Smartwatch-Based Prediction of Single-Stride and Stride-to-Stride Gait Outcomes Using Regression-Based Machine Learning.

Spatiotemporal variability during gait is linked to fall risk and could be monitored using wearable sensors. Although many users prefer wrist-worn sensors, most applications position at other sites. We developed and evaluated an application using a consumer-grade smartwatch inertial measurement unit (IMU). Young adults (n = 41) completed seven-minute conditions of treadmill gait at three speeds. Single-stride outcomes (stride time, length, width, and speed) and spatiotemporal variability (coefficient of variation of each single-stride outcome) were recorded using an optoelectronic system, while 232 single- and multi-stride IMU metrics were recorded using an Apple Watch Series 5. These metrics were input to train linear, ridge, support vector machine (SVM), random forest, and extreme gradient boosting (xGB) models of each spatiotemporal outcome. We conducted Model × Condition ANOVAs to explore model sensitivity to speed-related responses. xGB models were best for single-stride outcomes [relative mean absolute error (% error): 7-11%; intraclass correlation coefficient (ICC2,1) 0.60-0.86], and SVM models were best for spatiotemporal variability (% error: 18-22%; ICC2,1 = 0.47-0.64). Spatiotemporal changes with speed were captured by these models (Condition: p < 0.00625). Results support the feasibility of monitoring single-stride and multi-stride spatiotemporal parameters using a smartwatch IMU and machine learning.

Effects of a biomechanical-based Tai Chi program on gait and posture in people with Parkinson's disease: study protocol for a randomized controlled trial.

BACKGROUND: Parkinson's disease (PD) is associated with changes in gait and posture, which increases the rate of falls and injuries in this population. Tai Chi (TC) training enhances the movement capacity of patients with PD. However, the understanding of the effect of TC training on gait and postural stability in PD is lacking. This study aims to examine the effect of biomechanical-based TC training on dynamic postural stability and its relationship with walking performance. METHODS/DESIGN: A single-blind, randomized control trial of 40 individuals with early-stage PD was conducted (Hoehn and Yahr stages 1 to 3). Patients with PD will be randomly assigned to either the TC or control group. The TC group will participate in a biomechanical-based TC training program that is formed based on the movement analysis of TC and will be practiced thrice a week for 12 weeks. The control group will be required to engage in at least 60 min of regular physical activity (PA) on their own for three times per week for 12 weeks. The primary and secondary outcomes will be assessed at baseline and at 6 and 12 weeks after commencing the study protocol. The primary outcome measures will include dynamic postural stability indicated by the center of mass and center of pressure separation distance and clearance distance of the heel and toe measured during fixed-obstacle crossing. The secondary measures are gait speed, cadence, step length during level surface walking (simple task), and fixed-obstacle crossing (challenging task). The Unified Parkinson's Disease Rating Scale, single leg-stance test with eyes open and closed, and three cognitive scores (Stroop Test, Trail Making Test Part B, and the Wisconsin Card Sorting Test) were also employed. DISCUSSION: This protocol could lead to the development of a biomechanics TC training program for the improvement of gait and postural stability among individuals with PD. The program could enhance the understanding of the effect of TC training on gait and postural stability and could help improve or preserve the postural stability, self-confidence, and active participation in social activities of the participants, thus enhancing their overall quality of life. TRIAL REGISTRATION: ClinicalTrials.gov NCT04644367. Registered on 25 November 2020.

Barriers and facilitators to participation in exercise prehabilitation before cancer surgery for older adults with frailty: a qualitative study.

BACKGROUND: Older adults with frailty are at an increased risk of adverse outcomes after surgery. Exercise before surgery (exercise prehabilitation) may reduce adverse events and improve recovery after surgery. However, adherence with exercise therapy is often low, especially in older populations. The purpose of this study was to qualitatively assess the barriers and facilitators to participating in exercise prehabilitation from the perspective of older people with frailty participating in the intervention arm of a randomized trial. METHODS: This was a research ethics approved, nested descriptive qualitative study within a randomized controlled trial of home-based exercise prehabilitation vs. standard care with older patients (≥ 60 years) having elective cancer surgery, and who were living with frailty (Clinical Frailty Scale ≥ 4). The intervention was a home-based prehabilitation program for at least 3 weeks before surgery that involved aerobic activity, strength and stretching, and nutritional advice. After completing the prehabilitation program, participants were asked to partake in a semi-structured interview informed by the Theoretical Domains Framework (TDF). Qualitative analysis was guided by the TDF. RESULTS: Fifteen qualitative interviews were completed. Facilitators included: 1) the program being manageable and suitable to older adults with frailty, 2) adequate resources to support engagement, 3) support from others, 4) a sense of control, intrinsic value, noticing progress and improving health outcomes and 5) the program was enjoyable and facilitated by previous experience. Barriers included: 1) pre-existing conditions, fatigue and baseline fitness, 2) weather, and 3) guilt and frustration when unable to exercise. A need for individualization and variety was offered as a suggestion by participants and was therefore described as both a barrier and facilitator. CONCLUSIONS: Home-based exercise prehabilitation is feasible and acceptable to older people with frailty preparing for cancer surgery. Participants identified that a home-based program was manageable, easy to follow with helpful resources, included valuable support from the research team, and they reported self-perceived health benefits and a sense of control over their health. Future studies and implementation should consider increased personalization based on health and fitness, psychosocial support and modifications to aerobic exercises in response to adverse weather conditions.

Joint behaviour during arm swing changes with gait speed and predicts spatiotemporal variability and dynamic stability in healthy young adults.

BACKGROUND: Arm swing is linked to gait stability. How this is accomplished is unclear as most investigations artificially manipulate arm swing amplitude and examine average patterns. Biomechanical evaluation of stride-to-stride upper limb behaviour across a range of gait speeds, where the arm swings as preferred, could clarify this link. RESEARCH QUESTION: How do stride-to-stride arm swing behaviours change with gait speed and relate to stride-to-stride gait fluctuations? METHODS: Young adults (n = 45, 25 females) completed treadmill gait at preferred, slow (70% of preferred), and fast speed (130% of preferred) while full-body kinematics were acquired with optoelectronic motion capture. Arm swing behaviour was quantified by shoulder, elbow, and wrist joint angle amplitude (range of motion [ROM]) and motor variability (e.g. mean standard deviation [meanSD], local divergence exponent [λmax]). Stride-to-stride gait fluctuation was quantified by spatiotemporal variability (e.g. stride time CV) and dynamic stability (i.e. trunk local dynamic stability [trunk λmax], centre-of-mass smoothness [COM HR]). Repeated measures ANOVAs tested for speed effects and step-wise linear regressions identified arm swing-based predictors of stride-to-stride gait fluctuation. RESULTS: Speed decreased spatiotemporal variability and increased trunk λmax and COM HR in the anteroposterior and vertical axes. Adjustments in gait fluctuations occurred with increased upper limb ROM, particularly for elbow flexion, and increased meanSD and λmax of shoulder, elbow, and wrist angles. Models of upper limb measures predicted 49.9-55.5% of spatiotemporal variability and 17.7-46.4% of dynamic stability. For dynamic stability, wrist angle features were the best and most common independent predictors. SIGNIFICANCE: Findings highlight that all upper limb joints, and not solely the shoulder, underlie changes in arm swing amplitude, and that arm swing strategies pair with the trunk and contrast with centre-of-mass and stride strategies. Findings suggest that young adults search for flexible arm swing motor strategies to help optimize stride consistency and gait smoothness.

Transcranial Direct Current Stimulation Over Motor Areas Improves Reaction Time in Parkinson's Disease.

Background: Transcranial direct current stimulation (tDCS) has been shown to modulate cortical motor excitability and improve bradykinesia symptoms in Parkinson's disease. It is unclear how targeting different cortical motor areas with tDCS may differentially influence upper limb function for individuals diagnosed with PD. Objective: This study investigated whether anodal tDCS applied separately to the primary motor cortex and the supplementary motor area would improve upper limb function for individuals with Parkinson's disease. In addition, a startling acoustic stimulus was used to differentiate between the effect of stimulation on motor preparatory and initiation processes associated with upper limb movements. Methods: Eleven participants with idiopathic Parkinson's disease performed two upper limb simple reaction time tasks, involving elbow extension or a button press before and after either anodal tDCS or sham tDCS was applied over the primary motor cortex or supplementary motor area. A loud, startling stimulus was presented on a selection of trials to involuntarily trigger the prepared action. Results: Anodal tDCS led to improved premotor reaction time in both tasks, but this was moderated by reaction time in pre-tDCS testing, such that individuals with slower pre-tDCS reaction time showed the greatest reaction time improvements. Startle-trial reaction time was not modified following tDCS, suggesting that the stimulation primarily modulated response initiation processes. Conclusion: Anodal tDCS improved response initiation speed, but only in slower reacting individuals with PD. However, no differences attributable to tDCS were observed in clinical measures of bradykinesia or kinematic variables, suggesting that reaction time may represent a more sensitive measure of some components of bradykinesia.

Prediction of Freezing of Gait in Parkinson's Disease Using Unilateral and Bilateral Plantar-Pressure Data.

Background: Freezing of gait (FOG) is an intermittent walking disturbance experienced by people with Parkinson's disease (PD). FOG has been linked to falling, injury, and overall reduced mobility. Wearable sensor-based devices can detect freezes already in progress and provide a cue to help the person resume walking. While this is helpful, predicting FOG episodes before onset and providing a timely cue may prevent the freeze from occurring. Wearable sensors mounted on various body parts have been used to develop FOG prediction systems. Despite the known asymmetry of PD motor symptom manifestation, the difference between the most affected side (MAS) and least affected side (LAS) is rarely considered in FOG detection and prediction studies. Methods: To examine the effect of using data from the MAS, LAS, or both limbs for FOG prediction, plantar pressure data were collected during a series of walking trials and used to extract time and frequency-based features. Three datasets were created using plantar pressure data from the MAS, LAS, and both sides together. ReliefF feature selection was performed. FOG prediction models were trained using the top 5, 10, 15, 20, 25, or 30 features for each dataset. Results: The best models were the MAS model with 15 features and the LAS and bilateral models with 5 features. The LAS model had the highest sensitivity (79.5%) and identified the highest percentage of FOG episodes (94.9%). The MAS model achieved the highest specificity (84.9%) and lowest false positive rate (1.9 false positives/walking trial). Overall, the bilateral model was best with 77.3% sensitivity and 82.9% specificity. In addition, the bilateral model identified 94.2% of FOG episodes an average of 0.8 s before FOG onset. Compared to the bilateral model, the LAS model had a higher false positive rate; however, the bilateral and LAS models were similar in all the other evaluation metrics. Conclusion: The LAS model would have similar FOG prediction performance to the bilateral model at the cost of slightly more false positives. Given the advantages of single sensor systems, the increased false positive rate may be acceptable to people with PD. Therefore, a single plantar pressure sensor placed on the LAS could be used to develop a FOG prediction system and produce performance similar to a bilateral system.

Home-based prehabilitation with exercise to improve postoperative recovery for older adults with frailty having cancer surgery: the PREHAB randomised clinical trial.

BACKGROUND: Frailty is a state of vulnerability as a result of decreased reserves. Prehabilitation may increase reserve and improve postoperative outcomes. Our objective was to determine if home-based prehabilitation improves postoperative functional recovery in older adults with frailty having cancer surgery. METHODS: This double blind randomised trial enrolled people ≥60 yr having elective cancer surgery and ≥3 weeks from enrolment to surgery as eligible. Participation in a remotely supported, home-based exercise prehabilitation program plus nutritional guidance was compared with standard care plus written advice on age-appropriate activity and nutrition. The primary outcome was 6-min walk test (6MWT) distance at the first postoperative clinic visit. Secondary outcomes included physical performance, quality of life, disability, length of stay, non-home discharge, and 30-day readmission. RESULTS: Of 543 patients assessed, 254 were eligible and 204 (80%) were randomised (102 per arm); 182 (94 intervention and 88 control) had surgery and were analysed. Mean age was 74 yr and 57% were female. Mean duration of participation was 5 weeks, mean adherence was 61% (range 0%-100%). We found no significant difference in 6MWT at follow-up (+14 m, 95% confidence interval -26-55 m, P=0.486), or for secondary outcomes. Analyses using a prespecified adherence definition of ≥80% supported improvements in 6MWT distance, complication count, and disability. CONCLUSIONS: A home-based prehabilitation program did not significantly improve postoperative recovery or other outcomes in older adults with frailty having cancer surgery. Program adherence may be a key mediator of prehabilitation efficacy. CLINICAL TRIAL REGISTRATION: NCT02934230.

Sensitivity of discrete symmetry metrics: Implications for metric choice.

Gait asymmetry is present in several pathological populations, including those with Parkinson's disease, Huntington's disease, and stroke survivors. Previous studies suggest that commonly used discrete symmetry metrics, which compare single bilateral variables, may not be equally sensitive to underlying effects of asymmetry, and the use of a metric with low sensitivity could result in unnecessarily low statistical power. The purpose of this study was to provide a comprehensive assessment of the sensitivity of commonly used discrete symmetry metrics to better inform design of future studies. Monte Carlo simulations were used to estimate the statistical power of each symmetry metric at a range of asymmetry magnitudes, group/condition variabilities, and sample sizes. Power was estimated by repeated comparison of simulated symmetric and asymmetric data with a paired t-test, where the proportion of significant results is equivalent to the power. Simulation results confirmed that not all common discrete symmetry metrics are equally sensitive to reference effects of asymmetry. Multiple symmetry metrics exhibit equivalent sensitivities, but the most sensitive discrete symmetry metric in all cases is a bilateral difference (e.g. left-right). A ratio (e.g. left/right) has poor sensitivity when group/condition variability is not small, but a log-transformation produces increased sensitivity. Additionally, two metrics which included an absolute value in their definitions showed increased sensitivity when the absolute value was removed. Future studies should consider metric sensitivity when designing analyses to reduce the possibility of underpowered research.

Boxing with Parkinson's Disease: findings from a qualitative study using self-determination theory.

PURPOSE: Adults with Parkinson's disease (PD) experience debilitating symptoms that may be mitigated by boxing. Yet, attrition from boxing programs is problematic. Understanding whether PD-specific boxing programs can enhance motivation to remain physically active is important. This study investigated adults' experiences within a PD-specific boxing program and explored their perspectives on how the program has influenced physical activity motivational processes using a self-determination theory (SDT) lens. METHODS: Nine adults with PD who took part in the Boxing 4 Health PD-specific boxing program completed face-to-face, semi-structured interviews. Data were analyzed using a hybrid approach of inductive and deductive thematic analysis. RESULTS: The analysis yielded five themes: (1) I made an informed decision to participate and it feels good, (2) Boxing helps me stay active and keep moving, (3) To keep me going, the boxing program needs to have variety and allow for input, (4) A program that can be adapted to me is important, and (5) The instructor and the group facilitate my continued participation in the program. CONCLUSION: Providing participants with adapted exercises, varied sessions, and opportunities to provide input in a group-based PD-specific boxing program may be conducive to enhancing motivation for physical activity. Further, SDT may be a useful theoretical framework for developing and evaluating PD-specific programs.IMPLICATIONS FOR REHABILITATIONAdults with Parkinson's disease (PD) have many reasons for not engaging in physical activity, including a lack of motivation.A group-based PD-specific boxing program may be conducive to increasing motivation for physical activity.Professionals should consider: (1) educating adults with PD on the benefits of boxing, (2) offering group-based PD-specific boxing programs that are adaptable, varied, and open to input, and (3) fostering social support and networking opportunities within such programs.

Effects of arm swing amplitude and lower limb asymmetry on motor variability patterns during treadmill gait.

Motor variability is a fundamental feature of gait. Altered arm swing and lower limb asymmetry (LLA) may be contributing factors having been shown to affect the magnitude and dynamics of variability in spatiotemporal and trunk motion. However, the effects on lower limb joints remain unclear. Full-body kinematics of 15 healthy young adults were recorded during treadmill walking using the Computer-Assisted Rehabilitation Environment system. Participants completed six trials, combining three arm swing (AS) amplitude (normal, active, held) and two LLA (symmetrical, asymmetrical) conditions. The mean standard deviation (meanSD), maximum Lyapunov exponent (λmax), detrended fluctuation analysis scaling exponent of range of motion (DFAα), and sample entropy (SaEn) were computed for tridimensional trunk, pelvis, and lower limb joint angles, and compared using repeated-measures ANOVAs. Relative to normal AS, active AS increased meanSD of all joint angles, λmax of frontal plane hip and ankle angles, and SaEn of sagittal plane ankle angles. Active AS, however, did not affect λmax or SaEn of trunk or pelvis angles. LLA increased meanSD of sagittal plane joint angles, λmax of Euclidean norm trunk angle and of lower limb joint angles, and SaEn of ankle dorsiflexion/ plantarflexion, but decreased SaEn of tridimensional trunk angles and hip rotation in the slower moving leg. Alterations in lower limb variability with active AS and LLA suggest that young adults actively exploit their lower limb redundancies to maintain gait. This appears to preserve trunk stability and regularity during active AS but not during LLA.

Increased Arm Swing and Rocky Surfaces Reduces Postural Control in Healthy Young Adults.

Fall-induced injuries can stem from a disruption in the postural control system and place a financial burden on the healthcare system. Most gait research focused on lower extremities and neglected the contribution of arm swing, which have been shown to affect the movement of the center of mass when walking. This study evaluated the effect of arm swing on postural control and stability during regular and rocky surface walking. Fifteen healthy young adults (age = 23.4 ± 2.8) walked on these two surfaces with three arm motions (normal, held, and active) using the CAREN Extended-System (Motek Medical, Amsterdam, NL). Mean, standard deviation and maximal values of trunk linear and angular velocity were calculated in all three axes. Moreover, step length, time and width mean and coefficient of variation as well as margin of stability mean and standard deviation were calculated. Active arm swing increased trunk linear and angular velocity variability and peak values compared to normal and held arm conditions. Active arm swing also increased participants' step length and step time, as well as the variability of margin of stability. Similarly, rocky surface walking increased trunk kinematics variability and peak values compared to regular surface walking. Furthermore, rocky surface increased the average step width while reducing the average step time. Though this surface type increased the coefficient of variation of all spatiotemporal parameters, rocky surface also led to increased margin of stability mean and variation. The spatiotemporal adaptations showed the use of "cautious" gait to mitigate the destabilizing effects of both the active arm swing and rocky surface walking and, ultimately, maintain dynamic stability.

Prediction and detection of freezing of gait in Parkinson's disease from plantar pressure data using long short-term memory neural-networks.

BACKGROUND: Freezing of gait (FOG) is a walking disturbance in advanced stage Parkinson's disease (PD) that has been associated with increased fall risk and decreased quality of life. Freezing episodes can be mitigated or prevented with external intervention such as visual or auditory cues, activated by FOG prediction and detection systems. While most research on FOG detection and prediction has been based on inertial measurement unit (IMU) and accelerometer data, plantar-pressure data may capture subtle weight shifts unique to FOG episodes. Different machine learning algorithms have been used for FOG detection and prediction; however, long short-term memory (LSTM) deep learning methods hold an advantage when dealing with time-series data, such as sensor data. This research aimed to determine if LSTM can be used to detect and predict FOG from plantar pressure data alone, specifically for use in a real-time wearable system. METHODS: Plantar pressure data were collected from pressure-sensing insole sensors worn by 11 participants with PD as they walked a predefined freeze-provoking path. FOG instances were labelled, 16 features were extracted, and the dataset was balanced and normalized (z-score). The resulting datasets were classified using long short-term memory neural-network models. Separate models were trained for detection and prediction. For prediction models, data before FOG were included in the target class. Leave-one-freezer-out cross validation was used for model evaluation. In addition, the models were tested on all non-freezer data to determine model specificity. RESULTS: The best FOG detection model had 82.1% (SD 6.2%) mean sensitivity and 89.5% (SD 3.6%) mean specificity for one-freezer-held-out cross validation. Specificity improved to 93.3% (SD 4.0%) when ignoring inactive state data (standing) and analyzing the model only on active states (turning and walking). The model correctly detected 95% of freeze episodes. The best FOG prediction method achieved 72.5% (SD 13.6%) mean sensitivity and 81.2% (SD 6.8%) mean specificity for one-freezer-held-out cross validation. CONCLUSIONS: Based on FOG data collected in a laboratory, the results suggest that plantar pressure data can be used for FOG detection and prediction. However, further research is required to improve FOG prediction performance, including training with a larger sample of people who experience FOG.

Validity and Sensitivity of an Inertial Measurement Unit-Driven Biomechanical Model of Motor Variability for Gait.

Motor variability in gait is frequently linked to fall risk, yet field-based biomechanical joint evaluations are scarce. We evaluated the validity and sensitivity of an inertial measurement unit (IMU)-driven biomechanical model of joint angle variability for gait. Fourteen healthy young adults completed seven-minute trials of treadmill gait at several speeds and arm swing amplitudes. Trunk, pelvis, and lower-limb joint kinematics were estimated by IMU- and optoelectronic-based models using OpenSim. We calculated range of motion (ROM), magnitude of variability (meanSD), local dynamic stability (λmax), persistence of ROM fluctuations (DFAα), and regularity (SaEn) of each angle over 200 continuous strides, and evaluated model accuracy (RMSD: root mean square difference), consistency (ICC2,1: intraclass correlation), biases, limits of agreement, and sensitivity to within-participant gait responses (effects of speed and swing). RMSDs of joint angles were 1.7-9.2° (pooled mean of 4.8°), excluding ankle inversion. ICCs were mostly good to excellent in the primary plane of motion for ROM and in all planes for meanSD and λmax, but were poor to moderate for DFAα and SaEn. Modelled speed and swing responses for ROM, meanSD, and λmax were similar. Results suggest that the IMU-driven model is valid and sensitive for field-based assessments of joint angle time series, ROM in the primary plane of motion, magnitude of variability, and local dynamic stability.

Grouping successive freezing of gait episodes has neutral to detrimental effect on freeze detection and prediction in Parkinson's disease.

Freezing of gait (FOG) is an intermittent walking disturbance experienced by people with Parkinson's disease (PD). Wearable FOG identification systems can improve gait and reduce the risk of falling due to FOG by detecting FOG in real-time and providing a cue to reduce freeze duration. However, FOG prediction and prevention is desirable. Datasets used to train machine learning models often generate ground truth FOG labels based on visual observation of specific lower limb movements (event-based definition) or an overall inability to walk effectively (period of gait disruption based definition). FOG definition ambiguity may affect model performance, especially with respect to multiple FOG in rapid succession. This research examined whether merging multiple freezes that occurred in rapid succession could improve FOG detection and prediction model performance. Plantar pressure and lower limb acceleration data were used to extract a feature set and train decision tree ensembles. FOG was labeled using an event-based definition. Additional datasets were then produced by merging FOG that occurred in rapid succession. A merging threshold was introduced where FOG that were separated by less than the merging threshold were merged into one episode. FOG detection and prediction models were trained for merging thresholds of 0, 1, 2, and 3 s. Merging slightly improved FOG detection model performance; however, for the prediction model, merging resulted in slightly later FOG identification and lower precision. FOG prediction models may benefit from using event-based FOG definitions and avoiding merging multiple FOG in rapid succession.

Transcranial direct current stimulation of supplementary motor area improves upper limb kinematics in Parkinson's disease.

OBJECTIVE: Bradykinesia, defined as slowness of movements, is among the most functionally debilitating symptoms of Parkinson's disease (PD). Hypoactivation of cortical neurons in supplementary motor area (SMA) has been linked to the progression of bradykinesia symptoms. This study investigated the influence of transcranial direct current stimulation (tDCS) applied over SMA on upper limb movement for individuals diagnosed with PD. METHODS: Thirteen individuals with PD performed a simple reaction time (RT) task involving elbow extension following an auditory go-signal. Sham or anodal tDCS was then applied over SMA for 10 minutes before participants repeated the simple RT task. Participants were unaware of which stimulation they received in each testing session. Electromyography (EMG) and kinematic data were recorded on all trials. RESULTS: While there were no significant differences in premotor RT, anodal tDCS applied over SMA led to significantly shorter time to peak displacement (p = .015) and movement time (p = .003) compared to pre-tDCS trials, whereas sham stimulation had no impact on these variables. CONCLUSIONS: These results provide evidence that anodal tDCS applied over SMA contributes to improvements in movement kinematics of an upper limb simple RT task. SIGNIFICANCE: Anodal tDCS over SMA could be a useful therapy to mitigate bradykinesia associated with PD.

Early Detection of Freezing of Gait during Walking Using Inertial Measurement Unit and Plantar Pressure Distribution Data.

Freezing of gait (FOG) is a sudden and highly disruptive gait dysfunction that appears in mid to late-stage Parkinson's disease (PD) and can lead to falling and injury. A system that predicts freezing before it occurs or detects freezing immediately after onset would generate an opportunity for FOG prevention or mitigation and thus enhance safe mobility and quality of life. This research used accelerometer, gyroscope, and plantar pressure sensors to extract 861 features from walking data collected from 11 people with FOG. Minimum-redundancy maximum-relevance and Relief-F feature selection were performed prior to training boosted ensembles of decision trees. The binary classification models identified Total-FOG or No FOG states, wherein the Total-FOG class included data windows from 2 s before the FOG onset until the end of the FOG episode. Three feature sets were compared: plantar pressure, inertial measurement unit (IMU), and both plantar pressure and IMU features. The plantar-pressure-only model had the greatest sensitivity and the IMU-only model had the greatest specificity. The best overall model used the combination of plantar pressure and IMU features, achieving 76.4% sensitivity and 86.2% specificity. Next, the Total-FOG class components were evaluated individually (i.e., Pre-FOG windows, Freeze windows, transition windows between Pre-FOG and Freeze). The best model detected windows that contained both Pre-FOG and FOG data with 85.2% sensitivity, which is equivalent to detecting FOG less than 1 s after the freeze began. Windows of FOG data were detected with 93.4% sensitivity. The IMU and plantar pressure feature-based model slightly outperformed models that used data from a single sensor type. The model achieved early detection by identifying the transition from Pre-FOG to FOG while maintaining excellent FOG detection performance (93.4% sensitivity). Therefore, if used as part of an intelligent, real-time FOG identification and cueing system, even if the Pre-FOG state were missed, the model would perform well as a freeze detection and cueing system that could improve the mobility and independence of people with PD during their daily activities.

Recovery of dynamic stability during slips unaffected by arm swing in people with Parkinson's Disease.

The arm elevation strategy assists in recovering stability during slips in healthy young and elderly individuals. However, in people with Parkinson's Disease, one of the main motor symptoms affecting the upper limbs is reduced arm swing which intensifies throughout the course of the disease before becoming absent. This holds direct implications for these individuals when encountering slips as the arm elevation strategy is an integral component in the interlimb slip response to restore stability. Arm swing's effect in recovering from slips in people with Parkinson's Disease though remains unexamined. Twenty people with Parkinson's Disease (63.78 ± 8.97 years) walked with restricted and unrestricted arm swing conditions on a dual-belt treadmill where slips were induced on the least and most affected sides. Data were collected on the CAREN Extended System (Motek Medical, Amsterdam, NL). The Margin of Stability, linear and angular trunk velocities, as well as step length, time, and width were calculated. Data were examined during the slipped step and recovery step. The restricted arm swing condition, compared to unrestricted, caused a faster step time during the slipped step. Compared to the most affected leg, the least affected had a wider step width during the slipped step. During the recovery step, the least affected leg had a larger anteroposterior Margin of Stability and longer step time than the most affected. No differences between our arm swing conditions suggests that the normal arm swing in our participants was not more effective at restoring stability after an induced slip compared to when their arm motion was restricted. This may be due to the arm elevation strategy being ineffective in counteracting the slip's backward destabilization in these individuals. Differences between the legs revealed that our participants were asymmetrically impaired in their slip recovery response.

Regularity of kinematic data between single and dual-task treadmill walking in people with Parkinson's disease.

BACKGROUND: Regularity, quantified by sample entropy (SampEn), has been extensively used as a gait stability measure. Yet, there is no consensus on the calculation process and variant approaches, e.g. single-scale SampEn with and without incorporating a time delay greater than one, multiscale SampEn, and complexity index, have been used to calculate the regularity of kinematic or kinetic signals. The aim of the present study was to test the discriminatory performance of the abovementioned approaches during single and dual-task walking in people with Parkinson's disease (PD). METHODS: Seventeen individuals with PD were included in this study. Participants completed two walking trials that included single and dual-task conditions. The secondary task was word searching with twelve words randomly appearing in the participants' visual field. Trunk linear acceleration at sternum level, linear acceleration of the center of gravity, and angular velocity of feet, shanks, and thighs, each in three planes of motion were collected. The regularity of signals was computed using approaches mentioned above for single and dual-task conditions. RESULTS: Incorporating a time delay greater than one and considering multiple scales helped better distinguish between single and dual-task walking. For all signals, the complexity index, defined as the summary of multiscale SampEn analysis, was the most efficient discriminatory index between single-task walking and dual-tasking in people with Parkinson's disease. Specifically, the complexity index of the trunk linear acceleration of the center of gravity distinguished between the two walking conditions in all three planes of motion. CONCLUSIONS: The significant results observed across the 24 signals studied in this study are illustrative examples of the complexity index's potential as a gait feature for classifying different walking conditions.

Walking on Mild Slopes and Altering Arm Swing Each Induce Specific Strategies in Healthy Young Adults.

Slopes are present in everyday environments and require specific postural strategies for successful navigation; different arm strategies may be used to manage external perturbations while walking. It has yet to be determined what impact arm swing has on postural strategies and gait stability during sloped walking. We investigated the potentially interacting effects of surface slope and arm motion on gait stability and postural strategies in healthy young adults. We tested 15 healthy adults, using the CAREN-Extended system to simulate a rolling-hills environment which imparted both incline (uphill) and decline (downhill) slopes (± 3°). This protocol was completed under three imposed arm swing conditions: held, normal, active. Spatiotemporal gait parameters, mediolateral margin of stability, and postural kinematics in anteroposterior (AP), mediolateral (ML), and vertical (VT) directions were assessed. Main effects of conditions and interactions were evaluated by 2-way repeated measures analysis of variance. Our results showed no interactions between arm swing and slope; however, we found main effects of arm swing and main effects of slope. As expected, uphill and downhill sections of the rolling-hills yielded opposite stepping and postural strategies compared to level walking, and active and held arm swings led to opposite postural strategies compared to normal arm swing. Arm swing effects were consistent across slope conditions. Walking with arms held decreased gait speed, indicating a level of caution, but maintained stability comparable to that of walking with normal arm swing. Active arm swing increased both step width variability and ML-MoS during downhill sections. Alternately, ML-MoS was larger with increased step width and double support time during uphill sections compared to level, which demonstrates that distinct base of support strategies are used to manage arm swing compared to slope. The variability of the rolling-hills also required proactive base of support changes despite the mild slopes to maintain balance.

Prediction of Freezing of Gait in Parkinson's Disease from Foot Plantar-Pressure Arrays using a Convolutional Neural Network.

Freezing of gait (FOG) is a sudden cessation of locomotion in advanced Parkinson's disease (PD). A FOG episode can lead to falls, decreased mobility, and decreased overall quality of life. Prediction of FOG episodes provides an opportunity for intervention and freeze prevention. A novel method of FOG prediction that uses foot plantar pressure data acquired during gait was developed and evaluated, with plantar pressure data treated as 2D images and classified using a convolutional neural network (CNN). Data from five people with PD and a history of FOG were collected during walking trials. FOG instances were identified and data preceding each freeze were labeled as Pre-FOG. Left and right foot FScan pressure frames were concatenated into a single 60x42 pressure array. Each frame was considered as an independent image and classified as Pre-FOG, FOG, or Non-FOG, using the CNN. From prediction models using different Pre-FOG durations, shorter Pre-FOG durations performed best, with Pre-FOG class sensitivity 94.3%, and specificity 95.1%. These results demonstrated that foot pressure distribution alone can be a good FOG predictor when treating each plantar pressure frame as a 2D image, and classifying the images using a CNN. Furthermore, the CNN eliminated the need for feature extraction and selection.Clinical Relevance- This research demonstrated that foot plantar pressure data can be used to predict freezing of gait occurrence, using a convolutional neural network deep learning technique. This had the added advantage of eliminating the need for feature extraction and selection.