Gait Variability to Phenotype Common Orthopedic Gait Impairments Using Wearable Sensors.

Mobility impairments are a common symptom of age-related degenerative diseases. Gait features can discriminate those with mobility disorders from healthy individuals, yet phenotyping specific pathologies remains challenging. This study aims to identify if gait parameters derived from two foot-mounted inertial measurement units (IMU) during the 6 min walk test (6MWT) can phenotype mobility impairment from different pathologies (Lumbar spinal stenosis (LSS)-neurogenic diseases, and knee osteoarthritis (KOA)-structural joint disease). Bilateral foot-mounted IMU data during the 6MWT were collected from patients with LSS and KOA and matched healthy controls (N = 30, 10 for each group). Eleven gait parameters representing four domains (pace, rhythm, asymmetry, variability) were derived for each minute of the 6MWT. In the entire 6MWT, gait parameters in all four domains distinguished between controls and both disease groups; however, the disease groups demonstrated no statistical differences, with a trend toward higher stride length variability in the LSS group (p = 0.057). Additional minute-by-minute comparisons identified stride length variability as a statistically significant marker between disease groups during the middle portion of 6WMT (3rd min: p ≤ 0.05; 4th min: p = 0.06). These findings demonstrate that gait variability measures are a potential biomarker to phenotype mobility impairment from different pathologies. Increased gait variability indicates loss of gait rhythmicity, a common feature in neurologic impairment of locomotor control, thus reflecting the underlying mechanism for the gait impairment in LSS. Findings from this work also identify the middle portion of the 6MWT as a potential window to detect subtle gait differences between individuals with different origins of gait impairment.

Test-retest reliability of wireless inertial-sensor derived measurements of knee joint kinematics.

Advances in sensor technology have provided an opportunity to measure gait characteristics using body-worn inertial measurement units (IMUs). Whilst research investigating the validity of IMUs in reporting gait characteristics is extensive, research investigating the reliability of IMUs is limited. This study aimed to investigate the inter-session reliability of wireless IMU derived measures of gait (i.e., knee angle, range of motion) taking multiple test administrators into account. Fifteen healthy volunteers (43 ± 15 years) completed two visits. Within each visit, participants were required to perform two sets of 6 gait trials (6-metre walk tests). IMUs were placed on the participant in 7 locations on the lower limbs and waist. A different test administrator (n = 3) applied the IMUs at each set. At visit 2, this procedure was repeated with the same test administrators as visit 1. Kinematic measures of maximum angle (Knee_Max), minimum angle (Knee_Min), and range of motion (RoM) are reported for the left and right knee. The intraclass correlation coefficients (ICC), standard error of measurement (SEM) and minimum detectable change (MDC) are reported to determine IMU reliability. The results confirmed moderate to good inter-session reliability across all features (0.73-0.87). SEM values ranged from 1.21-3.32° and MDC values ranged from 3.37 - 9.21°. Therefore, IMUs appear to be a reliable method to determine inter-session gait characteristics across multiple test administrators.

An Automatic Foot and Shank IMU Synchronization Algorithm: Proof-of-concept.

When using wearable sensors for measurement and analysis of human performance, it is often necessary to integrate and synchronise data from separate sensor systems. This paper describes a synchronization technique between IMUs attached to the shanks and insoles attached at the feet and aims to solve the need to compute the ankle joint angle, which relies on synchronized sensor data. This will additionally enable concurrent analysis using gait kinematic and kinetic features. A proof-of-concept of the algorithm, which relies on cross-correlation of gyroscope sensor data from the shank and foot, to align the sensor systems is demonstrated. The algorithm output is validated against those signals synchronized using manually annotated heel-strike and toe-off ground-truth signal landmarks, identified in both the shank and feet signals using previously published definitions. Results demonstrate that the developed algorithm is capable of synchronizing both sensor systems, based on IMU data from both healthy participants and participants suffering from knee osteoarthritis, with a mean lag time bias of 25.56ms when compared to the ground truth. A proof-of-concept of technique to synchronise IMUs attached to the shanks and insoles attached at the feet is demonstrated and offers an alternative approach to sensor system synchronisation.

Objective features of sedentary time and light activity differentiate people with low back pain from healthy controls: a pilot study.

BACKGROUND CONTEXT: Physical inactivity has been described as both a cause and a consequence of low back pain (LBP) largely based on self-reported measures of daily activity. A better understanding of the connections between routine physical activity and LBP may improve LBP interventions. PURPOSE: In this study, we aim to objectively characterize the free-living physical activity of people with low back pain in comparison to healthy controls using accelerometers, and we aim to derive a set of LBP-specific physical activity minutes thresholds that may be used as targets for future physical activity interventions. STUDY DESIGN: Cross-sectional. PATIENT SAMPLE: A total of 22 low back pain patients and 155 controls. OUTCOME MEASURES: Accelerometry derived physical activity measures. METHODS: Twenty-two people with LBP were compared to 155 age and gender-matched healthy controls. All subjects wore an ActiGraph accelerometer on the right hip for 7 consecutive days. Accelerometry-based physical activity features (count-per-minute CPM) were derived using Freedson's intervals and physical performance intervals. A random forest machine learning classifier was trained to classify LBP status using a leave-one-out cross-validation procedure. An interpretation algorithm, the SHapley Additive exPlanations (SHAP) algorithm was subsequently applied to assess the feature importance and to establish LBP-specific physical activity thresholds. RESULTS: The LBP group reported mild to moderate disability (average ODI=18.5). The random forest classifier identified a set of 8 features (digital biomarkers) that achieved 88.1% accuracy for distinguishing LBP from controls. All of the top distinguishing features were related to differences in the sedentary and light activity ranges (<800 CPM), whereas moderate to vigorous physical activity was not discriminative. In addition, we identified and ranked physical activity thresholds that are associated with LBP prediction that can be used in future studies of physical activity interventions for LBP. CONCLUSIONS: We describe a set of physical activity features from accelerometry data associated with LBP. All of the discriminating features were derived from the sedentary and light activity range. We also identified specific activity intensity minutes thresholds that distinguished LBP subjects from healthy controls. Future examination on the digital markers and thresholds identified through this work can be used to improve physical activity interventions for LBP treatment and prevention by allowing the development of LBP-specific physical activity guidelines.

Examining the Association Between Self-Reported Estimates of Function and Objective Measures of Gait and Physical Capacity in Lumbar Stenosis.

OBJECTIVE: To evaluate the association of self-reported physical function with subjective and objective measures as well as temporospatial gait features in lumbar spinal stenosis (LSS). DESIGN: Cross-sectional pilot study. SETTING: Outpatient multispecialty clinic. PARTICIPANTS: Participants with LSS and matched controls without LSS (n=10 per group; N=20). INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Self-reported physical function (36-Item Short Form Health Survey [SF-36] physical functioning domain), Oswestry Disability Index, Swiss Spinal Stenosis Questionnaire, the Neurogenic Claudication Outcome Score, and inertia measurement unit (IMU)-derived temporospatial gait features. RESULTS: Higher self-reported physical function scores (SF-36 physical functioning) correlated with lower disability ratings, neurogenic claudication, and symptom severity ratings in patients with LSS (P<.05). Compared with controls without LSS, patients with LSS have lower scores on physical capacity measures (median total distance traveled on 6-minute walk test: controls 505 m vs LSS 316 m; median total distance traveled on self-paced walking test: controls 718 m vs LSS 174 m). Observed differences in IMU-derived gait features, physical capacity measures, disability ratings, and neurogenic claudication scores between populations with and without LSS were statistically significant. CONCLUSIONS: Further evaluation of the association of IMU-derived temporospatial gait with self-reported physical function, pain related-disability, neurogenic claudication, and spinal stenosis symptom severity score in LSS would help clarify their role in tracking LSS outcomes.

Relationship between tendon structure, stiffness, gait patterns and patient reported outcomes during the early stages of recovery after an Achilles tendon rupture.

After an Achilles tendon (AT) injury, the decision to return to full weightbearing for the practice of sports or strenuous activities is based on clinical features only. In this study, tendon stiffness and foot plantar pressure, as objective quantitative measures that could potentially inform clinical decision making, were repeatedly measured in 15 patients until 3 months after the AT rupture by using shear wave elastography (SWE) and wearable insoles, respectively. Meanwhile, patient reported outcomes assessing the impact on physical activity were evaluated using the Achilles Tendon Total Rupture Score (ATRS). At week-2 post-injury, stiffness of the injured tendon varied from 6.00 ± 1.62 m/s (mean ± SD) close to the rupture to 8.91 ± 2.29 m/s when measured more distally. While near complete recovery was observed in distal and middle regions at week-8, the shear wave velocity in the proximal region recovered to only 65% of the contralateral value at week-12. In a parallel pre-clinical study, the tendon stiffness measured in vivo by SWE in a rat model was found to be strongly correlated with ex vivo values of the Young's modulus, which attests to the adequacy of SWE for these measures. The insole derived assessment of the plantar pressure distribution during walking showed slight sub-optimal function of the affected foot at week-12, while the ATRS score recovered to a level of 59 ± 16. Significant correlations found between tendon stiffness, insole variables and distinct ATRS activities, suggest clinical relevance of tendon stiffness and foot plantar pressure measurements. These results illustrate how an alteration of the AT structure can impact daily activities of affected patients and show how digital biomarkers can track recovery in function over time.

Gait features for discriminating between mobility-limiting musculoskeletal disorders: Lumbar spinal stenosis and knee osteoarthritis.

BACKGROUND: Functional ambulation limitations are features of lumbar spinal stenosis (LSS) and knee osteoarthritis (OA). With numerous validated walking assessment protocols and a vast number of spatiotemporal gait parameters available from sensor-based assessment, there is a critical need for selection of appropriate test protocols and variables for research and clinical applications. RESEARCH QUESTION: In patients with knee OA and LSS, what are the best sensor-derived gait parameters and the most suitable clinical walking test to discriminate between these patient populations and controls? METHODS: We collected foot-mounted inertial measurement unit (IMU) data during three walking tests (fast-paced walk test-FPWT, 6-min walk test- 6MWT, self-paced walk test - SPWT) for subjects with LSS, knee OA and matched controls (N = 10 for each group). Spatiotemporal gait characteristics were extracted and pairwise compared (Omega partial squared - ωp2) between patients and controls. RESULTS: We found that normal paced walking tests (6MWT, SPWT) are better suited for distinguishing gait characteristics between patients and controls. Among the sensor-based gait parameters, stance and double support phase timing were identified as the best gait characteristics for the OA population discrimination, whereas foot flat ratio, gait speed, stride length and cadence were identified as the best gait characteristics for the LSS population discrimination. SIGNIFICANCE: These findings provide guidance on the selection of sensor-derived gait parameters and clinical walking tests to detect alterations in mobility for people with LSS and knee OA.

Robust Step Detection from Different Waist-Worn Sensor Positions: Implications for Clinical Studies.

Analyzing human gait with inertial sensors provides valuable insights into a wide range of health impairments, including many musculoskeletal and neurological diseases. A representative and reliable assessment of gait requires continuous monitoring over long periods and ideally takes place in the subjects' habitual environment (real-world). An inconsistent sensor wearing position can affect gait characterization and influence clinical study results, thus clinical study protocols are typically highly proscriptive, instructing all participants to wear the sensor in a uniform manner. This restrictive approach improves data quality but reduces overall adherence. In this work, we analyze the impact of altering the sensor wearing position around the waist on sensor signal and step detection. We demonstrate that an asymmetrically worn sensor leads to additional odd-harmonic frequency components in the frequency spectrum. We propose a robust solution for step detection based on autocorrelation to overcome sensor position variation (sensitivity = 0.99, precision = 0.99). The proposed solution reduces the impact of inconsistent sensor positioning on gait characterization in clinical studies, thus providing more flexibility to protocol implementation and more freedom to participants to wear the sensor in the position most comfortable to them. This work is a first step towards truly position-agnostic gait assessment in clinical settings.

Continuous Digital Monitoring of Walking Speed in Frail Elderly Patients: Noninterventional Validation Study and Longitudinal Clinical Trial.

BACKGROUND: Digital technologies and advanced analytics have drastically improved our ability to capture and interpret health-relevant data from patients. However, only limited data and results have been published that demonstrate accuracy in target indications, real-world feasibility, or the validity and value of these novel approaches. OBJECTIVE: This study aimed to establish accuracy, feasibility, and validity of continuous digital monitoring of walking speed in frail, elderly patients with sarcopenia and to create an open source repository of raw, derived, and reference data as a resource for the community. METHODS: Data described here were collected as a part of 2 clinical studies: an independent, noninterventional validation study and a phase 2b interventional clinical trial in older adults with sarcopenia. In both studies, participants were monitored by using a waist-worn inertial sensor. The cross-sectional, independent validation study collected data at a single site from 26 naturally slow-walking elderly subjects during a parcours course through the clinic, designed to simulate a real-world environment. In the phase 2b interventional clinical trial, 217 patients with sarcopenia were recruited across 32 sites globally, where patients were monitored over 25 weeks, both during and between visits. RESULTS: We have demonstrated that our approach can capture in-clinic gait speed in frail slow-walking adults with a residual standard error of 0.08 m per second in the independent validation study and 0.08, 0.09, and 0.07 m per second for the 4 m walk test (4mWT), 6-min walk test (6MWT), and 400 m walk test (400mWT) standard gait speed assessments, respectively, in the interventional clinical trial. We demonstrated the feasibility of our approach by capturing 9668 patient-days of real-world data from 192 patients and 32 sites, as part of the interventional clinical trial. We derived inferred contextual information describing the length of a given walking bout and uncovered positive associations between the short 4mWT gait speed assessment and gait speed in bouts between 5 and 20 steps (correlation of 0.23) and longer 6MWT and 400mWT assessments with bouts of 80 to 640 steps (correlations of 0.48 and 0.59, respectively). CONCLUSIONS: This study showed, for the first time, accurate capture of real-world gait speed in slow-walking older adults with sarcopenia. We demonstrated the feasibility of long-term digital monitoring of mobility in geriatric populations, establishing that sufficient data can be collected to allow robust monitoring of gait behaviors outside the clinic, even in the absence of feedback or incentives. Using inferred context, we demonstrated the ecological validity of in-clinic gait assessments, describing positive associations between in-clinic performance and real-world walking behavior. We make all data available as an open source resource for the community, providing a basis for further study of the relationship between standardized physical performance assessment and real-world behavior and independence.

Quantifying Functional Difference in Centre of Pressure Post Achilles Tendon Rupture using Sensor Insoles.

Significant advances are being made to instrument and more objectively quantify gait and mobility assessment, treatment and rehabilitation. Wearable, inertial, optical and location-based technologies are proposed as scalable soutions, suited to both clinic and home-based settings, that can provide clinically meaningful insights into gait and mobility. In this paper, sensorised insoles are shown to provide the means to measure where pressure is distributed through each foot for each step, while it is in contact with the ground. Through profiling the points through which pressure is applied over each step and comparing changes between the affected and healthy limbs, insights into biomechanical foot dysfunction are shown for a patient population which may inform assessment, treatment and rehabilitation. This paper proposes a series of sensor-agnostic metrics derived from sensorised insoles to quantify foot mobility over a series of steps in a patient population. Differences in these metrics are shown between the affected and unaffected foot in a cohort of patients 8 weeks post Achilles tendon rupture.

DigitalROM: Development and validation of a system for assessment of shoulder range of motion.

Assessing shoulder mobility is traditionally performed by a clinician using a goniometer, however this method suffers from inter-rater reliability issues. Wearable inertial sensors, image-based systems and 3D-cameras are proposed to objectively quantify shoulder range of motion (ROM). Standardised data collection platforms are required to ensure the consistency of measurements. This paper describes DigitalROM, a Microsoft Kinect 3D camera based system, and a standardised data collection protocol for shoulder ROM assessment optimised for multi-centre clinical trial deployments. DigitalROM is shown to compare very well against image-based ground truth measures (R2= 0.98 and RMSE≤7°) and shows slightly better performance than inertial sensor based ROM measurements (R2= 0.96 and RMSE≤9°). Additionally, DigitalROM offers the ability to ensure patient adherence to the movement protocol during data collection.

Simple Gait Symmetry Measures Based on Foot Angular Velocity: Analysis in Post Stroke Patients.

In this paper, we propose symmetry measures for post stroke assessment based on gait signal profiles from inertial sensors. Ten healthy controls and eight post stroke patients performed 6-Minute Walk Tests while wearing an inertial sensor on top of each shoe. Symmetry measures based on the linear correlation and the normalized sample distance between left and right foot pitch angular velocity showed high discriminating power to differentiate post stroke gait from healthy controls (Cliff's D = 0.95, Wilcoxon test p<0.001). The proposed symmetry measures are simple to estimate and do not require spatiotemporal gait parameters while they provide comparable discriminating power than symmetry measures based on spatiotemporal gait characteristics such as maximum angular velocity and stance ratio of each cycle. The proposed symmetry measures have the potential for generalization in wearable sensor based gait symmetry assessment.

Gait Symmetry Assessment with a Low Back 3D Accelerometer in Post-Stroke Patients.

Gait asymmetry is an important marker of mobility impairment post stroke. This study proposes a new gait symmetry index (GSI) to quantify gait symmetry with one 3D accelerometer at L3 (GSIL3). GSIL3 was evaluated with 16 post stroke patients and nine healthy controls in the Six-Minute-Walk-Test (6-MWT). Discriminative power was evaluated with Wilcoxon test and the effect size (ES) was computed with Cliff's Delta. GSIL3 estimated during the entire 6-MWT and during a short segment straight walk (GSIL3straight) have comparable effect size to one another (ES = 0.89, p < 0.001) and to the symmetry indices derived from feet sensors (|ES| = [0.22, 0.89]). Furthermore, while none of the indices derived from feet sensors showed significant differences between post stroke patients walking with a cane compared to those able to walk without, GSIL3 was able to discriminate between these two groups with a significantly lower value in the group using a cane (ES = 0.70, p = 0.02). In addition, GSIL3 was strongly associated with several symmetry indices measured by feet sensors during the straight walking cycles (Spearman correlation: |ρ| = [0.82, 0.88], p < 0.05). The proposed index can be a reliable and cost-efficient post stroke gait symmetry assessment with implications for research and clinical practice.

Objective measurement of function following lumbar spinal stenosis decompression reveals improved functional capacity with stagnant real-life physical activity.

BACKGROUND CONTEXT: Lumbar spinal stenosis (LSS) is a prevalent and costly condition associated with significant dysfunction. Alleviation of pain and improvement of function are the primary goals of surgical intervention. Although prior studies have measured subjective improvements in function after surgery, few have examined objective markers of functional improvement. PURPOSE: We aimed to objectively measure and quantify changes in physical capacity and physical performance following surgical decompression of LSS. STUDY DESIGN/SETTING: Prospective cohort study. PATIENT SAMPLE: Thirty-eight patients with LSS determined by the treating surgeon's clinical and imaging evaluation, and who were scheduled for surgical treatment, were consecutively recruited at two academic medical facilities, with 28 providing valid data for analysis at baseline and 6 months after surgery. OUTCOME MEASURES: Before surgery and at 6 months after surgery, participants provided 7 days of real-life physical activity (performance) using ActiGraph accelerometers; completed two objective functional capacity measures, the Short Physical Performance Battery and Self-Paced Walking Test; and completed three subjective functional outcome questionnaires, Oswestry Disability Index, Spinal Stenosis Symptom Questionnaire, and Short-Form 36. METHODS: Physical activity, as measured by continuous activity monitoring, was analyzed as previously described according to the 2008 American Physical Activity Guidelines. Paired t tests were performed to assess for postsurgical changes in all questionnaire outcomes and all objective functional capacity measures. Chi-square analysis was used to categorically assess whether patients were more likely to meet these physical activity recommendations after surgery. RESULTS: Participants were 70.1 years old (±8.9) with 17 females (60.7%) and an average body mass index of 28.4 (±6.2). All subjective measures (Oswestry Disability Index, Spinal Stenosis Symptom Questionnaire, and Short-Form 36) improved significantly at 6 months after surgery, as did objective functional measures of capacity including balance, gait speed, and ambulation distance (Short Physical Performance Battery, Self-Paced Walking Test). However, objectively measured performance (real-life physical activity) did not change following surgery. Although fewer participants qualified as inactive (54% vs. 71%), and more (11% vs. 4%) met the physical activity guideline recommendations at the 6-month follow-up, these differences were not statistically significant (p=.22) CONCLUSIONS: This is the first study, of which we are aware, to objectively evaluate changes in postsurgical performance (real-life physical activity) in people with LSS. We found that at 6 months after surgery for LSS, participants demonstrated significant improvements in self-reported function and objectively measured physical capacity, but not physical performance as measured by continuous activity monitoring. This lack of improvement in performance, despite improvements in self-reported function and objective capacity, suggests a role for postoperative rehabilitation focused specifically on increasing performance after surgery in the LSS population.

Smartphone-based recognition of states and state changes in bipolar disorder patients.

Today's health care is difficult to imagine without the possibility to objectively measure various physiological parameters related to patients' symptoms (from temperature through blood pressure to complex tomographic procedures). Psychiatric care remains a notable exception that heavily relies on patient interviews and self-assessment. This is due to the fact that mental illnesses manifest themselves mainly in the way patients behave throughout their daily life and, until recently there were no "behavior measurement devices." This is now changing with the progress in wearable activity recognition and sensor enabled smartphones. In this paper, we introduce a system, which, based on smartphone-sensing is able to recognize depressive and manic states and detect state changes of patients suffering from bipolar disorder. Drawing upon a real-life dataset of ten patients, recorded over a time period of 12 weeks (in total over 800 days of data tracing 17 state changes) by four different sensing modalities, we could extract features corresponding to all disease-relevant aspects in behavior. Using these features, we gain recognition accuracies of 76% by fusing all sensor modalities and state change detection precision and recall of over 97%. This paper furthermore outlines the applicability of this system in the physician-patient relations in order to facilitate the life and treatment of bipolar patients.

Towards Measuring Stress with Smartphones and Wearable Devices During Workday and Sleep.

Work should be a source of health, pride, and happiness, in the sense of enhancing motivation and strengthening personal development. Healthy and motivated employees perform better and remain loyal to the company for a longer time. But, when the person constantly experiences high workload over a longer period of time and is not able to recover, then work may lead to prolonged negative effects and might cause serious illnesses like chronic stress disease. In this work, we present a solution for assessing the stress experience of people, using features derived from smartphones and wearable chest belts. In particular, we use information from audio, physical activity, and communication data collected during workday and heart rate variability data collected at night during sleep to build multinomial logistic regression models. We evaluate our system in a real work environment and in daily-routine scenarios of 35 employees over a period of 4 months and apply the leave-one-day-out cross-validation method for each user individually to estimate the prediction accuracy. Using only smartphone features, we get an accuracy of 55 %, and using only heart rate variability features, we get an accuracy of 59 %. The combination of all features leads to a rate of 61 % for a three-stress level (low, moderate, and high perceived stress) classification problem.