Implementation of a Deep Learning Algorithm Based on Vertical Ground Reaction Force Time-Frequency Features for the Detection and Severity Classification of Parkinson's Disease

Artificial Intelligence in the Diagnosis of Neurological Diseases Using Biomechanical and Gait Analysis Data: A Scopus-Based Bibliometric Analysis

Neurological diseases are increasingly diverse and prevalent, presenting significant challenges for their timely and accurate diagnosis. The aim of the present study is to conduct a bibliometric analysis and literature review in the field of neurology to explore advancements in the application of artificial intelligence (AI) techniques, including machine learning (ML) and deep learning (DL). Using VOSviewer software (version 1.6.20.0) and documents retrieved from the Scopus database, the analysis included 113 articles published between 1 January 2018 and 31 December 2024. Key journals, authors, and research collaborations were identified, highlighting major contributions to the field. Science mapping investigated areas of research focus, such as biomechanical data and gait analysis including AI methodologies for neurological disease diagnosis. Co-occurrence analysis of author keywords allowed for the identification of four major themes: (a) machine learning and gait analysis; (b) sensors and wearable health technologies; (c) cognitive disorders; and (d) neurological disorders and motion recognition technologies. The bibliometric insights demonstrate a growing but relatively limited collaborative interest in this domain, with only a few highly cited authors, documents, and journals driving the research. Meanwhile, the literature review highlights the current methodologies and advancements in this field. This study offers a foundation for future research and provides researchers, clinicians, and occupational therapists with an in-depth understanding of AI's potentially transformative role in neurology.

Gait-based Parkinson's disease diagnosis and severity classification using force sensors and machine learning

A dual-stage model for classifying Parkinson's disease severity, through a detailed analysis of Gait signals using force sensors and machine learning approaches, is proposed in this study. Parkinson's disease is the primary neurodegenerative disorder that results in a gradual reduction in motor function. Early detection and monitoring of the disease progression is highly challenging due to the gradual progression of symptoms and the inadequacy of conventional methods in identifying subtle changes in mobility. The proposed dual-stage model utilized a hypertuned Random Forest Tree (RFT) to classify the subjects into PD and non-PD classes at Stage 1 and a hypertuned Ensemble Regressor (ER) to predict the severity of illness at Stage 2. Further, we have implemented the proposed model on the data signals gathered from both feet of 166 participants using Vertical Ground Reaction Force Sensors (VGRF). The dataset comprised 93 persons with Parkinson's disease and 73 healthy controls. The dataset (imbalance) collected from both feet is passed to the preprocessing phase (for balancing data using the SMOTE method), followed by the feature extraction phase to extract features related to time, frequency, spatial, and temporal features domains that are highly effective for detecting and assigning severity levels of PD. A Recursive Feature Elimination method is also used to select the optimal set of features to improve the model performance. It is acknowledged that the early detection of Parkinson's disease is contingent upon critical parameters, including stride length, stance duration, swing interval, double limb support, step time, and step length. The crucial evaluation metrics used for evaluating model performance include accuracy, mean absolute error, and root mean square error. The findings indicate that the suggested model significantly surpasses current methodologies. It attained an accuracy of 97.5 ± 2.1%, Sensitivity of 97% ± 2.5%, and average Specificity of 95% ± 2.2% in differentiating between PD and non-PD participants utilizing RFT and evaluated disease severity with an average accuracy of 96.4 ± 2.3%, an average mean absolute error of 0.065 ± 0.024, and a root mean square error of 0.080 ± 0.06. The results indicate that the proposed dual-stage model is exceptionally successful in the early detection and severity assessment of Parkinson's disease and demonstrates better efficacy than alternative models.

Classification of Parkinson's disease severity using gait stance signals in a spatiotemporal deep learning classifier

Parkinson's disease (PD) is a degenerative nervous system disorder involving motor disturbances. Motor alterations affect the gait according to the progression of PD and can be used by experts in movement disorders to rate the severity of the disease. However, this rating depends on the expertise of the clinical specialist. Therefore, the diagnosis may be inaccurate, particularly in the early stages of PD where abnormal gait patterns can result from normal aging or other medical conditions. Consequently, several classification systems have been developed to enhance PD diagnosis. In this paper, a PD gait severity classification algorithm was developed using vertical ground reaction force (VGRF) signals. The VGRF records used are from a public database that includes 93 PD patients and 72 healthy controls adults. The work presented here focuses on modeling each foot's gait stance phase signals using a modified convolutional long deep neural network (CLDNN) architecture. Subsequently, the results of each model are combined to predict PD severity. The classifier performance was evaluated using ten-fold cross-validation. The best-weighted accuracies obtained were 99.296(0.128)% and 99.343(0.182)%, with the Hoehn-Yahr and UPDRS scales, respectively, outperforming previous results presented in the literature. The classifier proposed here can effectively differentiate gait patterns of different PD severity levels based on gait signals of the stance phase.

The Role of Deep Learning and Gait Analysis in Parkinson's Disease: A Systematic Review

Parkinson's disease (PD) is the second most common movement disorder in the world. It is characterized by motor and non-motor symptoms that have a profound impact on the independence and quality of life of people affected by the disease, which increases caregivers' burdens. The use of the quantitative gait data of people with PD and deep learning (DL) approaches based on gait are emerging as increasingly promising methods to support and aid clinical decision making, with the aim of providing a quantitative and objective diagnosis, as well as an additional tool for disease monitoring. This will allow for the early detection of the disease, assessment of progression, and implementation of therapeutic interventions. In this paper, the authors provide a systematic review of emerging DL techniques recently proposed for the analysis of PD by using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The Scopus, PubMed, and Web of Science databases were searched across an interval of six years (between 2018, when the first article was published, and 2023). A total of 25 articles were included in this review, which reports studies on the movement analysis of PD patients using both wearable and non-wearable sensors. Additionally, these studies employed DL networks for classification, diagnosis, and monitoring purposes. The authors demonstrate that there is a wide employment in the field of PD of convolutional neural networks for analyzing signals from wearable sensors and pose estimation networks for motion analysis from videos. In addition, the authors discuss current difficulties and highlight future solutions for PD monitoring and disease progression.

Simultaneous time-frequency analysis of gait signals of both legs in classifying neurodegenerative diseases

BACKGROUND

Neurodegenerative diseases (NDDs) pose significant challenges due to their debilitating nature and limited therapeutic options. Accurate and timely diagnosis is crucial for optimizing patient care and treatment strategies. Gait analysis, utilizing wearable sensors, has shown promise in assessing motor abnormalities associated with NDDs.

RESEARCH QUESTION

Research Question 1 To what extent can analyzing the interaction of both limbs in the time-frequency domain serve as a suitable methodology for accurately classifying NDDs? Research Question 2 How effective is the utilization of color-coded images, in conjunction with deep transfer learning models, for the classification of NDDs?

METHODS

GaitNDD database was used, comprising recordings from patients with Huntington's disease, amyotrophic lateral sclerosis, Parkinson's disease, and healthy controls. The gait signals underwent signal preparation, wavelet coherence analysis, and principal component analysis for feature enhancement. Deep transfer learning models (AlexNet, GoogLeNet, SqueezeNet) were employed for classification. Performance metrics, including accuracy, sensitivity, specificity, precision, and F1 score, were evaluated using 5-fold cross-validation.

RESULTS

The classification performance of the models varied depending on the time window used. For 5-second gait signal segments, AlexNet achieved an accuracy of 95.91 %, while GoogLeNet and SqueezeNet achieved accuracies of 96.49 % and 92.73 %, respectively. For 10-second segments, AlexNet outperformed other models with an accuracy of 99.20 %, while GoogLeNet and SqueezeNet achieved accuracies of 96.75 % and 95.00 %, respectively. Statistical tests confirmed the significance of the extracted features, indicating their discriminative power for classification.

SIGNIFICANCE

The proposed method demonstrated superior performance compared to previous studies, offering a non-invasive and cost-effective approach for the automated diagnosis of NDDs. By analyzing the interaction between both legs during walking using wavelet coherence, and utilizing deep transfer learning models, accurate classification of NDDs was achieved.

Vertical Ground Reaction Forces in Parkinson's Disease: A Speed-Matched Comparative Analysis with Healthy Subjects

This study aimed to investigate and compare the vertical Ground Reaction Forces (vGRFs) of patients with Parkinson's Disease (PwPD) and healthy subjects (HS) when the confounding effect of walking speed was absent. Therefore, eighteen PwPD and eighteen age- and linear walking speed-matched HS were recruited. Using plantar pressure insoles, participants walked along linear and curvilinear paths at self-selected speeds. Interestingly, PwPD exhibited similar walking speed to HS during curvilinear trajectories (p = 0.48) and similar vGRF during both linear and curvilinear paths. In both groups, vGRF at initial contact and terminal stance was higher during linear walking, while vGRF at mid-stance was higher in curvilinear trajectories. Similarly, the time to peak vGRF at each phase showed no significant group differences. The vGRF timing variability was different between the two groups, particularly at terminal stance (p < 0.001). In conclusion, PwPD and HS showed similar modifications in vGRF and a similar reduction in gait speed during curvilinear paths when matched for linear walking speed. This emphasized the importance of considering walking speed when assessing gait dynamics in PwPD. This study also suggests the possibility of the variability of specific temporal measures in differentiating the gait patterns of PwPD versus those of HS, even in the early stages of the disease.

A review of emergent intelligent systems for the detection of Parkinson's disease

Parkinson's disease (PD) is a neurodegenerative disorder affecting people worldwide. The PD symptoms are divided into motor and non-motor symptoms. Detection of PD is very crucial and essential. Such challenges can be overcome by applying artificial intelligence to diagnose PD. Many studies have also proposed the implementation of computer-aided diagnosis for the detection of PD. This systematic review comprehensively analyzed all appropriate algorithms for detecting and assessing PD based on the literature from 2012 to 2023 which are conducted as per PRISMA model. This review focused on motor symptoms, namely handwriting dynamics, voice impairments and gait, multimodal features, and brain observation using single photon emission computed tomography, magnetic resonance and electroencephalogram signals. The significant challenges are critically analyzed, and appropriate recommendations are provided. The critical discussion of this review article can be helpful in today's PD community in such a way that it allows clinicians to provide proper treatment and timely medication.

A novel plantar pressure analysis method to signify gait dynamics in Parkinson's disease

Plantar pressure can signify the gait performance of patients with Parkinson's disease (PD). This study proposed a plantar pressure analysis method with the dynamics feature of the sub-regions plantar pressure signals. Specifically, each side's plantar pressure signals were divided into five sub-regions. Moreover, a dynamics feature extractor (DFE) was designed to extract features of the sub-regions signals. The radial basis function neural network (RBFNN) was used to learn and store gait dynamics. And a classification mechanism based on the output error in RBFNN was proposed. The classification accuracy of the proposed method achieved 100.00% in PD diagnosis and 95.89% in severity assessment on the online dataset, and 96.00% in severity assessment on our dataset. The experimental results suggested that the proposed method had the capability to signify the gait dynamics of PD patients.

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

Introduction

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.

Methods

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).

Results

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).

Discussion

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.