Foot-worn Sensors Research Articles

Abstract TP74: MR-001 Improves Stride Length and Cadence in People With Chronic Stroke Walking Impairment

Introduction: Chronic stroke walking impairments impact approximately 3.5 million Americans and can lead to decreased quality of life, increased fall risk, and increased comorbidities. Stroke results in changes to spatiotemporal gait characteristics, including cadence, stride length, and speed, which can negatively impact walking stability and increase falls. In a multicenter randomized controlled trial, MR-001 was shown to increase comfortable walking speed more than Active Control (walking without MR-001). The purpose of this investigation is to characterize the spatiotemporal gait changes underlying MR-001's improvement in walking speed. Methods: Participants (n = 34) received the MR-001 (InTandem™) intervention for 30 minutes, 3 times a week for 5 weeks. MR-001 autonomously delivers an individualized and progressive intervention based on the principles of rhythmic auditory stimulation. The device algorithm uses input from foot-worn sensors to change the auditory stimuli in the form of embedded cues in time-shifted music. This secondary analysis from a larger clinical trial included change in stride length and cadence while walking without auditory stimuli, calculated as the change from before to after the intervention, as well as the relative contribution of changes in stride length and cadence to changes in walking speed. Results: Participants showed a significant increase in both stride length [+8%, Δ 0.06 +/- 0.02 m, p < 0.004] and cadence [+4%, Δ 3.04 +/- 1.32 steps/min, p < 0.028]. The average increase in stride length was 2x the established minimal detectable change of 4%. Changes in stride length and cadence each independently predicted the change in speed [ R 2 = 0.99, F (2,31) = 1132.44, p < 0.001], with the change in stride length being the stronger contributor [stride length: β = .78, p < 0.001, cadence: β = .50, p < 0.001]. Conclusions: Post-stroke reductions in stride length and cadence result in slower walking speed and negatively impact walking stability. In conclusion, results of this secondary analysis show that the previously reported increase in walking speed resulting from MR-001 is influenced by stride length more strongly than cadence for individuals with chronic stroke walking impairment.

Revealing the Mutual Information between Body-Worn Sensors and Metabolic Cost in Running.

Running power is a popular measure to gauge objective intensity. It has recently been shown, though, that foot-worn sensors alone cannot reflect variations in the exerted energy that stems from changes in the running economy. In order to support long-term improvement in running, these changes need to be taken into account. We propose leveraging the presence of two additional sensors worn by the most ambitious recreational runners for improved measurement: a watch and a heart rate chest strap. Using these accelerometers, which are already present and distributed over the athlete's body, carries more information about metabolic demand than a single foot-worn sensor. In this work, we demonstrate the mutual information between acceleration data and the metabolic demand of running by leveraging the information bottleneck of a constrained convolutional neural network. We perform lab measurements on 29 ambitious recreational runners (age = 28 ± 7 years, weekly running distance = 50 ± 25 km, V˙O2max = 60.3 ± 7.4 mL · min-1·kg-1). We show that information about the metabolic demand of running is contained in kinetic data. Additionally, we prove that the combination of three sensors (foot, torso, and lower arm) carries significantly more information than a single foot-worn sensor. We advocate for the development of running power systems that incorporate the sensors in watches and chest straps to improve the validity of running power and, thereby, long-term training planning.

A Pairwise Deep Ranking Model for Relative Assessment of Parkinson’s Disease Patients From Gait Signals

Continuous monitoring of the symptoms is crucial to improve the quality of life for patients with Parkinson’s Disease (PD). Thus, it is necessary to objectively assess the PD symptoms. Since manual assessment is subjective and prone to misinterpretation, computer-aided methods that use sensory measurements have recently been used to make objective PD assessment. Current methods follow an absolute assessment strategy, where the symptoms are classified into known categories or quantified with exact values. These methods are usually difficult to generalize and considered to be unreliable in practice. In this paper, we formulate the PD assessment problem as a relative assessment of one patient compared to another. For this assessment, we propose a new approach to the comparative analysis of gait signals obtained via foot-worn sensors. We introduce a novel pairwise deep-ranking model that is fed by data from a pair of patients, where the data is obtained from multiple ground reaction force sensors. The proposed model, called Ranking by Siamese Recurrent Network with Attention, takes two multivariate time-series as inputs and produces a probability of the first signal having a higher continuous attribute than the second one. Our detailed performance analysis shows that the accuracy of pairwise ranking predictions can reach up to 82% with an AUROC of 0.89 with ten-fold cross validation. The model outperforms the previous methods for PD monitoring when run in the same experimental setup. To the best of our knowledge, this is the first study that attempts to relatively assess PD patients using a pairwise ranking measure on sensory data. The model can serve as a complementary model to computer-aided prognosis tools by monitoring the progress of the patient during the applied treatment.

Differences in walking-to-turning characteristics between older adult fallers and nonfallers: a prospective and observational study using wearable inertial sensors.

Wearable inertial sensors have gradually been used as an objective technology for biomechanical assessments of both healthy and pathological movement patterns. This paper used foot-worn sensors for characterizing the spatiotemporal characteristics of walking and turning between older fallers and nonfallers. Thirty community-dwelling older fallers and 30 older nonfallers performed 10-m straight walking, turned 180° around a cone, and then walked 10-m back to the starting point. Specific algorithms were used to measure spatiotemporal gait (double support phase of the gait cycle, swing width, and minimal toe clearance) and turning parameters (turn duration and turn steps) using two foot-worn Physiolog inertial sensor system. The researchers directly exported data as reported by the system. Our findings indicated that older fallers showed 26.58% longer time (P = 0.036) and 13.21% more steps (P = 0.038) compared to nonfallers during turning. However, both groups decreased their walking velocity (both P < 0.001), increased double support (both P = 0.001), and increased the swing width (both P = 0.001) during the transition from walking to turning. The older nonfallers additionally increased toe clearance (P = 0.001). Compared with the fallers, the older nonfallers showed a larger change in the swing width (P = 0.025) and toe clearance (P = 0.025) in walking to turning. Older fallers may adopt a cautionary strategy while turning to reduce the risk of falls. Wearable sensors can provide the temporospatial characteristics of turning and reveal significant differences by fall status, indicating the potential of turning measures as possible markers for identifying those at fall risk.

Limitations of Foot-Worn Sensors for Assessing Running Power.

Running power as measured by foot-worn sensors is considered to be associated with the metabolic cost of running. In this study, we show that running economy needs to be taken into account when deriving metabolic cost from accelerometer data. We administered an experiment in which 32 experienced participants (age = 28 ± 7 years, weekly running distance = 51 ± 24 km) ran at a constant speed with modified spatiotemporal gait characteristics (stride length, ground contact time, use of arms). We recorded both their metabolic costs of transportation, as well as running power, as measured by a Stryd sensor. Purposely varying the running style impacts the running economy and leads to significant differences in the metabolic cost of running (p < 0.01). At the same time, the expected rise in running power does not follow this change, and there is a significant difference in the relation between metabolic cost and power (p < 0.001). These results stand in contrast to the previously reported link between metabolic and mechanical running characteristics estimated by foot-worn sensors. This casts doubt on the feasibility of measuring running power in the field, as well as using it as a training signal.

Spatio-temporal gait parameters obtained from foot-worn inertial sensors are reliable in healthy adults in single- and dual-task conditions

Inertial measurement units (IMUs) are increasingly popular and may be usable in clinical routine to assess gait. However, assessing their intra-session reliability is crucial and has not been tested with foot-worn sensors in healthy participants. The aim of this study was to assess the intra-session reliability of foot-worn IMUs for measuring gait parameters in healthy adults. Twenty healthy participants were enrolled in the study and performed the 10-m walk test in single- and dual-task ('carrying a full cup of water') conditions, three trials per condition. IMUs were used to assess spatiotemporal gait parameters, gait symmetry parameters (symmetry index (SI) and symmetry ratio (SR)), and dual task effects parameters. The relative and the absolute reliability were calculated for each gait parameter. Results showed that spatiotemporal gait parameters measured with foot-worn inertial sensors were reliable; symmetry gait parameters relative reliability was low, and SR showed better absolute reliability than SI; dual task effects were poorly reliable, and taking the mean of the second and the third trials was the most reliable. Foot-worn IMUs are reliable to assess spatiotemporal and symmetry ratio gait parameters but symmetry index and DTE gait parameters reliabilities were low and need to be interpreted with cautious by clinicians and researchers.

Inertial sensor-based gait parameters reflect patient-reported fatigue in multiple sclerosis

BackgroundMultiple sclerosis (MS) is a disabling disease affecting the central nervous system and consequently the whole body’s functional systems resulting in different gait disorders. Fatigue is the most common symptom in MS with a prevalence of 80%. Previous research studied the relation between fatigue and gait impairment using stationary gait analysis systems and short gait tests (e.g. timed 25 ft walk). However, wearable inertial sensors providing gait data from longer and continuous gait bouts have not been used to assess the relation between fatigue and gait parameters in MS. Therefore, the aim of this study was to evaluate the association between fatigue and spatio-temporal gait parameters extracted from wearable foot-worn sensors and to predict the degree of fatigue.MethodsForty-nine patients with MS (32 women; 17 men; aged 41.6 years, EDSS 1.0–6.5) were included where each participant was equipped with a small Inertial Measurement Unit (IMU) on each foot. Spatio-temporal gait parameters were obtained from the 6-min walking test, and the Borg scale of perceived exertion was used to represent fatigue. Gait parameters were normalized by taking the difference of averaged gait parameters between the beginning and end of the test to eliminate inter-individual differences. Afterwards, normalized parameters were transformed to principle components that were used as input to a Random Forest regression model to formulate the relationship between gait parameters and fatigue.ResultsSix principal components were used as input to our model explaining more than 90% of variance within our dataset. Random Forest regression was used to predict fatigue. The model was validated using 10-fold cross validation and the mean absolute error was 1.38 points. Principal components consisting mainly of stride time, maximum toe clearance, heel strike angle, and stride length had large contributions (67%) to the predictions made by the Random Forest.ConclusionsThe level of fatigue can be predicted based on spatio-temporal gait parameters obtained from an IMU based system. The results can help therapists to monitor fatigue before and after treatment and in rehabilitation programs to evaluate their efficacy. Furthermore, this can be used in home monitoring scenarios where therapists can monitor fatigue using IMUs reducing time and effort of patients and therapists.

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.

Parkinson's disease monitoring from gait analysis via foot-worn sensors

BackgroundIn Parkinson’s disease (PD), neuronal loss in the substantia nigra ultimate in dopaminergic denervation of the stiratum is followed by disarraying of the movements’ preciseness, automatism, and agility. Hence, the seminal sign of PD is a change in motor performance of affected individuals. As PD is a neurodegenerative disease, progression of disability in mobility is an inevitable consequence. Indeed, the major cause of morbidity and mortality among patients with PD is the motor changes restricting their functional independence. Therefore, monitoring the manifestations of the disease is crucial to detect any worsening of symptoms timely, in order to maintain and improve the quality of life of these patients. AimThe changes in motion of patients with PD can be ascertained by the help of wearable sensors attached to the limbs of subjects. Then analysing the recorded data for variation of signals would make it possible to figure an individualized profile of the disease. Advancement of such tools would improve understanding of the disease evolution in the long term and simplify the detection of precipitous changes in gait on a daily basis in the short term. In both cases the apperception of such events would contribute to improve the clinical decision making process with reliable data. To this end, we offer here a computational solution for effective monitoring of PD patients from gait analysis via multiple foot-worn sensors. MethodsWe introduce a supervised model that is fed by ground reaction force (GRF) signals acquired from these gait sensors. We offer a hybrid model, called Locally Weighted Random Forest (LWRF), for regression analysis over the numerical features extracted from input signals to predict the severity of PD symptoms in terms of Universal Parkinson Disease Rating Scale (UPDRS) and Hoehn and Yahr (H&Y) scale. From GRF signals sixteen time-domain features and seven frequency-domain features were extracted and used. Results and conclusionAn experimental analysis conducted on a real data acquired from PD patients and healthy controls has shown that the predictions are highly correlated with the clinical annotations. Proposed approach for severity detection has the best correlation coefficient (CC), mean absolute error (MAE) and root mean squared error (RMSE) values with 0.895, 4.462 and 7.382 respectively in terms of UPDRS. The regression results for H&Y Scale discerns that proposed model outperforms other models with CC, MAE and RMSE with values 0.960, 0.168 and 0.306 respectively. In classification setup, proposed approach achieves higher accuracy in comparison with other studies with accuracy and specificity of 99.0% and 99.5% respectively. Main novelty of this approach is the fact that an exact value of the symptom level can be inferred rather than a categorical result that defines the severity of motor disorders.

Novel Foot Progression Angle Algorithm Estimation via Foot-Worn, Magneto-Inertial Sensing.

The foot progression angle (FPA) is an important clinical measurement but currently can only be computed while walking in a laboratory with a marker-based motion capture system. This paper proposes a novel FPA estimation algorithm based on a single integrated sensor unit, consisting of an accelerometer, gyroscope, and magnetometer, worn on the foot. The algorithm introduces a real-time heading vector with a complementary filter and utilizes a gradient descent method and zero-velocity update correction. Validation testing was performed by comparing FPA estimation from the wearable sensor with the standard FPAs computed from a marker-based motion capture system. Subjects performed nine walking trials of 2.5 min each on a treadmill. During each trial, subjects walked at one speed out of three options (1.0, 1.2, and 1.4 m/s) and walked with one gait pattern out of three options (normal, toe-in, and toe-out). The algorithm estimated FPA to within 0.2 ° of error or less for each walking conditions. A novel FPA algorithm has been introduced and described based on a single foot-worn sensor unit, and validation testing showed that FPA estimation was accurate for different walking speeds and foot angles. This study enables future wearable systems gait research to assess or train walking patterns outside a laboratory setting in natural walking environments.