Auditory Cue Effects on Gait-Phase-Dependent Electroencephalogram (EEG) Modulations during Overground and Treadmill Walking.

Walking rehabilitation following injury or disease involves voluntary gait modification, yet the specific brain signals underlying this process remains unclear. This aim of this study was to investigate the impact of an auditory cue on changes in brain activity when walking overground (O) and on a treadmill (T) using an electroencephalogram (EEG) with a 32-electrode montage. Employing a between-group repeated-measures design, 24 participants (age: 25.7 ± 3.8 years) were randomly allocated to either an O (n = 12) or T (n = 12) group to complete two walking conditions (self-selected speed control (sSC) and speed control (SC)). The differences in brain activities during the gait cycle were investigated using statistical non-parametric mapping (SnPM). The addition of an auditory cue did not modify cortical activity in any brain area during the gait cycle when walking overground (all p > 0.05). However, significant differences in EEG activity were observed in the delta frequency band (0.5-4 Hz) within the sSC condition between the O and T groups. These differences occurred at the central frontal (loading phase) and frontocentral (mid stance phase) brain areas (p < 0.05). Our data suggest auditory cueing has little impact on modifying cortical activity during overground walking. This may have practical implications in neuroprosthesis development for walking rehabilitation, sports performance optimization, and overall human quality-of-life improvement.

Gait Event Detection and Travel Distance Using Waist-Worn Accelerometers across a Range of Speeds: Automated Approach.

Estimation of temporospatial clinical features of gait (CFs), such as step count and length, step duration, step frequency, gait speed, and distance traveled, is an important component of community-based mobility evaluation using wearable accelerometers. However, accurate unsupervised computerized measurement of CFs of individuals with Duchenne muscular dystrophy (DMD) who have progressive loss of ambulatory mobility is difficult due to differences in patterns and magnitudes of acceleration across their range of attainable gait velocities. This paper proposes a novel calibration method. It aims to detect steps, estimate stride lengths, and determine travel distance. The approach involves a combination of clinical observation, machine-learning-based step detection, and regression-based stride length prediction. The method demonstrates high accuracy in children with DMD and typically developing controls (TDs) regardless of the participant's level of ability. Fifteen children with DMD and fifteen TDs underwent supervised clinical testing across a range of gait speeds using 10 m or 25 m run/walk (10 MRW, 25 MRW), 100 m run/walk (100 MRW), 6-min walk (6 MWT), and free-walk (FW) evaluations while wearing a mobile-phone-based accelerometer at the waist near the body's center of mass. Following calibration by a trained clinical evaluator, CFs were extracted from the accelerometer data using a multi-step machine-learning-based process and the results were compared to ground-truth observation data. Model predictions vs. observed values for step counts, distance traveled, and step length showed a strong correlation (Pearson's r = -0.9929 to 0.9986, p < 0.0001). The estimates demonstrated a mean (SD) percentage error of 1.49% (7.04%) for step counts, 1.18% (9.91%) for distance traveled, and 0.37% (7.52%) for step length compared to ground-truth observations for the combined 6 MWT, 100 MRW, and FW tasks. Our study findings indicate that a single waist-worn accelerometer calibrated to an individual's stride characteristics using our methods accurately measures CFs and estimates travel distances across a common range of gait speeds in both DMD and TD peers.

Motion Planning for a Legged Robot with Dynamic Characteristics.

Legged soccer robots present a significant challenge in robotics owing to the need for seamless integration of perception, manipulation, and dynamic movement. While existing models often depend on external perception or static techniques, our study aims to develop a robot with dynamic and untethered capabilities. We have introduced a motion planner that allows the robot to excel in dynamic shooting and dribbling. Initially, it identifies and predicts the position of the ball using a rolling model. The robot then pursues the ball, using a novel optimization-based cycle planner, continuously adjusting its gait cycle. This enables the robot to kick without stopping its forward motion near the ball. Each leg is assigned a specific role (stance, swing, pre-kick, or kick), as determined by a gait scheduler. Different leg controllers were used for tailored tiptoe trajectory planning and control. We validated our approach using real-world penalty shot experiments (5 out of 12 successful), cycle adjustment tests (11 out of 12 successful), and dynamic dribbling assessments. The results demonstrate that legged robots can overcome onboard capability limitations and achieve dynamic mobility and manipulation.

Gait Characterization in Duchenne Muscular Dystrophy (DMD) Using a Single-Sensor Accelerometer: Classical Machine Learning and Deep Learning Approaches.

Differences in gait patterns of children with Duchenne muscular dystrophy (DMD) and typically developing (TD) peers are visible to the eye, but quantifications of those differences outside of the gait laboratory have been elusive. In this work, we measured vertical, mediolateral, and anteroposterior acceleration using a waist-worn iPhone accelerometer during ambulation across a typical range of velocities. Fifteen TD and fifteen DMD children from 3 to 16 years of age underwent eight walking/running activities, including five 25 m walk/run speed-calibration tests at a slow walk to running speeds (SC-L1 to SC-L5), a 6-min walk test (6MWT), a 100 m fast walk/jog/run (100MRW), and a free walk (FW). For clinical anchoring purposes, participants completed a Northstar Ambulatory Assessment (NSAA). We extracted temporospatial gait clinical features (CFs) and applied multiple machine learning (ML) approaches to differentiate between DMD and TD children using extracted temporospatial gait CFs and raw data. Extracted temporospatial gait CFs showed reduced step length and a greater mediolateral component of total power (TP) consistent with shorter strides and Trendelenberg-like gait commonly observed in DMD. ML approaches using temporospatial gait CFs and raw data varied in effectiveness at differentiating between DMD and TD controls at different speeds, with an accuracy of up to 100%. We demonstrate that by using ML with accelerometer data from a consumer-grade smartphone, we can capture DMD-associated gait characteristics in toddlers to teens.

The knee kinematic patterns and associated factors in healthy Thai adults.

BACKGROUND: Reference values for normal knee kinematics were limited in Asian population and were influenced by race and other factors. This study was aimed to establish the reference values and identify the factors associated with knee kinematics in healthy Thai adults, aged 18-40 years. METHODS: A retrospective cohort study was conducted between 2016 and 2020. Healthy Thai adults aged 18-40 years old with body mass index (BMI) between 18.5 and 24.9 kg/m2 were included. All eligible participants were attached with reflective markers. Their walking was captured by 8-digital cameras, and assessed by motion analysis software. The primary outcomes were average knee kinematic data (degrees) in three dimensional planes as valgus-varus, flexion-extension, and internal-external rotation. Paired t-test and multiple linear regression were applied to compare the outcomes and to determine their associated factors. RESULTS: Ninety-eight participants (60 females and 38 males) were included with mean age 28.5 ± 5.4 years, and BMI 21.1 ± 2.0 kg/m2. Knee kinematics showed slight adduction during the swing phase, flexion during the stance phase, and obvious external rotation throughout the gait cycle, with a peak of 30-31 degrees during mid-swing. Right knee was significantly more adducted, flexed and externally rotated than the left side, particularly at mid-stance (P = 0.047, 0.017, and < 0.001, respectively). Females had more knee abduction, flexion and external rotation than males. Age, sex, and BMI were significantly correlated with knee abduction at terminal stance (correlation coefficient - 0.12, 95% confidence interval (CI) -0.23, -0.01; -1.37, 95%CI -2.54, -0.20; and - 0.32, 95%CI -0.61, -0.39, respectively), and rotation at mid-swing (correlation coefficient - 0.36, 95%CI -0.69, -0.02; -7.37, 95%CI -10.82, -3.92; and 0.89, 95%CI 0.01, 1.78, respectively). CONCLUSION: Knee kinematics demonstrates external tibial rotation throughout the gait cycle, significant side differences, and are associated with age, sex, and BMI. Reference values from this study will be useful for functional gait assessment in healthy Thais. However, further comprehensive knee kinetic study including spatio-temporal parameter is recommended.

Evaluation of Gait Parameters on Subjects with Hallux Limitus Using an Optogait Sensor System: A Case-Control Study.

Background and Objetives: The foot is a part of the body's kinetic chain and needs to be efficient during the entire gait cycle. Electronic Sensor Gait analysis is useful and an important tool within the area of podiatry to assess the physical state of patients that helps the comprehensive intervention in situations where the daily activity is limited. The aim of this research is to evaluate if the presence of a hallux limitus (HL) can alter gait space-time parameters and consequently can affect the take-off phase of the gait and the limitation of the range of motion (ROM) of the hallux. Materials and Methods: A case-control study was designed to verify whether there are alterations in the spatiotemporal parameters of the gait cycle between subjects with structural HL compared to the group of subjects with a normal hallux range. A total of n = 138 participants, cases (68 HL subjects) and healthy controls (70 subjects) were studied using an OptoGait LED sensor system to identify gait imbalances using OptoGait photocell gait analysis sensors. Results: Significant differences were found between the two groups with respect to stride length, gait cycle duration in seconds (for both feet) and for total stride and load response (p < 0.05). Conclusions: The limitation of the Hallux ROM may alter the normal gait patterns measured with an Optogait system. The early identification and treatment of gait disturbances due to HL are important to achieve normal gait physical activity to maintain a healthy lifestyle.

Stress distribution patterns during the gait cycle in patients with anterior femoral notching following total knee replacement.

BACKGROUND: Anterior femoral notching (AFN) is a severe complication of total knee replacement (TKR), which in a percentage of patients may lead to fractures after surgery. The purpose of this study was to investigate the stress distribution in patients with AFN and the safety depth of AFN during the gait cycle. METHODS: We performed a finite element (FE) analysis to analyse the mechanics around the femur during the gait cycle in patients with AFN. An adult volunteer was selected as the basis of the model. The TKR models were established in the 3D reconstruction software to simulate the AFN model during the TKR process, and the 1 mm, 2 mm, 3 mm, 4 mm, and 5 mm AFN models were established, after which the prosthesis was assembled. Three key points of the gait cycle (0°, 22°, and 48°) were selected for the analysis. RESULTS: The stress on each osteotomy surface was stable in the 0° phase. In the 22° phase, the maximum equivalent stress at 3 mm was observed. In the 48° phase, with the increase in notch depth, each osteotomy surface showed an overall increasing trend, the stress range was more extended, and the stress was more concentrated. Moreover, the maximum equivalent force value (158.3 MPa) exceeded the yield strength (115.1 MPa) of the femur when the depth of the notch was ≥ 3 mm. CONCLUSIONS: During the gait cycle, if there is an anterior femoral cortical notch ≥ 3 mm, the stress will be significantly increased, especially at 22° and 48°. The maximum equivalent stress exceeded the femoral yield strength and may increase the risk of periprosthetic fractures.

Biomechanical assessment of disease outcome in surgical interventions for medial meniscal posterior root tears: a finite element analysis.

BACKGROUND: The adverse consequences of medial meniscus posterior root tears have become increasingly familiar to surgeons, and treatment strategies have become increasingly abundant. In this paper, the finite element gait analysis method was used to explore the differences in the biomechanical characteristics of the knee joint under different conditions. METHODS: Based on CT computed tomography and MR images, (I) an intact knee (IK) model with bone, cartilage, meniscus and main ligaments was established. Based on this model, the posterior root of the medial meniscus was resected, and (ii) the partial tear (PT) model, (iii) the entire radial tear (ERT) model, and (iv) the entire oblique tear (EOT) model were established according to the scope and degree of resection. Then, the (v) meniscus repair (MR) model and (vi) partial meniscectomy (PM) model were developed according to the operation method. The differences in stress, displacement and contact area among different models were evaluated under ISO gait loading conditions. RESULTS: Under gait loading, there was no significant difference in the maximum stress of the medial and lateral tibiofemoral joints among the six models. Compared with the medial tibiofemoral joint stress of the IK model, the stress of the PM model increased by 8.3%, while that of the MR model decreased by 18.9%; at the same time, the contact stress of the medial tibiofemoral joint of the ERT and EOT models increased by 17.9 and 25.3%, respectively. The displacement of the medial meniscus in the ERT and EOT models was significantly larger than that in the IK model (P < 0.05), and the tibial and femoral contact areas of these two models were lower than those of the IK model (P < 0.05). CONCLUSIONS: The integrity of the posterior root of the medial meniscus plays an important role in maintaining normal tibial-femoral joint contact mechanics. Partial meniscectomy is not beneficial for improving the tibial-thigh contact situation. Meniscal repair has a positive effect on restoring the normal biomechanical properties of the medial meniscus.

Temporal Synergies Detection in Gait Cyclograms Using Wearable Technology.

The human gait can be described as the synergistic activity of all individual components of the sensory-motor system. The central nervous system (CNS) develops synergies to execute endpoint motion by coordinating muscle activity to reflect the global goals of the endpoint trajectory. This paper proposes a new method for assessing temporal dynamic synergies. Principal component analysis (PCA) has been applied on the signals acquired by wearable sensors (inertial measurement units, IMU and ground reaction force sensors, GRF mounted on feet) to detect temporal synergies in the space of two-dimensional PCA cyclograms. The temporal synergy results for different gait speeds in healthy subjects and stroke patients before and after the therapy were compared. The hypothesis of invariant temporal synergies at different gait velocities was statistically confirmed, without the need to record and analyze muscle activity. A significant difference in temporal synergies was noticed in hemiplegic gait compared to healthy gait. Finally, the proposed PCA-based cyclogram method provided the therapy follow-up information about paretic leg gait in stroke patients that was not available by observing conventional parameters, such as temporal and symmetry gait measures.

Comparing Loose Clothing-Mounted Sensors with Body-Mounted Sensors in the Analysis of Walking.

A person's walking pattern can reveal important information about their health. Mounting multiple sensors onto loose clothing potentially offers a comfortable way of collecting data about walking and other human movement. This research investigates how well the data from three sensors mounted on the lateral side of clothing (on a pair of trousers near the waist, upper thigh and lower shank) correlate with the data from sensors mounted on the frontal side of the body. Data collected from three participants (two male, one female) for two days were analysed. Gait cycles were extracted based on features in the lower-shank accelerometry and analysed in terms of sensor-to-vertical angles (SVA). The correlations in SVA between the clothing- and body-mounted sensor pairs were analysed. Correlation coefficients above 0.76 were found for the waist sensor pairs, while the thigh and lower-shank sensor pairs had correlations above 0.90. The cyclical nature of gait cycles was evident in the clothing data, and it was possible to distinguish the stance and swing phases of walking based on features in the clothing data. Furthermore, simultaneously recording data from the waist, thigh, and shank was helpful in capturing the movement of the whole leg.

Measuring Gait Parameters from Structural Vibrations.

Measuring gait parameters (e.g. speed, cadence, step duration) accurately is invaluable for evaluation during treatment of older adults who struggle with disability onset, disease progression, balance, and injurious falls. Traditionally stopwatches or timing gates are used to measure gait speed in clinical settings, and these are limited to measuring gait speed. Other wearable and non-wearable technologies offer the ability to measure additional gait parameters though patients are known to walk differently with the devices and even tend to slow down before engaging with a non-wearable such as a floor mat. Floor vibrations are a promising option to measuring gait parameters while not being intrusive and not requiring line-of-sight to the patient for measurements. This paper presents methodology for extracting gait parameters using vibrations with comparisons to APDM Wearable Technologies Mobility Lab sensors and stopwatch measurements. Performance is examined across 97 participants for self-selected speed forward, full speed forward, and backwards walks at three different testing sites for a total of 1039 walks. Gait speed vibrations measurements demonstrated excellent reliability with APDM Mobility Lab (ICC: 0.98; 99% CI: 0.01±0.01 m/s) and stopwatch (ICC: 0.97; 99% CI: -0.01±0.01 m/s) measurements. Similar excellent results are reported for cadence, gait cycle duration, step duration, and stride length parameters.

Gait cycle time variability in patients with knee osteoarthritis and its possible associating factors.

[Purpose] Knee osteoarthritis can alter gait variability; however, few studies have investigated the associating factors with gait cycle time variability. The first objective was to compare gait cycle variability between female patients with knee osteoarthritis and healthy elderly females and to determine gait characteristics in patients with knee osteoarthritis. The second objective was to identify the associating factors with gait cycle time variability. [Participants and Methods] The participants included 24 female patients diagnosed with knee osteoarthritis and 12 healthy elderly females. Gait cycle variability (coefficient of variation of gait cycle time), knee extension range of motion, knee extension strength, 5-m walk test, Timed Up & Go Test, and Western Ontario and McMaster Universities Osteoarthritis Index were measured. All assessment results were compared between the knee osteoarthritis and healthy groups. [Results] Gait cycle time variability was significantly higher in the knee osteoarthritis group than in the healthy group. Further, it showed a significant positive correlation with the 5-m walk test and the Western Ontario and McMaster Universities Osteoarthritis Index. [Conclusion] Patients with knee osteoarthritis presented greater gait cycle variability than that of healthy individuals. Therefore, rehabilitation to improve gait variability might enhance the quality of life of patients with knee osteoarthritis.

The effects of cognitive tasks on the frequency of non-MTC gait cycle during walking in healthy older and young adults.

[Purpose] To investigate the effects of cognitive tasks on the non-minimum toe clearance gait cycles (nMTC) frequency during walking in healthy older and young adults. [Participants and Methods] This study included 20 healthy older and 20 young adults. The participants performed 3 min preferred-speed walking under a single-task and three dual-tasks (DTs) consisting of verbal, subtraction, and recall tasks. We determined the nMTC, which could not detect a trough in the toe trajectory during the swing phase. We evaluated the nMTC frequency (the cases of nMTC / total gait cycles) and compared them among the tasks and between groups. [Results] The results of the two-way analysis of variance revealed that there were no differences among the tasks, while the nMTC frequency in the older group was higher than that in the young group. The DT cost (DTc), which was used as an indicator of cognitive-motor interference (CMI), was higher in the subtraction and recall tasks in the older group than those in the young group. [Conclusion] This study showed that adding a cognitive task while walking increased in the nMTC frequency in older adults. These results suggest that the nMTC frequency under DT would reflect the increased CMI in healthy older adults.

Description of spine motion during gait in normal adolescents and young adults.

INTRODUCTION: Standing radiographs allow analysis of spinal segments and their relative positioning. However, it requires a specific positioning influencing spinal alignment. Knowledge of trunk movements when walking is therefore an essential step to evaluate dynamic sagittal balance. Our objective was to define spinal junction kinematics and their correlations during gait in a healthy population. METHOD: This is a prospective, single-center study. Between 2015 and 2017, 25 healthy volunteers were included. The measurements were taken in a motion analysis laboratory. Several kinematic parameters were studied, including spinal junction movements in the three planes and dynamic sagittal vertical axis (Dyn-SVA). Pearson correlation coefficients were calculated to determine the interactions between the spinal junctions. RESULTS: In the sagittal plane, the average amplitude of variation of the dyn-SVA was 25.5 cm (SD = 8.9). The average range of motion of the lumbosacral and thoracolumbar junction was approximately 3°, they operated in anti-phase during the gait cycle and were strongly correlated (r = -0.5069, p = 0.01). In the transverse plane, the anti-rotation of the upper body relative to the pelvis was mainly ensured by the opposite movements of the lumbosacral and thoracolumbar junction (r = 0.5689, p = 0.003). In the frontal plane, the lateral inclination in the lumbar region was made in the opposite direction from the pelvis toward the carrying member. CONCLUSION: Although there is substantial inter-subject variability, our study characterized the angular movements in the three planes of the different spinal junctions, of the pelvis and the lower limbs during a gait cycle in a healthy population.

Short communication: Claw block application improves locomotion and weight-bearing characteristics in cattle with foot diseases.

In cattle with foot diseases, application of a block on the healthy partner claw is a common method of pain relief. The aim of this study was to evaluate the effect of wooden claw blocks on locomotion characteristics and weight distribution in healthy (group C; n = 17) versus lame (group L; n = 17) cattle. Group L was further subdivided into group L1 (lameness score ≤3; n = 7) and group L2 (lameness score >3; n = 10). We performed lameness scoring using a numeric rating system and measured locomotion characteristics using 2 accelerometers (400 Hz; kinematic outcome = stance phase duration; kinetic outcomes = foot load and toe-off) and a 4-scale weighing platform (difference of mean weight distribution across the limbs; ∆weight) before and after application of a claw block. We applied claw blocks to a randomly assigned lateral or medial claw of the fore or hindlimb in group C cows, and on the healthy partner claw in group L cows. Variables were expressed as differences across limbs. We used 1-way ANOVA to determine the differences between groups C and L and between groups L1 and L2 for ∆weight after application of the claw block. We performed paired t tests to compare variables before and after application of the claw block in groups C and L. Group L scored higher on the numeric rating system than group C (mean ± SD, 3.40 ± 0.62 vs. 1.87 ± 0.28) and showed greater differences in relative stance phase duration (16.34 ± 10.78% vs. 2.13 ± 1.94%), foot load (9.68 ± 8.06 g vs. 3.26 ± 3.69 g), toe-off (3.91 ± 3.14 g vs. 0.78 ± 0.66 g), and ∆weight (53.62 ± 28.85% vs. 8.52 ± 6.19%). In group C, we observed an increase of 12.17 percentage points in ∆weight after block application, from 8.52 ± 6.19% to 20.69 ± 17.01%. Compared with the baseline, group L showed a decrease in numeric rating system score (2.88 ± 0.49 vs. 3.40 ± 0.62) and a decrease in differences between the limbs in relative stance phase duration (7.66 ± 9.96% vs. 16.34 ± 10.78%) and foot load (4.26 ± 4.14 g vs. 9.68 ± 8.06 g) after application of a claw block. Group L2 showed smaller ∆weight after application of a claw block than group L1 (-7.8 ± 8.7% vs. 10.4 ± 7.6%). After block application in group L, we observed smaller differences across the limbs in variables measured to describe gait-cycle characteristics while walking, but no significant improvement while standing. We concluded that application of a claw block must be combined with other methods of pain relief, such as analgesic medication.

A Novel Framework for Quantifying Accuracy and Precision of Event Detection Algorithms in FES-Cycling.

Functional electrical stimulation (FES) is a technique used in rehabilitation, allowing the recreation or facilitation of a movement or function, by electrically inducing the activation of targeted muscles. FES during cycling often uses activation patterns which are based on the crank angle of the pedals. Dynamic changes in their underlying predefined geometrical models (e.g., change in seating position) can lead to desynchronised contractions. Adaptive algorithms with a real-time interpretation of anatomical segments can avoid this and open new possibilities for the automatic design of stimulation patterns. However, their ability to accurately and precisely detect stimulation triggering events has to be evaluated in order to ensure their adaptability to real-case applications in various conditions. In this study, three algorithms (Hilbert, BSgonio, and Gait Cycle Index (GCI) Observer) were evaluated on passive cycling inertial data of six participants with spinal cord injury (SCI). For standardised comparison, a linear phase reference baseline was used to define target events (i.e., 10%, 40%, 60%, and 90% of the cycle's progress). Limits of agreement (LoA) of ±10% of the cycle's duration and Lin's concordance correlation coefficient (CCC) were used to evaluate the accuracy and precision of the algorithm's event detections. The delays in the detection were determined for each algorithm over 780 events. Analysis showed that the Hilbert and BSgonio algorithms validated the selected criteria (LoA: +5.17/-6.34% and +2.25/-2.51%, respectively), while the GCI Observer did not (LoA: +8.59/-27.89%). When evaluating control algorithms, it is paramount to define appropriate criteria in the context of the targeted practical application. To this end, normalising delays in event detection to the cycle's duration enables the use of a criterion that stays invariable to changes in cadence. Lin's CCC, comparing both linear correlation and strength of agreement between methods, also provides a reliable way of confirming comparisons between new control methods and an existing reference.

Human Motion Recognition of Knitted Flexible Sensor in Walking Cycle.

Knitted fabric sensors have been widely used as strain sensors in the sports health field and its large strain performance and structure are suitable for human body movements. When a knitted structure is worn, different human body movements are reflected through the large strain deformation of fabric structure and consequently change the electrical signal. Here, the mechanical and electrical properties of highly elastic knitted sweatpants were tested under large strain. This sensor has good sensitivity and stability during movement. Compared with traditional motion monitoring, this technique divides the walking cycle into two stages, namely, stance and swing phases, which can be further subdivided into six stages. The corresponding resistance characteristic values can accurately distinguish the gait cycle. Analysis on hysteresis and repeatability revealed that the sensor exhibits a constant electrical performance. Four kinds of motion postures were predicted and judged by comparing the resistance characteristic range value, peak value calculation function and time axis. The measured sensor outputs were transferred to a computer via 4.0 Bluetooth. Matlab language was used to detect the status through a rule-based algorithm and the sensor outputs.

Data-Driven Based Approach to Aid Parkinson's Disease Diagnosis.

This article presents a machine learning methodology for diagnosing Parkinson's disease (PD) based on the use of vertical Ground Reaction Forces (vGRFs) data collected from the gait cycle. A classification engine assigns subjects to healthy or Parkinsonian classes. The diagnosis process involves four steps: data pre-processing, feature extraction and selection, data classification and performance evaluation. The selected features are used as inputs of each classifier. Feature selection is achieved through a wrapper approach established using the random forest algorithm. The proposed methodology uses both supervised classification methods including K-nearest neighbour (K-NN), decision tree (DT), random forest (RF), Naïve Bayes (NB), support vector machine (SVM) and unsupervised classification methods such as K-means and the Gaussian mixture model (GMM). To evaluate the effectiveness of the proposed methodology, an online dataset collected within three different studies is used. This data set includes vGRF measurements collected from eight force sensors placed under each foot of the subjects. Ninety-three patients suffering from Parkinson's disease and 72 healthy subjects participated in the experiments. The obtained performances are compared with respect to various metrics including accuracy, precision, recall and F-measure. The classification performance evaluation is performed using the leave-one-out cross validation. The results demonstrate the ability of the proposed methodology to accurately differentiate between PD subjects and healthy subjects. For the purpose of validation, the proposed methodology is also evaluated with an additional dataset including subjects with neurodegenerative diseases (Amyotrophic Lateral Sclerosis (ALS) and Huntington's disease (HD)). The obtained results show the effectiveness of the proposed methodology to discriminate PD subjects from subjects with other neurodegenerative diseases with a relatively high accuracy.

Are there different factors affecting walking speed and gait cycle variability between men and women in community-dwelling older adults?

BACKGROUND: Few studies have examined the relationships between walking speed and gait cycle variability, and muscle strength and postural stability, with a focus on gender differences. AIM: The aim of this study was to examine whether there are different factors affecting walking speed and gait cycle variability between men and women in community-dwelling older adults. METHODS: The subjects comprised 712 community-dwelling older adults (252 men, 460 women, aged 68.7 ± 4.8 years). Walking speed and coefficient of variation (CV) of step time at a comfortable walking pace were measured. The maximal isometric strength of six lower limb muscles and postural stability were evaluated. Stepwise regression analysis was performed, using lower limb muscle strength and postural stability as independent variables, to investigate the association with walking speed or CV. RESULTS: For older men, age, body mass index (BMI) and quadriceps setting (QS) strength were significant and independent determinants of walking speed. No variables were identified as significant determinants of CV. For older women, BMI and hip flexion, hip abduction, QS muscle strength were significant determinants of walking speed. Only hip abduction strength was a significant determinant of CV. DISCUSSION: The results of this study suggest that QS strength is related to walking speed in both men and women, whereas hip flexion and abduction muscle strength are related to walking speed, and hip abduction muscle strength is related to gait cycle variability in older women. CONCLUSION: Gender differences exist in factors affecting walking speed and gait cycle variability in community-dwelling older adults.

Technical note: Validation of a semi-automated software tool to determine gait-cycle variables in dairy cows.

This paper presents the validation of a software tool called Cow-Gait-Analyzer (University of Bern, Switzerland) to determine gait-cycle variables in lame and non-lame dairy cows using features derived from low-cost, stand-alone 3-dimensional accelerometers (400 Hz). The Cow-Gait-Analyzer automatically extracts the relevant gait events of foot load and toe off, which characterize gait-cycle duration, stance phase, and swing phase during walking. A nonautomatic step is visual inspection of the pedograms. If the software does not automatically choose the right peaks according to pedogram definitions, peaks can be manually chosen. We validated the algorithms by comparing the accelerometer data (pedogram) with the synchronized video data, which we used as a gold standard. We carried out the measurements at the metatarsal level of paired hind limbs during walking. We included 12 non-lame cows and 5 lame cows and expressed overall differences between the Cow-Gait-Analyzer and the gold standard as relative measurement error (RME). We analyzed 34 hind limbs with a mean of 9 gait cycles. The median RME for gait-cycle duration and stance phases were 0 and 1.69%, respectively. The peaks of gait-cycle variables showed RME of 0.67 and 0.24% for foot load and toe off, respectively. The semi-automated Cow-Gait-Analyzer can accurately determine gait-cycle variables in both lame and non-lame cows, and could be used to assess gait patterns in routine clinical and research practice focusing on individual cows.