Human gait activity recognition is an emerging field of motion analysis that can be applied in various application domains. One of the most attractive applications includes monitoring of gait disorder patients, tracking their disease progression and the modification/evaluation of drugs. This paper proposes a robust, wearable gait motion data acquisition system that allows either the classification of recorded gait data into desirable activities or the identification of common risk factors, thus enhancing the subject’s quality of life. Gait motion information was acquired using accelerometers and gyroscopes mounted on the lower limbs, where the sensors were exposed to inertial forces during gait. Additionally, leg muscle activity was measured using strain gauge sensors. As a matter of fact, we wanted to identify different gait activities within each gait recording by utilizing Machine Learning algorithms. In line with this, various Machine Learning methods were tested and compared to establish the best-performing algorithm for the classification of the recorded gait information. The combination of attention-based convolutional and recurrent neural networks algorithms outperformed the other tested algorithms and was individually tested further on the datasets of five subjects and delivered the following averaged results of classification: 98.9% accuracy, 96.8% precision, 97.8% sensitivity, 99.1% specificity and 97.3% F1-score. Moreover, the algorithm’s robustness was also verified with the successful detection of freezing gait episodes in a Parkinson’s disease patient. The results of this study indicate a feasible gait event classification method capable of complete algorithm personalization.

Neurophysiological evidence that transcutaneous auricular vagal nerve stimulation (taVNS) affects neuronal signalling at the cortical level is sparse. We used transcranial magnetic stimulation to assess the effect of taVNS on the excitability of intracortical GABAergic and cholinergic circuits.In this within‐subject, double‐blind study on 30 healthy participants, we used TMS paradigms to assess the effect of a single session of taVNS at 100 Hz and sham earlobe VNS (sVNS) on short‐interval intracortical inhibition (SICI) curve and short‐latency afferent inhibition (SAI). Control experiment was performed on additional 15 participants using the same experimental settings, but delivering no stimulation (xVNS). Bayesian statistics were used to assess the differences, producing % values that reflect the certainty that the values of interest were decreased during or after stimulation compared with baseline. taVNS increased SICI (96.3%), whereas sVNS decreased SICI (1.2%). SAI was not affected by taVNS, although it was decreased during sVNS (1.34% and 9.1%, for interstimulus intervals 20 and 24 ms, respectively). The changes in TMS parameters detected during sVNS were present in the same direction in the control experiment with no stimulation.Our study provides evidence that taVNS increases the activity of cortical GABAAergic system, leaving cortical cholinergic circuits unaffected. Changes in intracortical cortical excitability during sVNS, which were also observed in the control experiment with no stimulation were likely the effect of expectation related to participation in an interventional study.

Background: Transcutaneous electrostimulation of the auricular branch of the vagal nerve (taVNS) has the propensity to reach diffuse neuromodulatory networks, which are dysfunctional in Parkinson's disease (PD). Previous studies support the use of taVNS as an add‐on treatment for gait in PD.Objectives: We assessed the effect of taVNS at 25 Hz (taVNS25), taVNS at 100 Hz (taVNS100), and sham earlobe stimulation (sVNS) on levodopa responsive (arm swing velocity, arm range of motion, stride length, gait speed) and non‐responsive gait characteristics (arm range of motion asymmetry, anticipatory postural adjustment [APA] duration, APA first step duration, APA first step range of motion), and turns (first turn duration, double 360° turn duration, steps per turn) in advanced PD.Methods: In our double blind sham controlled within‐subject randomized trial, we included 30 PD patients (modified Hoehn and Yahr stage, 2.5–4) to assess the effect of taVNS25, taVNS100, and sVNS on gait characteristics measured with inertial motion sensors during the instrumented stand and walk test and a double 360° turn. Separate generalized mixed models were built for each gait characteristic.Results: During taVNS100 compared to sVNS arm swing velocity (P = 0.030) and stride length increased (P = 0.027), and APA duration decreased (P = 0.050). During taVNS25 compared to sVNS stride length (P = 0.024) and gait speed (P = 0.021) increased and double 360° turn duration decreased (P = 0.039).Conclusions: We have found that taVNS has a frequency specific propensity to improve stride length, arm swing velocity, and gait speed and double 360° turn duration in PD patients. © 2024 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

FMRI studies show activation of cerebellum during transcutaneous auricular vagal nerve stimulation (taVNS); however, there is no evidence whether taVNS induced activation of the cerebellum translates to the cerebellar closed loops involved in motor functions. We assessed the propensity of taVNS at 25 Hz (taVNS25) and 100 Hz (taVNS100) to modulate cerebello-thalamo-cortical pathways using transcranial magnetic stimulation. In our double blind within-subjects study thirty-two participants completed one visit during which cerebellar brain inhibition (CBI) was assessed at baseline (no stimulation) and in a randomized order during taVNS100, taVNS25, and sham taVNS (xVNS). Generalized linear mixed models with gamma distribution were built to assess the effect of taVNS on CBI. The estimated marginal means of linear trends during each taVNS condition were computed and compared in a pairwise fashion with Benjamini-Hochberg correction for multiple comparisons. CBI significantly increased during taVNS100 compared to taVNS25 and xVNS (p = 0.0003 and p = 0.0465, respectively). The taVNS current intensity and CBI conditioning stimulus intensity had no significant effect on CBI. taVNS has a frequency dependent propensity to modulate the cerebello-thalamo-cortical pathway. The cerebellum participates in closed-loop circuits involved in motor, cognitive, and affective operations and may serve as an entry for modulating effects of taVNS.

This paper presents a real-time wearable system designed to assist Parkinson’s disease patients experiencing freezing of gait episodes. The system utilizes advanced machine learning models, including convolutional and recurrent neural networks, enhanced with past sample data preprocessing to achieve high accuracy, efficiency, and robustness. By continuously monitoring gait patterns, the system provides timely interventions, improving mobility and reducing the impact of freezing episodes. This paper explores the implementation of a CNN+RNN+PS machine learning model on a microcontroller-based device. The device operates at a real-time processing rate of 40 Hz and is deployed in practical settings to provide ‘on demand’ vibratory stimulation to patients. This paper examines the system’s ability to operate with minimal latency, achieving an average detection delay of just 261 milliseconds and a freezing of gait detection accuracy of 95.1%. While patients received on-demand stimulation, the system’s effectiveness was assessed by decreasing the average duration of freezing of gait episodes by 45%. These preliminarily results underscore the potential of personalized, real-time feedback systems in enhancing the quality of life and rehabilitation outcomes for patients with movement disorders.

Background:Brain health is one of the cornerstones of a long and full life. Active care for brain health and reduction of lifestyle-related risks for brain disorders may be a key strategy in tackling the growing prevalence of mental and neurological illnesses. Public knowledge, perception, and preventive behavior need to be considered in the planning of effective strategies for brain health promotion. Our research is the first effort aimed at assessing Slovenian lay public knowledge, search and use of scientific information about the brain, and care for brain health.Methods:An online survey was used to gather data for descriptive and associative statistical analyses of a sample of the Slovenian public (n= 2568) in August 2017. Participants with formal brain-related education were excluded, leaving the remaining sample of the lay public (n= 1012). Demographic characteristics and information regarding the perceived importance and knowledge of brain health and engagement in preventive behaviors of participants were collected, and key associative analyses were carried out.Results:The majority of respondents (89%) considered brain health to be important. Over one-third (39%) considered their knowledge of the brain as sufficient relative to their needs. Most of the respondents identified science-recommended practices to be important for brain health. No recommendation was followed daily by the majority of the respondents, primarily due to declared lack of time (59%), and lack of information (32%). Information was obtained primarily from television (38%), followed by newspapers and magazines (31%), the Internet (31%), and direct conversations (27%). However, the highest-rated, preferred source of information was lectured by experts. One-third of our sample struggled with the trustworthiness of information sources. Female gender and older age were associated with a higher frequency of healthy practices. Personal or familial diagnoses of brain disorders were not associated with a higher frequency of the behavior in favor of brain health, but did affect available time and perceived value of preventive practices.Conclusions:Our research provides an initial insight into the perceptions, knowledge, and brain health-promoting behavior of the Slovenian lay public. Our findings can inform future strategies for science communication, public education and engagement, and policy-making to improve lifelong active care for brain health.