Mathematical Approaches: A Systematic Review

Given the importance of young children's postures and movements to health and development, robust objective measures are required to provide high-quality evidence. This study aimed to systematically review the available evidence for objective measurement of young (0-5 years) children's posture and movement using machine learning and other algorithm methods on accelerometer data. From 1663 papers, a total of 20 papers reporting on 18 studies met the inclusion criteria. Papers were quality-assessed and data extracted and synthesised on sample, postures and movements identified, sensors used, model development, and accuracy. A common limitation of studies was a poor description of their sample data, yet over half scored adequate/good on their overall study design quality assessment. There was great diversity in all aspects examined, with evidence of increasing sophistication in approaches used over time. Model accuracy varied greatly, but for a range of postures and movements, models developed on a reasonable-sized (n > 25) sample were able to achieve an accuracy of >80%. Issues related to model development are discussed and implications for future research outlined. The current evidence suggests the rapidly developing field of machine learning has clear potential to enable the collection of high-quality evidence on the postures and movements of young children.

Enhancing Wearable Gait Monitoring Systems: Identifying Optimal Kinematic Inputs in Typical Adolescents

Machine learning-based gait systems facilitate the real-time control of gait assistive technologies in neurological conditions. Improving such systems needs the identification of kinematic signals from inertial measurement unit wearables (IMUs) that are robust across different walking conditions without extensive data processing. We quantify changes in two kinematic signals, acceleration and angular velocity, from IMUs worn on the frontal plane of bilateral shanks and thighs in 30 adolescents (8-18 years) on a treadmills and outdoor overground walking at three different speeds (self-selected, slow, and fast). Primary curve-based analyses included similarity analyses such as cosine, Euclidean distance, Poincare analysis, and a newly defined bilateral symmetry dissimilarity test (BSDT). Analysis indicated that superior-inferior shank acceleration (SI shank Acc) and medial-lateral shank angular velocity (ML shank AV) demonstrated no differences to the control signal in BSDT, indicating the least variability across the different walking conditions. Both SI shank Acc and ML shank AV were also robust in Poincare analysis. Secondary parameter-based similarity analyses with conventional spatiotemporal gait parameters were also performed. This normative dataset of walking reports raw signal kinematics that demonstrate the least to most variability in switching between treadmill and outdoor walking to help guide future machine learning models to assist gait in pediatric neurological conditions.

DeepHAR: a deep feed-forward neural network algorithm for smart insole-based human activity recognition

Health monitoring, rehabilitation, and fitness are just a few domains where human activity recognition can be applied. In this study, a deep learning approach has been proposed to recognise ambulation and fitness activities from data collected by five participants using smart insoles. Smart insoles, consisting of pressure and inertial sensors, allowed for seamless data collection while minimising user discomfort, laying the baseline for the development of a monitoring and/or rehabilitation system for everyday life. The key objective has been to enhance the deep learning model performance through several techniques, including data segmentation with overlapping technique (2 s with 50% overlap), signal down-sampling by averaging contiguous samples, and a cost-sensitive re-weighting strategy for the loss function for handling the imbalanced dataset. The proposed solution achieved an Accuracy and F1-Score of 98.56% and 98.57%, respectively. The Sitting activities obtained the highest degree of recognition, closely followed by the Spinning Bike class, but fitness activities were recognised at a higher rate than ambulation activities. A comparative analysis was carried out both to determine the impact that pre-processing had on the proposed core architecture and to compare the proposed solution with existing state-of-the-art solutions. The results, in addition to demonstrating how deep learning solutions outperformed those of shallow machine learning, showed that in our solution the use of data pre-processing increased performance by about 2%, optimising the handling of the imbalanced dataset and allowing a relatively simple network to outperform more complex networks, reducing the computational impact required for such applications.

Wearables and their applications for the rehabilitation of elderly people

Globally, there has been a change in the population pyramid with an accelerated aging process. This increase requires a greater challenge to maintain autonomy and independence. Currently, there are technologies developed with a focus on health. This is given by the development of wearables and their areas of applications. As a general context, this technology is characterized by the research field in energy generation, the development of external devices for human control and monitoring, clothing, smart textiles, and electronics. The latter are classified into three areas of application: monitoring and safety; fabrics, perception, and physical activity; and rehabilitation. A literature review is conducted to identify the state-of-the-art in these fields within the last years. The progress in monitoring systems and intelligent textiles is evidenced, being able to highlight remote feedback, materials, and wearability both at a commercial and user level. A discussion is included to address the main challenges and future trends in the application of wearables in elderly people.

DeepBBWAE-Net: A CNN-RNN Based Deep SuperLearner For Estimating Lower Extremity Sagittal Plane Joint Kinematics Using Shoe-Mounted IMU Sensors In Daily Living

Measurement of human body movement is an essential step in biomechanical analysis. The current standard for human motion capture systems uses infrared cameras to track reflective markers placed on the subject. While these systems can accurately track joint kinematics, the analyses are spatially limited to the lab environment. Though Inertial Measurement Unit (IMU) can eliminate the spatial limitations of the motion capture system, those systems are impractical for use in daily living due to the need for many sensors, typically one per body segment. Due to the need for practical and accurate estimation of joint kinematics, this study implements a reduced number of IMU sensors and employs machine learning algorithm to map sensor data to joint angles. Our developed algorithm estimates hip, knee, and ankle angles in the sagittal plane using two shoe-mounted IMU sensors in different practical walking conditions: treadmill, level overground, stair, and slope conditions. Specifically, we proposed five deep learning networks that use combinations of Convolutional Neural Networks (CNN) and Gated Recurrent Unit (GRU) based Recurrent Neural Networks (RNN) as base learners for our framework. Using those five baseline models, we proposed a novel framework, DeepBBWAE-Net, that implements ensemble techniques such as bagging, boosting, and weighted averaging to improve kinematic predictions. DeepBBWAE-Net predicts joint kinematics for the three joint angles under all the walking conditions with a Root Mean Square Error (RMSE) 6.93-29.0% lower than base models individually. This is the first study that uses a reduced number of IMU sensors to estimate kinematics in multiple walking environments.

A novel smartphone application is reliable for repeat administration and comparable to the Tekscan Strideway for spatiotemporal gait

Smartphone applications are increasingly being used to measure gait due to their portability and cost-effectiveness. Important reliability metrics are not available for most of these devices. The purpose of this article was to evaluate the test-retest reliability and concurrent validity of spatiotemporal gait using the novel Gait Analyzer smartphone application compared to the Tekscan Strideway. Healthy participants (n=23) completed 12 trials of 10-meter walking, at two separate time points, using Gait Analyzer and while walking across the Tekscan Strideway. The results suggest excellent test-retest reliability for the Gait Analyzer and good test-retest reliability for the Tekscan Strideway for both velocity and cadence. At both time points, these devices were moderately to strongly correlated to one another for both velocity and cadence. These data suggest that the Gait Analyzer and Tekscan Strideway are reliable over time and can comparably calculate velocity and cadence.

Transductive Learning Models for Accurate Ambulatory Gait Analysis in Elderly Residents of Assisted Living Facilities

Instrumented footwear represents a promising technology for spatiotemporal gait analysis in out-of-the-lab conditions. However, moderate accuracy impacts this technology's ability to capture subtle, but clinically meaningful, changes in gait patterns that may indicate adverse outcomes or underlying neurological conditions. This limitation hampers the use of instrumented footwear to aid functional assessments and clinical decision making. This paper introduces new transductive-learning inference models that substantially reduce measurement errors relative to conventional data processing techniques, without requiring subject-specific labelled data. The proposed models use subject-optimized input features and hyperparameters to adjust the spatiotemporal gait metrics (i.e., stride time, length, and velocity, swing time, and double support time) obtained with conventional techniques, resulting in computationally simpler models compared to end-to-end machine learning approaches. Model validity and reliability were evaluated against a gold-standard electronic walkway during a clinical gait performance test (6-minute walk test) administered to N=95 senior residents of assisted living facilities with diverse levels of gait and balance impairments. Average reductions in absolute errors relative to conventional techniques were -42.0% and -33.5% for spatial and gait-phase parameters, respectively, indicating the potential of transductive learning models for improving the accuracy of instrumented footwear for ambulatory gait analysis.

Operationalization, measurement, and health indicators of sedentary behavior in individuals with cerebral palsy: a scoping review

PURPOSE

To explore the operationalization and measurement of sedentary behavior (SB) in individuals with cerebral palsy (CP).

MATERIALS AND METHODS

We searched five databases from 2011 to 2020 for primary studies of experimental, qualitative, longitudinal, or observational designs measuring SB or postures typically characterized as sedentary (sitting, reclining, lying).

RESULTS

We screened 1112 citations and selected 47 studies. SB was operationalized through muscle activation, energy expenditure or oxygen consumption in typically sedentary postures (n = 9), and through thresholds and postures used by accelerometers, activity monitors, and a questionnaire to measure time spent in SB (n = 25). Seven out of the eight studies that measured energy expenditure found ≤1.5 metabolic equivalents of task (METs) for sitting and lying. While different accelerometer thresholds were used to measure SB, the behavior (SB) was consistently operationalized as sitting and lying. Little consistency existed in the subpopulation, instruments and cut-points for studies on validity or reliability of tools for measuring SB (n = 19).

CONCLUSIONS

Sitting and lying are considered sedentary postures, which is defined as ≤1.5 METs in individuals with CP. There is variability in the tools used to measure SB in individuals with CP. Therefore, consensus on the definition and reporting of SB is needed.Implications for rehabilitationAlthough sedentary behavior (SB) is increased in individuals with cerebral palsy (CP) compared to the typically developing population, there is no standard definition for SB for these individuals; this makes it difficult to synthesize data across studies.Sitting and lying are ≤1.5 METs in individuals with CP, suggesting we only need to measure posture to show change in SB.The commonly used accelerometer cut-point in the typically developing population of ≤100 counts per minute generally has excellent reliability across multiple devices in ambulatory children with CP.

A Soft Pressure Sensor Skin to Predict Contact Pressure Limit Under Hand Orthosis

Customized static orthoses in rehabilitation clinics often cause side effects, such as discomfort and skin damage due to excessive local contact pressure. Currently, clinicians adjust orthoses to reduce high contact pressure based on subjective feedback from patients. However, the adjustment is inefficient and prone to variability due to the unknown contact pressure distribution as well as differences in discomfort due to pressure across patients. This paper proposed a new method to predict a threshold of contact pressure (pressure limit) associated with moderate discomfort at each critical spot under hand orthoses. A new pressure sensor skin with 13 sensing units was configured from FEA results of pressure distribution simulated with hand geometry data of six healthy participants. It was used to measure contact pressure under two types of customized orthoses for 40 patients with bone fractures. Their subjective perception of discomfort was also measured using a 6 scores discomfort scale. Based on these data, five critical spots were identified that correspond to high discomfort scores (>1) or high pressure magnitudes (>0.024 MPa). An artificial neural network was trained to predict contact pressure at each critical spot with orthosis type, gender, height, weight, discomfort scores and pressure measurements as input variables. The neural networks show satisfactory prediction accuracy with R² values over 0.81 of regression between network outputs and measurements. This new method predicts a set of pressure limits at critical locations under the orthosis that the clinicians can use to make orthosis adjustment decisions.

Service Level Agreements for 5G and Beyond: Overview, Challenges and Enablers of 5G-Healthcare Systems

5G and beyond networks will transform the healthcare sector by opening possibilities for novel use cases and applications. Service level agreements (SLAs) can enable 5G-enabled medical device use cases by documenting how a medical device communication requirements are met by the unique characteristics of 5G networks and the roles and responsibilities of the stakeholders involved in offering safe and effective 5G-enabled healthcare to patients. However, there are gaps in this space that should be addressed to facilitate the efficient implementation of 5G technology in healthcare. Current literature is scarce regarding SLAs for 5G and is absent regarding SLAs for 5G-enabled medical devices. This paper aims to bridge these gaps by identifying key challenges, providing insight, and describing open research questions related to SLAs in 5G and specifically 5G-healthcare systems. This is helpful to network service providers, users, and regulatory authorities in developing, managing, monitoring, and evaluating SLAs in 5G-enabled medical systems.

Systematic review on the application of wearable inertial sensors to quantify everyday life motor activity in people with mobility impairments

BACKGROUND

Recent advances in wearable sensor technologies enable objective and long-term monitoring of motor activities in a patient's habitual environment. People with mobility impairments require appropriate data processing algorithms that deal with their altered movement patterns and determine clinically meaningful outcome measures. Over the years, a large variety of algorithms have been published and this review provides an overview of their outcome measures, the concepts of the algorithms, the type and placement of required sensors as well as the investigated patient populations and measurement properties.

METHODS

A systematic search was conducted in MEDLINE, EMBASE, and SCOPUS in October 2019. The search strategy was designed to identify studies that (1) involved people with mobility impairments, (2) used wearable inertial sensors, (3) provided a description of the underlying algorithm, and (4) quantified an aspect of everyday life motor activity. The two review authors independently screened the search hits for eligibility and conducted the data extraction for the narrative review.

RESULTS

Ninety-five studies were included in this review. They covered a large variety of outcome measures and algorithms which can be grouped into four categories: (1) maintaining and changing a body position, (2) walking and moving, (3) moving around using a wheelchair, and (4) activities that involve the upper extremity. The validity or reproducibility of these outcomes measures was investigated in fourteen different patient populations. Most of the studies evaluated the algorithm's accuracy to detect certain activities in unlabeled raw data. The type and placement of required sensor technologies depends on the activity and outcome measure and are thoroughly described in this review. The usability of the applied sensor setups was rarely reported.

CONCLUSION

This systematic review provides a comprehensive overview of applications of wearable inertial sensors to quantify everyday life motor activity in people with mobility impairments. It summarizes the state-of-the-art, it provides quick access to the relevant literature, and it enables the identification of gaps for the evaluation of existing and the development of new algorithms.

Random forest algorithms for recognizing daily life activities using plantar pressure information: a smart-shoe study

Background

Wearable activity trackers are regarded as a new opportunity to deliver health promotion interventions. Indeed, while the prediction of active behaviors is currently primarily relying on the processing of accelerometer sensor data, the emergence of smart clothes with multi-sensing capacities is offering new possibilities. Algorithms able to process data from a variety of smart devices and classify daily life activities could therefore be of particular importance to achieve a more accurate evaluation of physical behaviors. This study aims to (1) develop an activity recognition algorithm based on the processing of plantar pressure information provided by a smart-shoe prototype and (2) to determine the optimal hardware and software configurations.

Method

Seventeen subjects wore a pair of smart-shoe prototypes composed of plantar pressure measurement insoles, and they performed the following nine activities: sitting, standing, walking on a flat surface, walking upstairs, walking downstairs, walking up a slope, running, cycling, and completing office work. The insole featured seven pressure sensors. For each activity, at least four minutes of plantar pressure data were collected. The plantar pressure data were cut in overlapping windows of different lengths and 167 features were extracted for each window. Data were split into training and test samples using a subject-wise assignment method. A random forest model was trained to recognize activity. The resulting activity recognition algorithms were evaluated on the test sample. A multi hold-out procedure allowed repeating the operation with 5 different assignments. The analytic conditions were modulated to test (1) different window lengths (1–60 seconds), (2) some selected sensor configurations and (3) different numbers of data features.

Results

A window length of 20 s was found to be optimum and therefore used for the rest of the analysis. Using all the sensors and all 167 features, the smart shoes predicted the activities with an average success of 89%. “Running” demonstrated the highest sensitivity (100%). “Walking up a slope” was linked with the lowest performance (63%), with the majority of the false negatives being “walking on a flat surface” and “walking upstairs.” Some 2- and 3-sensor configurations were linked with an average success rate of 87%. Reducing the number of features down to 20 does not alter significantly the performance of the algorithm.

Conclusion

High-performance human behavior recognition using plantar pressure data only is possible. In the future, smart-shoe devices could contribute to the evaluation of daily physical activities. Minimalist configurations integrating only a small number of sensors and computing a reduced number of selected features could maintain a satisfying performance. Future experiments must include a more heterogeneous population.

Towards Wearable-Inertial-Sensor-Based Gait Posture Evaluation for Subjects with Unbalanced Gaits

Human gait reflects health condition and is widely adopted as a diagnostic basisin clinical practice. This research adopts compact inertial sensor nodes to monitor the functionof human lower limbs, which implies the most fundamental locomotion ability. The proposedwearable gait analysis system captures limb motion and reconstructs 3D models with high accuracy.It can output the kinematic parameters of joint flexion and extension, as well as the displacementdata of human limbs. The experimental results provide strong support for quick access to accuratehuman gait data. This paper aims to provide a clue for how to learn more about gait postureand how wearable gait analysis can enhance clinical outcomes. With an ever-expanding gait database,it is possible to help physiotherapists to quickly discover the causes of abnormal gaits, sports injuryrisks, and chronic pain, and provides guidance for arranging personalized rehabilitation programsfor patients. The proposed framework may eventually become a useful tool for continually monitoringspatio-temporal gait parameters and decision-making in an ambulatory environment.

Locomotion and cadence detection using a single trunk-fixed accelerometer: validity for children with cerebral palsy in daily life-like conditions

BACKGROUND

Physical therapy interventions for ambulatory youth with cerebral palsy (CP) often focus on activity-based strategies to promote functional mobility and participation in physical activity. The use of activity monitors validated for this population could help to design effective personalized interventions by providing reliable outcome measures. The objective of this study was to devise a single-sensor based algorithm for locomotion and cadence detection, robust to atypical gait patterns of children with CP in the real-life like monitoring conditions.

METHODS

Study included 15 children with CP, classified according to Gross Motor Function Classification System (GMFCS) between levels I and III, and 11 age-matched typically developing (TD). Six IMU devices were fixed on participant's trunk (chest and low back/L5), thighs, and shanks. IMUs on trunk were independently used for development of algorithm, whereas the ensemble of devices on lower limbs were used as reference system. Data was collected according to a semi-structured protocol, and included typical daily-life activities performed indoor and outdoor. The algorithm was based on detection of peaks associated to heel-strike events, identified from the norm of trunk acceleration signals, and included several processing stages such as peak enhancement and selection of the steps-related peaks using heuristic decision rules. Cadence was estimated using time- and frequency-domain approaches. Performance metrics were sensitivity, specificity, precision, error, intra-class correlation coefficient, and Bland-Altman analysis.

RESULTS

According to GMFCS, CP children were classified as GMFCS I (n = 7), GMFCS II (n = 3) and GMFCS III (n = 5). Mean values of sensitivity, specificity and precision for locomotion detection ranged between 0.93-0.98, 0.92-0.97 and 0.86-0.98 for TD, CP-GMFCS I and CP-GMFCS II-III groups, respectively. Mean values of absolute error for cadence estimation (steps/min) were similar for both methods, and ranged between 0.51-0.88, 1.18-1.33 and 1.94-2.3 for TD, CP-GMFCS I and CP-GMFCS II-III groups, respectively. The standard deviation was higher in CP-GMFCS II-III group, the lower performances being explained by the high variability of atypical gait patterns.

CONCLUSIONS

The algorithm demonstrated good performance when applied to a wide range of gait patterns, from normal to the pathological gait of highly affected children with CP using walking aids.

Optimizing Energy Harvesting for Foot Based Wearable Sensors

Wearable devices have the potential to improve healthcare, but suffer from significant barriers to adoption, including the need for constant recharging. Harvesting energy from the ambient environment to top-up batteries can overcome this, but the actual energy available is very small, and hence it is critical that the whole system is highly optimized. This paper presents an investigation into the optimization of inertial energy harvesters for placement at the human foot. Lower body locations have previously been shown to be very energy dense, however previous energy harvester modeling has focused on the lower leg rather than the foot itself for ease of device placement. We show that the typical energy density can be almost double at the foot compared with lower leg positions, with substantially more energy concentrated in a smaller bandwidth. There is thus a dual benefit of placing a harvester at the foot: there is more energy due to the larger movement of the foot, and more efficient (higher Q) harvesters can be used to increase the collected energy. We place these results in context by analyzing the power demands of a typical wearable, and identify that with appropriate harvester tuning the peak current requirements of the electronics can be fitted into the energy peaks generated from each footstep.

Toward Smart Footwear to Track Frailty Phenotypes-Using Propulsion Performance to Determine Frailty

Frailty assessment is dependent on the availability of trained personnel and it is currently limited to clinic and supervised setting. The growing aging population has made it necessary to find phenotypes of frailty that can be measured in an unsupervised setting for translational application in continuous, remote, and in-place monitoring during daily living activity, such as walking. We analyzed gait performance of 161 older adults using a shin-worn inertial sensor to investigate the feasibility of developing a foot-worn sensor to assess frailty. Sensor-derived gait parameters were extracted and modeled to distinguish different frailty stages, including non-frail, pre-frail, and frail, as determined by Fried Criteria. An artificial neural network model was implemented to evaluate the accuracy of an algorithm using a proposed set of gait parameters in predicting frailty stages. Changes in discriminating power was compared between sensor data extracted from the left and right shin sensor. The aim was to investigate the feasibility of developing a foot-worn sensor to assess frailty. The results yielded a highly accurate model in predicting frailty stages, irrespective of sensor location. The independent predictors of frailty stages were propulsion duration and acceleration, heel-off and toe-off speed, mid stance and mid swing speed, and speed norm. The proposed model enables discriminating different frailty stages with area under curve ranging between 83.2–95.8%. Furthermore, results from the neural network suggest the potential of developing a single-shin worn sensor that would be ideal for unsupervised application and footwear integration for continuous monitoring during walking.