Variance of the Gait Parameters and Fraction of Double-Support Interval for Determining the Severity of Parkinson’s Disease

Development of machine learning models for gait-based classification of incomplete spinal cord injuries and cauda equina syndrome

Incomplete tetraplegia, incomplete paraplegia, and cauda equina syndrome are major neurological disorders that significantly reduce patients' quality of life, primarily due to impaired motor function and gait instability. Although conventional neurological assessments and imaging techniques are widely used for diagnosis, they are limited by temporal constraints and physical accessibility. This study explores the integration of machine learning and 3D motion capture gait data for effective classification of these conditions. Gait data from 214 patients were analyzed, and key features were identified using recursive feature elimination. Machine learning models, including support vector machine, random forest, and XGBoost, were trained and validated. The XGBoost model achieved the highest accuracy (74.42%) and F1-score (74.27%), with age, cadence, and double support emerging as the most influential features. Sex-based differences revealed that males exhibited greater dynamic gait variables, while females showed higher stability-oriented metrics. Age-based analysis indicated significant gait changes after 60 years, highlighting the role of stability-related features. These findings demonstrate the potential of integrating 3D motion capture and machine learning as a scalable, noninvasive diagnostic tool. By detecting subtle gait variations, this approach can aid in early diagnosis and personalized treatment planning for individuals with neurological impairments.

Machine learning for early detection and severity classification in people with Parkinson's disease

Early detection of Parkinson's disease (PD) and accurate assessment of disease progression are critical for optimizing treatment and rehabilitation. However, there is no consensus on how to effectively detect early-stage PD and classify motor symptom severity using gait analysis. This study evaluated the accuracy of machine learning models in classifying early and moderate-stages of PD based on spatiotemporal gait features at different walking speeds. A total of 178 participants were recruited, including 103 individuals with PD (61 early-stage, 42 moderate-stage) and 75 healthy controls. Participants performed a walking test on a 24-m walkway at three speeds: preferred walking speed (PWS), 20% faster (HWS), and 20% slower (LWS). Key features-walking speed at PWS, stride length at HWS, and the coefficient of variation (CV) of the stride length at LWS-achieved a classification accuracy of 78.1% using the random forest algorithm. For early PD detection, the stride length at HWS and CV of the stride length at LWS provided an accuracy of 67.3% with Naïve Bayes. Walking at PWS was the most critical feature for distinguishing early from moderate PD, with an accuracy of 69.8%. These findings suggest that assessing gait over consecutive steps under different speed conditions may improve the early detection and severity assessment of individuals with PD.

Transient Increases in Neural Oscillations and Motor Deficits in a Mouse Model of Parkinson's Disease

Parkinson's disease (PD) is a neurodegenerative disorder characterized by motor symptoms like tremors and bradykinesia. PD's pathology involves the aggregation of α-synuclein and loss of dopaminergic neurons, leading to altered neural oscillations in the cortico-basal ganglia-thalamic network. Despite extensive research, the relationship between the motor symptoms of PD and transient changes in brain oscillations before and after motor tasks in different brain regions remain unclear. This study aimed to investigate neural oscillations in both healthy and PD model mice using local field potential (LFP) recordings from multiple brain regions during rest and locomotion. The histological evaluation confirmed the significant dopaminergic neuron loss in the injection side in 6-OHDA lesioned mice. Behavioral tests showed motor deficits in these mice, including impaired coordination and increased forelimb asymmetry. The LFP analysis revealed increased delta, theta, alpha, beta, and gamma band activity in 6-OHDA lesioned mice during movement, with significant increases in multiple brain regions, including the primary motor cortex (M1), caudate-putamen (CPu), subthalamic nucleus (STN), substantia nigra pars compacta (SNc), and pedunculopontine nucleus (PPN). Taken together, these results show that the motor symptoms of PD are accompanied by significant transient increases in brain oscillations, especially in the gamma band. This study provides potential biomarkers for early diagnosis and therapeutic evaluation by elucidating the relationship between specific neural oscillations and motor deficits in PD.

Wearable sensors for assessing disease severity and progression in Progressive Supranuclear Palsy

INTRODUCTION

Progressive supranuclear palsy (PSP) is an atypical parkinsonism characterized by prominent gait and postural impairment. The PSP rating scale (PSPrs) is a clinician-administered tool to evaluate disease severity and progression. More recently, digital technologies have been used to investigate gait parameters. Therefore, object of this study was to implement a protocol using wearable sensors evaluating disease severity and progression in PSP.

METHODS

Patients were evaluated with the PSPrs as well as with three wearable sensors located on the feet and lumbar area. Spearman coefficient was used to assess the relationship between PSPrs and quantitative measurements. Furthermore, sensor parameters were included in a multiple linear regression model to assess their ability in predicting the PSPrs total score and sub-scores. Finally, differences between baseline and three-month follow-up were calculated for PSPrs and each quantitative variable. The significance level in all analyses was set at ≤ 0.05.

RESULTS

Fifty-eight evaluations from thirty-five patients were analyzed. Quantitative measurements showed multiple significant correlations with the PSPrs scores (r between 0.3 and 0.7; p < 0.05). Linear regression models confirmed the relationships. After three months visit, significant worsening from baseline was observed for cadence, cycle duration and PSPrs item 25, while PSPrs item 10 showed a significant improvement.

CONCLUSION

We propose wearable sensors can provide an objective, sensitive quantitative evaluation and immediate notification of gait changes in PSP. Our protocol can be easily introduced in outpatient and research settings as a complementary tool to clinical measures as well as an informative tool on disease severity and progression in PSP.

A Single Wearable Sensor for Gait Analysis in Parkinson’s Disease: A Preliminary Study

Movement monitoring in patients with Parkinson’s disease (PD) is critical for quantifying disease progression and assessing how a subject responds to medication administration over time. In this work, we propose a continuous monitoring system based on a single wearable sensor placed on the lower back and an algorithm for gait parameters evaluation. In order to preliminarily validate the proposed system, seven PD subjects took part in an experimental protocol in preparation for a larger randomized controlled study. We validated the feasibility of our algorithm in a constrained environment through a laboratory scenario. Successively, it was tested in an unsupervised environment, such as the home scenario, for a total of almost 12 h of daily living activity data. During all phases of the experimental protocol, videos were shot to document the tasks. The obtained results showed a good accuracy of the proposed algorithm. For all PD subjects in the laboratory scenario, the algorithm for step identification reached a percentage error low of 2%, 99.13% of sensitivity and 100% of specificity. In the home scenario the Bland–Altman plot showed a mean difference of −3.29 and −1 between the algorithm and the video recording for walking bout detection and steps identification, respectively.

Kinematic Relations during Double Support Phase in Parkinsonian Gait

The gait of Parkinson’s disease (PD) patients is shuffling, slow, and hesitant. We investigated peculiar gait relations during the double support phase (DSP) in PD patients and healthy controls. We used 3D motion capture (SIMI) to collect kinematic parameters of the natural gait of 11 PD patients (Hoehn and Yahr 2–3, 5 females, 6 males) tested on medication and the same-sized control sample (5 females, 6 males). The difference between groups was evaluated by the Mann-Whitney U test; for target parameters, the Spearman correlation was computed. Compared to the controls, the Parkinsonian step length index was significantly smaller (0.27 vs. 0.35, p < 0.05), step width index higher (0.12 vs. 0.09, p < 0.05), and the DSP duration was extended (0.165 s vs. 0.13 s, p < 0.05), whereas the single support phase was shortened (0.38 s vs. 0.4 s, p < 0.05). The Parkinsonians were faster during DSP initiation and slower during DSP termination (0.908 m·s−1 vs. 0.785 m·s−1, p < 0.05); the Parkinsonian speed was more constant. The patients showed significantly decreased range of motion (ROM) in the hip, ankle, and shoulder and adopted straighter posture during the gait. Understanding gait concatenations can update physiotherapy approaches to target the roots of movement problems instead of the consequences.

A pathophysiological model of gait captures the details of the impairment of pace/rhythm, variability and asymmetry in Parkinsonian patients at distinct stages of the disease

Locomotion in people with Parkinson' disease (pwPD) worsens with the progression of disease, affecting independence and quality of life. At present, clinical practice guidelines recommend a basic evaluation of gait, even though the variables (gait speed, cadence, step length) may not be satisfactory for assessing the evolution of locomotion over the course of the disease. Collecting variables into factors of a conceptual model enhances the clinical assessment of disease severity. Our aim is to evaluate if factors highlight gait differences between pwPD and healthy subjects (HS) and do it at earlier stages of disease compared to single variables. Gait characteristics of 298 pwPD and 84 HS able to walk without assistance were assessed using a baropodometric walkway (GAITRite®). According to the structure of a model previously validated in pwPD, eight spatiotemporal variables were grouped in three factors: pace/rhythm, variability and asymmetry. The model, created from the combination of three factor scores, proved to outperform the single variables or the factors in discriminating pwPD from HS. When considering the pwPD split into the different Hoehn and Yahr (H&Y) stages, the spatiotemporal variables, factor scores and the model showed that multiple impairments of gait appear at H&Y stage 2.5, with the greatest difference from HS at stage 4. A contrasting behavior was found for the asymmetry variables and factor, which showed differences from the HS already in the early stages of PD. Our findings support the use of factor scores and of the model with respect to the single variables in gait staging in PD.

Detecting Effect of Levodopa in Parkinson's Disease Patients Using Sustained Phonemes

BACKGROUND

Parkinson's disease (PD) is a multi-symptom neurodegenerative disease generally managed with medications, of which levodopa is the most effective. Determining the dosage of levodopa requires regular meetings where motor function can be observed. Speech impairment is an early symptom in PD and has been proposed for early detection and monitoring of the disease. However, findings from previous research on the effect of levodopa on speech have not shown a consistent picture.

METHOD

This study has investigated the effect of medication on PD patients for three sustained phonemes; /a/, /o/, and /m/, which were recorded from 24 PD patients during medication off and on stages, and from 22 healthy participants. The differences were statistically investigated, and the features were classified using Support Vector Machine (SVM).

RESULTS

The results show that medication has a significant effect on the change of time and amplitude perturbation (jitter and shimmer) and harmonics of /m/, which was the most sensitive individual phoneme to the levodopa response. /m/ and /o/ performed at a comparable level in discriminating PD-off from control recordings. However, SVM classifications based on the combined use of the three phonemes /a/, /o/, and /m/ showed the best classifications, both for medication effect and for separating PD from control voice. The SVM classification for PD-off versus PD-on achieved an AUC of 0.81.

CONCLUSION

Studies of phonation by computerized voice analysis in PD should employ recordings of multiple phonemes. Our findings are potentially relevant in research to identify early parkinsonian dysarthria, and to tele-monitoring of the levodopa response in patients with established PD.