Vertical Ground Reaction Force Signals Research Articles

An efficient tool for Parkinson's disease detection and severity grading based on time-frequency and fuzzy features of cumulative gait signals through improved LSTM networks

Parkinson's disease (PD) is a widespread neurodegenerative condition that affects many individuals annually. Early identification and monitoring of disease progression are crucial to effectively managing symptoms and preventing motor complications. This research proposes an automated PD diagnosis and severity-grading model based on time-frequency and fuzzy features using improved uni-directional and bi-directional long short-term memory networks with sensitive hyperparameters optimization. We utilize vertical ground reaction force signals collected from Physionet's publicly available dataset recorded during regular and dual-task clinical trials of walking measurements. Only the cumulative signal of both feet was then utilized and segmented into 30-s windows without further pre-processing. Subsequently, we extracted only four key time-frequency and fuzzy features from each segment, effectively capturing the signal's inherent uncertainty. Bayesian optimization is employed in both detection and grading approaches to fine-tune the two critical hyperparameters: the initial learning rate and the number of hidden units in the network. The detection phase yields an exceptional accuracy of 99.19%, surpassing state-of-the-art studies with the same dataset. In the grading phase, classification based on the unified PD rating scale values achieves an accuracy of 92.28%. The proposed study delves into the potential of cumulative gait signals as a powerful diagnostic tool for PD, aiming to extract precise and intricate information by implementing straightforward and minimal processing endeavors. This method demonstrates significant efficiency in terms of complexity, cost, and energy consumption by utilizing a single-dimensional signal, eliminating the need for pre-processing steps, and limiting the features used for training.

Isolating the speed factor is crucial in gait analysis for Parkinson's disease.

Parkinson's disease (PD) is characterized by an alteration of the walking gait, frequently including a slower self-selected walking speed (SSWS). Although the reduction of walking speed is inherent to people with PD, such speed reduction also represents a potential confounding factor that might partly explain the observed gait differences between PD and control participants. In this study, each participant walked along a 25 m level corridor during which vertical ground reaction force signals were recorded using shoes equipped with eight pressure sensors. Vertical ground reaction force signals (using statistical parametric mapping) and temporal and kinetic variables as well as their related variability and asymmetry (using Student's t-test) were compared between PD (n = 54) and walking-speed-matched control subjects (n = 39). Statistical parametric mapping did not yield significant differences between PD and control groups for the vertical ground reaction force signal along the walking stance phase. Stride time and single support time (equivalent to swing time) were shorter and peak vertical ground reaction force was larger in PD patients compared to controls (p ≤ 0.05). However, the single support time was no longer different between people with PD and healthy subjects when expressed relatively to stride time (p = 0.07). While single support, double support, and stance times were significantly more variable and asymmetric for PD than for the control group (p ≤ 0.05), stride time was similar (p ≥ 0.07). These results indicate that at matched SSWS, PD patients adopt a higher cadence than control participants. Moreover, the temporal subdivision of the walking gait of people with PD is similar to healthy individuals but the coordination during the double support phase is different. Hence, this study indicates that isolating the speed factor is crucial in gait analysis for PD.

A Robust Frequency-Domain-Based Graph Adaptive Network for Parkinson's Disease Detection From Gait Data

Parkinson's disease (PD) is a neurodegenerative disease with a high incidence rate. Effective early diagnosis of PD is critical to prevent further deterioration of a patient's condition, where gait abnormalities are important factors for doctors to diagnose PD. Deep learning (DL)-based methods for PD detection using gait information recorded by non-invasive sensors have emerged to assist doctors in accurate and efficient disease diagnosis. However, most existing DL-based PD detection models neglect information in the frequency domain and do not adaptively model the correlation of signals among sensors. Moreover, different people have different gait patterns. Therefore, the generalization capabilities of PD detection models on diversities of individuals' gaits are essential. This work proposes a novel robust frequency-domain-based graph adaptive network (RFdGAD) for PD detection from gait information (i.e., vertical ground reaction force signals recorded by foot sensors). Specifically, the RFdGAD first learns the frequency-domain features of signals from each foot sensor by a frequency representation learning block. Then, the RFdGAD utilizes a graph adaptive network block taking frequency-domain features as input to adaptively learn and exploit the interconnection between different sensor signals for accurate PD detection. Moreover, the RFdGAD is trained by minimizing the proposed Jensen-Shannon divergence-based localized generalization error to improve the generalization performance of RFdGAD on unseen subjects. Experimental results show that the RFdGAD outperforms existing DL-based models for PD detection on three widely used datasets in terms of three metrics, including accuracy, F1-score, and geometric mean.

Parkinson’s disease diagnosis and stage prediction based on gait signal analysis using EMD and CNN–LSTM network

Parkinson’s disease (PD) diagnosis is a complex and challenging task which needs the assessment of various motor and non-motor symptoms. As gait impairment is one of the early and important symptoms of PD, in a clinical setting, physicians generally evaluate the gait abnormality based on visual observations along with other numerous manifestations to assess the severity of PD. As such kind of assessment majorly depends on the experience and expertise of the physicians, there is scope for bias in assessment, leading to misdiagnosis. In this context, to assist the physicians to diagnose PD effectively, this study aims to design and investigate a gait analysis based classifier model using a hybrid convolutional neural network-long short term memory (CNN–LSTM) network to predict the severity rating of PD. For evaluation, we utilize the openly available gait dataset from Physionet that consists of vertical ground reaction force (VGRF) signals from three different walking tests. Firstly, the prominent VGRF signals obtained using the variability analysis are decomposed using the empirical mode decomposition (EMD) technique to extract the significant intrinsic mode functions (IMFs) that contain the vital gait features. Secondly, through the power spectral analysis the dominant IMFs of the selected VGRF signals are extracted to train the CNN–LSTM classifier model. To address the data overfitting problem in the classifier model, the proposed approach employs L2 regularization along with dropout techniques. Moreover, to solve the stochastic cost function, CNN–LSTM network utilizes the Adam optimizer for its minimal memory requirement and tuning. Finally, the experiments conducted using the gait patterns from 93 PD subjects and 73 healthy controls substantiate that the proposed CNN–LSTM​ classifier model can achieve a maximum multi-class classification accuracy of 98.32% and offer superior performance compared to several other similar methods which have used gait pattern to diagnose PD.

Identification of Neurodegenerative Diseases Based on Vertical Ground Reaction Force Classification Using Time-Frequency Spectrogram and Deep Learning Neural Network Features.

A novel identification algorithm using a deep learning approach was developed in this study to classify neurodegenerative diseases (NDDs) based on the vertical ground reaction force (vGRF) signal. The irregularity of NDD vGRF signals caused by gait abnormalities can indicate different force pattern variations compared to a healthy control (HC). The main purpose of this research is to help physicians in the early detection of NDDs, efficient treatment planning, and monitoring of disease progression. The detection algorithm comprises a preprocessing process, a feature transformation process, and a classification process. In the preprocessing process, the five-minute vertical ground reaction force signal was divided into 10, 30, and 60 s successive time windows. In the feature transformation process, the time–domain vGRF signal was modified into a time–frequency spectrogram using a continuous wavelet transform (CWT). Then, feature enhancement with principal component analysis (PCA) was utilized. Finally, a convolutional neural network, as a deep learning classifier, was employed in the classification process of the proposed detection algorithm and evaluated using leave-one-out cross-validation (LOOCV) and k-fold cross-validation (k-fold CV, k = 5). The proposed detection algorithm can effectively differentiate gait patterns based on a time–frequency spectrogram of a vGRF signal between HC subjects and patients with neurodegenerative diseases.

Gait Analysis by Causal Decomposition

Recent studies have investigated bilateral gaits based on the causality analysis of kinetic (or kinematic) signals recorded using both feet. However, these approaches have not considered the influence of their simultaneous causation, which might lead to inaccurate causality inference. Furthermore, the causal interaction of these signals has not been investigated within their frequency domain. Therefore, in this study we attempted to employ a causal-decomposition approach to analyze bilateral gait. The vertical ground reaction force (VGRF) signals of Parkinson's disease (PD) patients and healthy control (HC) individuals were taken as an example to illustrate this method. To achieve this, we used ensemble empirical mode decomposition to decompose the left and right VGRF signals into intrinsic mode functions (IMFs) from the high to low frequency bands. The causal interaction strength (CIS) between each pair of IMFs was then assessed through the use of their instantaneous phase dependency. The results show that the CISes between pairwise IMFs decomposed in the high frequency band of VGRF signals can not only markedly distinguish PD patients from HC individuals, but also found a significant correlation with disease progression, while other pairwise IMFs were not able to produce this. In sum, we found for the first time that the frequency specific causality of bilateral gait may reflect the health status and disease progression of individuals. This finding may help to understand the underlying mechanisms of walking and walking-related diseases, and offer broad applications in the fields of medicine and engineering.

Reconstruction of dual tasking gait pattern in Parkinson’s disease subjects using radial basis function based artificial intelligence

Vertical Ground Reaction Force (VGRF) is a force obtained during gait cycle beneath the feet and is used to screen the severity of Parkinson’s disease (PD) patient’s in clinical environment. This article investigates the VGRF signals (left and right) semblance nature among PD patients and control subjects as a function of time and possibility of reconstructing dual tasking VGRF signal from normal walking VGRF signals using radial basis function (RBF) based artificial intelligence (AI). There are many traditional methods for gait analysis and these methods are purely subjective and none made semblance analysis of same subjects gait pattern in different tasking. In order to overcome the difficulties faced by PD patients, RBF based AI is proposed in this research to reconstruct the dual tasking VGRF signal from normal walking VGRF signal. 93 PD patients with mean age: 66.3 years (63% men), and 73 healthy controls with mean age: 66.3 years (55% men) datasets are used in this work. Proposed RBF network is trained on VGRF signals obtained in normal walking and dual tasking conditions from control. The network was trained with 60% of VGRF data and tested on remaining 40% data. Semblance analysis results are encouraging, and it shows that semblance is high in PD patients than control subjects during dual tasking (P < 0.05). In order to test the findings of semblance analysis, we explicitly reconstruct VGRF signal of clinically significant dual tasking from VGRF signal of normal walking by the proposed RBF method. Findings proved that the proposed RBF network can reconstruct dual tasking VGRF signal of PD patients from their normal walking VGRF signal with high cross correlation (P < 0.0001). These findings pave way for a new adjunct tool to diagnose the gait dynamics of PD patients using the proposed reconstruction method.

Gait Influence Diagrams in Parkinson's Disease.

Previous studies have shown that gait patterns differ between Parkinson's disease (PD) patients and controls. However, almost all these studies focused only on univariate time series of a single variable. This approach cannot reveal detailed information of foot loading dynamics and the cooperative relationships of different anatomical plantar foot areas when the subjects walk. By contrast, we propose a novel multivariate method for analyzing gait patterns of the PD patients: Gait Influence Diagrams (GIDs). These are constructed by analyzing the Wiener-Akaike-Granger- Schweder influences between vertical ground reaction force signals at different plantar areas of both feet. In this paper, we use the particular case of WAGS influence measures known as "extended Granger causality analysis". GIDs are directed graphs, with arrows indicating those influences that are significantly different between PD patients and healthy subjects. We confirm prior clinical observations that Parkinsonian gait differs significantly from the healthy one in the anterior-posterior movement direction. A new finding is that there are also pathological changes in the lateral-medial direction. Importantly, gait asymmetry for the PD patients is clearly evident in GIDs, even in earlier stages of the disease. These results suggest that GID might be of use in future PD gait pattern studies.

Gait-Ground Reaction Force Sensors Selection Based on ROC Curve Evaluation

Classification of normal gait from pathological gait as then can be used as indicator of falling among subjects requires the correct choice of sensor location in the insole. Such a flexi force- sensor can be used underneath foot to measure vertical ground reaction force. To start with, the most relevant information (parameters) that can characterize the recorded signals are extracted from the vertical ground reaction force signals. Then Receiver Operating Characteristic curve is used to evaluate the features upon 8 sensors underneath each foot located at different locations. To confirm results obtained, features are passed upon a chosen classifier, in this paper K-nearest neighbors algorithm is chosen. Results show that the sensor located at the inner arch of the sole of the foot (i.e. at the mid foot) holds the most relevant information needed for better classification compared to other sensors.

Impact reduction through long-term intervention in recreational runners: midfoot strike pattern versus low-drop/low-heel height footwear

Impact reduction has become a factor of interest in the prevention of running-related injuries such as stress fractures. Currently, the midfoot strike pattern (MFS) is thought as a potential way to decrease impact. The purpose was to test the effects of two long-term interventions aiming to reduce impact during running via a transition to an MFS: a foot strike retraining versus a low-drop/low-heel height footwear. Thirty rearfoot strikers were randomly assigned to two experimental groups (SHOES and TRAIN). SHOES progressively wore low-drop/low-heel height shoes and TRAIN progressively adopted an MFS, over a 3-month period with three 30-min running sessions per week. Measurement sessions (pre-training, 1, 2 and 3 months) were performed during which subjects were equipped with three accelerometers on the shin, heel and metatarsals, and ran for 15 min on an instrumented treadmill. Synchronized acceleration and vertical ground reaction force signals were recorded. Peak heel acceleration was significantly lower as compared to pre-training for SHOES (-33.5 ± 12.8 % at 2 months and -25.3 ± 18.8 % at 3 months, p < 0.001), and so was shock propagation velocity (-12.1 ± 9.3 %, p < 0.001 at 2 months and -11.3 ± 4.6 %, p < 0.05 at 3 months). No change was observed for TRAIN. Important inter-individual variations were noted in both groups and reported pains were mainly located at the shin and calf. Although it induced reversible pains, low-drop/low-heel height footwear seemed to be more effective than foot strike retraining to attenuate heel impact in the long term.

Muscle co-activation, knee joint kinematics, and ground reaction forces are altered in the operated leg of meniscectomized patients at high risk of knee osteoarthritis

Purpose: Every other meniscectomized patient develop knee osteoarthritis (OA) 10-15 years after surgery. Thus, meniscectomized patients constitute a useful model to study changes in neuromuscular activity and knee joint biomechanics, which are factors suggested to play a role in OA development. Recently, we were unable to detect differences in neuromuscular activity and knee joint kinetics/kinematics betweenmeniscectomized patients and controls during stair descent. Furthermore, only modest leg-to-leg differences were observed between the operated and contra-lateral leg of the patients. More demanding motor tasks may be needed to detect early changes in knee joint kinetics/kinematics and neuromuscular activity in meniscectomized patients at high risk of knee OA. The aim of this study was therefore to investigate knee joint kinematics, ground reaction force (GRF) kinetics and level of muscle co-activation during a standardized forward lunge maneuver in meniscectomized patients at high risk of knee osteoarthritis. We hypothesized that patients would display increased levels of muscle co-activation along with reduced knee joint range of motion (ROM) and altered GRF kinetics in the operated compared to the contra-lateral leg. Methods: Patients: Twenty-two patients meniscectomized uni-laterally for a medial meniscal tear in the posterior half of the meniscus (15 men and 7 women, 45.4 5.1 years, 174.3 7.1 cm, 77.3 15.4 kg, BMI 25.4 kg/ m2, values are mean SD) were investigated during a standardized forward lunge with synchronous electromyography (EMG), goniometer and force plate recording. In the analyseswe focusedon threedifferent phasesof the forward lunge; the loading phase (foot-strike to 80% peak GRF), the unloading phase (80% peak GRF to toe-off) and mean of the entire stance phase (foot strike to toe-off). Knee joint range of motion (ROM): Knee joint ROM during the loading phase (ROMload), unloading phase (ROMunload) and from foot strike to peak knee flexion (ROMpeakflex) were measured using a flexible electrogoniometer. Ground reaction forces (GRF): The vertical GRF signal during the forward lunge was used to calculate the rate of loading (Loadslope), rate of unloading (Unloadslope) and average magnitude of GRF during the entire stance phase (GRFmean). Co-activation: Thigh muscle co-activation in the above phases of the forward lunge was quantified using normalized EMG signals obtained in the vastus lateralis (VL), vastus medialis (VM), biceps femoris (BF) and semitendinosus (ST) muscles. Statistics: Paired t-test with 0.05 level of significance was used to assess differences between the operated and contra-lateral leg of the patients. Results: All results are reported as mean SE. Consistent differences were observed between the operated leg and contra-lateral leg during the impact phase (loading phase) of the forward lunge. These differences were manifested as increased levels of muscle co-activation (38.0 4.0 vs. 30.1 3.1 %MVC, p1⁄40.02), reduced ROM (23.4 2.9 vs. 29.7 2.7 degrees, p1⁄40.01) and a higher loading rate (Loadslope) (985 160 vs. 696 82 %BW s-1, p1⁄40.01). Furthermore, ROMpeakflex was reduced in the operated compared with the contra-lateral leg (59.4 2.3 vs. 64.9 2.0 degrees, p1⁄40.01). No differences were observed in ROMunload, Unloadslope or muscle co-activation during the unloading phase. In addition, no differences were observed in GRFmean and averagemuscle co-activation during the entire stance phase. Conclusions: The findings of increasedmuscle co-activation, reduced ROM and increased rate of loading during the loading phase between the operated and contra-lateral leg support the hypothesis that meniscectomized patients demonstrate early modulations in knee joint kinetics, kinematics and neuromuscular activity in the operated leg. Future studies should include more demanding motor tasks than stair walking. Representing such a task, the forward lunge test appears to provide a sensitive approach to identify leg-to-leg differences in relevant neuromuscular and biomechanical variables in middle-aged patients at risk of OA.

달리기 시도 수 증가에 따른 VGRF 신호 성분의 Variability 분석

The purpose of this study was to determine the variability of components of the vertical ground reaction force signal to seek the suitable number of attempt datum to be analyzed during running at 2m/s and 4m/s. For this study, six subjects (height mean:<TEX>$174.5{\pm}4.4cm$</TEX>, weight <TEX>$671.5{\pm}116.4N.$</TEX>, age:<TEX>$25.0{\pm}yrs.$</TEX>) were selected and asked to run at least 3 times each run condition randomly. FFT(fast Fourier transform) was used to analyze the frequency domain analysis of the vertical ground reaction forces signal and an accumulated PSD (power spectrum density) was calculated to reconstruct the certain signal. To examine the deviation of the vertical ground reaction between signals collected from an different number of attempt, variability of frequency, magnitude of passive peak, time up to the passive peak and maximum load rate were determined in a coefficient of variance. The variability analysis revealed that when analyze the vertical reaction force components at 2m/s speed running, which belongs to slow pace relatively, it would be good to calculate these components from signal of one attempt, but 4m/s speed running needs data collected from two attempts to decrease the deviation of signal between attempts. In summary, when analyzing the frequency and passive peak of the vertical reaction force signal during the fast run, it should be considered the number of attempt.

Electromyographic evidence of selective fatigue during the eccentric phase of stretch/shortening cycles in man

Ten male subjects were tested to determine the effects of muscle fatigue upon the activation pattern of the two main ankle extensor muscles, the 'slow-twitch' soleus (SOL) and the relatively 'fast-twitch' medial gastrocnemius (MG), during a fatiguing 60-s trial of hopping to maximal height. The myoelectric signals from SOL and MG were recorded together with the vertical ground reaction force signal and analysed by means of a computer-aided electromyograph (EMG) contour analysis, i.e. two-dimensional frequency distributions were obtained relating the activation patterns of the two synergists. The EMGs were also full-wave rectified and integrated (IEMG) according to three phases of the hopping movement (PRE, pre-activation phase; ECC, eccentric phase; CON, concentric phase). Results indicated that there were significant decreases (P less than 0.01) in the peak ground reaction force, the height of hopping and the mechanical power per unit body weight at the end of the fatiguing contractions. These decreases in mechanical parameters were accompanied by significant (P less than 0.01) decreases in all three phases of MG IEMG while SOL IEMG showed no such significant declines, except in the CON phase. Thus, the decreased mechanical parameters could in large part be accounted for by the substantial and selective decline of the excitation level of the relatively fast-twitch MG muscle. Our data suggest that the centrally mediated pre-activation of the fatiguable MG muscle as well as the MG activation during the eccentric phase, which is largely controlled by supraspinal inputs and stretch-reflex modulation, are most affected by fatigue changes during repeated maximal stretch/shortening cycles of the ankle extensors.