Feature Learning for Detection and Prediction of Freezing of Gait in Parkinson’s Disease

On-Demand Gait-Synchronous Electrical Cueing in Parkinson's Disease Using Machine Learning and Edge Computing: A Pilot Study

Goal: Parkinson's disease (PD) can lead to gait impairment and Freezing of Gait (FoG). Recent advances in cueing technologies have enhanced mobility in PD patients. While sensor technology and machine learning offer real-time detection for on-demand cueing, existing systems are limited by the usage of smartphones between the sensor(s) and cueing device(s) for data processing. By avoiding this we aim at improving usability, robustness, and detection delay. Methods: We present a new technical solution, that runs detection and cueing algorithms directly on the sensing and cueing devices, bypassing the smartphone. This solution relies on edge computing on the devices' hardware. The wearable system consists of a single inertial sensor to control a stimulator and enables machine-learning-based FoG detection by classifying foot motion phases as either normal or FoG-affected. We demonstrate the system's functionality and safety during on-demand gait-synchronous electrical cueing in two patients, performing freezing of gait assessments. As references, motion phases and FoG episodes have been video-annotated. Results: The analysis confirms adequate gait phase and FoG detection performance. The mobility assistant detected foot motions with a rate above 94 % and classified them with an accuracy of 84 % into normal or FoG-affected. The FoG detection delay is mainly defined by the foot-motion duration, which is below the delay in existing sliding-window approaches. Conclusions: Direct computing on the sensor and cueing devices ensures robust detection of FoG-affected motions for on demand cueing synchronized with the gait. The proposed solution can be easily adopted to other sensor and cueing modalities.

Detection and prediction of freezing of gait with wearable sensors in Parkinson's disease

Freezing of gait (FoG) is one of the most distressing symptoms of Parkinson's Disease (PD), commonly occurring in patients at middle and late stages of the disease. Automatic and accurate FoG detection and prediction have emerged as a promising tool for long-term monitoring of PD and implementation of gait assistance systems. This paper reviews the recent development of FoG detection and prediction using wearable sensors, with attention on identifying knowledge gaps that need to be filled in future research. This review searched the PubMed and Web of Science databases to collect studies that detect or predict FoG with wearable sensors. After screening, 89 of 270 articles were included. The data description, extracted features, detection/prediction methods, and classification performance were extracted from the articles. As the number of papers of this area is increasing, the performance has been steadily improved. However, small datasets and inconsistent evaluation processes still hinder the application of FoG detection and prediction with wearable sensors in clinical practice.

Graph neural networks for multivariate time series regression with application to seismic data

Machine learning, with its advances in deep learning has shown great potential in analyzing time series. In many scenarios, however, additional information that can potentially improve the predictions is available. This is crucial for data that arise from e. g., sensor networks that contain information about sensor locations. Then, such spatial information can be exploited by modeling it via graph structures, along with the sequential (time series) information. Recent advances in adapting deep learning to graphs have shown potential in various tasks. However, these methods have not been adapted for time series tasks to a great extent. Most attempts have essentially consolidated around time series forecasting with small sequence lengths. Generally, these architectures are not well suited for regression or classification tasks where the value to be predicted is not strictly depending on the most recent values, but rather on the whole length of the time series. We propose TISER-GCN, a novel graph neural network architecture for processing, in particular, these long time series in a multivariate regression task. Our proposed model is tested on two seismic datasets containing earthquake waveforms, where the goal is to predict maximum intensity measurements of ground shaking at each seismic station. Our findings demonstrate promising results of our approach—with an average MSE reduction of 16.3%—compared to the best performing baselines. In addition, our approach matches the baseline scores by needing only half the input size. The results are discussed in depth with an additional ablation study.

Intelligent wearable system with accurate detection of abnormal gait and timely cueing for mobility enhancement of people with Parkinson's disease

Previously reported wearable systems for people with Parkinson's disease (PD) have been focused on the detection of abnormal gait. They suffered from limited accuracy, large latency, poor durability, comfort, and convenience for daily use. Herewith we report an intelligent wearable system (IWS) that can accurately detect abnormal gait in real-time and provide timely cueing for PD patients. The system features novel sensitive, comfortable and durable plantar pressure sensing insoles with a highly compressed data set, an accurate and fast gait algorithm, and wirelessly controlled timely sensory cueing devices. A total of 29 PD patients participated in the first phase without cueing for developing processes of the algorithm, which achieved an accuracy of over 97% for off-line detection of freezing of gait (FoG). In the second phase with cueing, the evaluation of the whole system was conducted with 16 PD subjects via trial and a questionnaire survey. This system demonstrated an accuracy of 94% for real-time detection of FoG and a mean latency of 0.37 s between the onset of FoG and cueing activation. In questionnaire survey, 88% of the PD participants confirmed that this wearable system could effectively enhance walking, 81% thought that the system was comfortable and convenient, and 70% overcame the FoG. Therefore, the IWS makes it an effective, powerful, and convenient tool for enhancing the mobility of people with PD.

Prediction of Freezing of Gait in Parkinson's Disease Using Unilateral and Bilateral Plantar-Pressure Data

Background

Freezing of gait (FOG) is an intermittent walking disturbance experienced by people with Parkinson's disease (PD). FOG has been linked to falling, injury, and overall reduced mobility. Wearable sensor-based devices can detect freezes already in progress and provide a cue to help the person resume walking. While this is helpful, predicting FOG episodes before onset and providing a timely cue may prevent the freeze from occurring. Wearable sensors mounted on various body parts have been used to develop FOG prediction systems. Despite the known asymmetry of PD motor symptom manifestation, the difference between the most affected side (MAS) and least affected side (LAS) is rarely considered in FOG detection and prediction studies.

Methods

To examine the effect of using data from the MAS, LAS, or both limbs for FOG prediction, plantar pressure data were collected during a series of walking trials and used to extract time and frequency-based features. Three datasets were created using plantar pressure data from the MAS, LAS, and both sides together. ReliefF feature selection was performed. FOG prediction models were trained using the top 5, 10, 15, 20, 25, or 30 features for each dataset.

Results

The best models were the MAS model with 15 features and the LAS and bilateral models with 5 features. The LAS model had the highest sensitivity (79.5%) and identified the highest percentage of FOG episodes (94.9%). The MAS model achieved the highest specificity (84.9%) and lowest false positive rate (1.9 false positives/walking trial). Overall, the bilateral model was best with 77.3% sensitivity and 82.9% specificity. In addition, the bilateral model identified 94.2% of FOG episodes an average of 0.8 s before FOG onset. Compared to the bilateral model, the LAS model had a higher false positive rate; however, the bilateral and LAS models were similar in all the other evaluation metrics.

Conclusion

The LAS model would have similar FOG prediction performance to the bilateral model at the cost of slightly more false positives. Given the advantages of single sensor systems, the increased false positive rate may be acceptable to people with PD. Therefore, a single plantar pressure sensor placed on the LAS could be used to develop a FOG prediction system and produce performance similar to a bilateral system.

Modelling and identification of characteristic kinematic features preceding freezing of gait with convolutional neural networks and layer-wise relevance propagation

BACKGROUND

Although deep neural networks (DNNs) are showing state of the art performance in clinical gait analysis, they are considered to be black-box algorithms. In other words, there is a lack of direct understanding of a DNN's ability to identify relevant features, hindering clinical acceptance. Interpretability methods have been developed to ameliorate this concern by providing a way to explain DNN predictions.

METHODS

This paper proposes the use of an interpretability method to explain DNN decisions for classifying the movement that precedes freezing of gait (FOG), one of the most debilitating symptoms of Parkinson's disease (PD). The proposed two-stage pipeline consists of (1) a convolutional neural network (CNN) to model the reduction of movement present before a FOG episode, and (2) layer-wise relevance propagation (LRP) to visualize the underlying features that the CNN perceives as important to model the pathology. The CNN was trained with the sagittal plane kinematics from a motion capture dataset of fourteen PD patients with FOG. The robustness of the model predictions and learned features was further assessed on fourteen PD patients without FOG and fourteen age-matched healthy controls.

RESULTS

The CNN proved highly accurate in modelling the movement that precedes FOG, with 86.8% of the strides being correctly identified. However, the CNN model was unable to model the movement for one of the seven patients that froze during the protocol. The LRP interpretability case study shows that (1) the kinematic features perceived as most relevant by the CNN are the reduced peak knee flexion and the fixed ankle dorsiflexion during the swing phase, (2) very little relevance for FOG is observed in the PD patients without FOG and the healthy control subjects, and (3) the poor predictive performance of one subject is attributed to the patient's unique and severely flexed gait signature.

CONCLUSIONS

The proposed pipeline can aid clinicians in explaining DNN decisions in clinical gait analysis and aid machine learning practitioners in assessing the generalization of their models by ensuring that the predictions are based on meaningful kinematic features.

Prediction and detection of freezing of gait in Parkinson's disease from plantar pressure data using long short-term memory neural-networks

Background

Freezing of gait (FOG) is a walking disturbance in advanced stage Parkinson’s disease (PD) that has been associated with increased fall risk and decreased quality of life. Freezing episodes can be mitigated or prevented with external intervention such as visual or auditory cues, activated by FOG prediction and detection systems. While most research on FOG detection and prediction has been based on inertial measurement unit (IMU) and accelerometer data, plantar-pressure data may capture subtle weight shifts unique to FOG episodes. Different machine learning algorithms have been used for FOG detection and prediction; however, long short-term memory (LSTM) deep learning methods hold an advantage when dealing with time-series data, such as sensor data. This research aimed to determine if LSTM can be used to detect and predict FOG from plantar pressure data alone, specifically for use in a real-time wearable system.

Methods

Plantar pressure data were collected from pressure-sensing insole sensors worn by 11 participants with PD as they walked a predefined freeze-provoking path. FOG instances were labelled, 16 features were extracted, and the dataset was balanced and normalized (z-score). The resulting datasets were classified using long short-term memory neural-network models. Separate models were trained for detection and prediction. For prediction models, data before FOG were included in the target class. Leave-one-freezer-out cross validation was used for model evaluation. In addition, the models were tested on all non-freezer data to determine model specificity.

Results

The best FOG detection model had 82.1% (SD 6.2%) mean sensitivity and 89.5% (SD 3.6%) mean specificity for one-freezer-held-out cross validation. Specificity improved to 93.3% (SD 4.0%) when ignoring inactive state data (standing) and analyzing the model only on active states (turning and walking). The model correctly detected 95% of freeze episodes. The best FOG prediction method achieved 72.5% (SD 13.6%) mean sensitivity and 81.2% (SD 6.8%) mean specificity for one-freezer-held-out cross validation.

Conclusions

Based on FOG data collected in a laboratory, the results suggest that plantar pressure data can be used for FOG detection and prediction. However, further research is required to improve FOG prediction performance, including training with a larger sample of people who experience FOG.

A Comparative Study of Time Frequency Representation Techniques for Freeze of Gait Detection and Prediction

Freezing of Gait (FOG) is an impairment that affects the majority of patients in the advanced stages of Parkinson's Disease (PD). FOG can lead to sudden falls and injuries, negatively impacting the quality of life for the patients and their families. Rhythmic Auditory Stimulation (RAS) can be used to help patients recover from FOG and resume normal gait. RAS might be ineffective due to the latency between the start of a FOG event, its detection and initialization of RAS. We propose a system capable of both FOG prediction and detection using signals from tri-axial accelerometer sensors that will be useful in initializing RAS with minimal latency. We compared the performance of several time frequency analysis techniques, including moving windows extracted from the signals, handcrafted features, Recurrence Plots (RP), Short Time Fourier Transform (STFT), Discreet Wavelet Transform (DWT) and Pseudo Wigner Ville Distribution (PWVD) with Deep Learning (DL) based Long Short Term Memory (LSTM) and Convolutional Neural Networks (CNN). We also propose three Ensemble Network Architectures that combine all the time frequency representations and DL architectures. Experimental results show that our ensemble architectures significantly improve the performance compared with existing techniques. We also present the results of applying our method trained on a publicly available dataset to data collected from patients using wearable sensors in collaboration with A.T. Still University.

Prediction of Freezing of Gait in Parkinson's Disease Using a Random Forest Model Based on an Orthogonal Experimental Design: A Pilot Study

Purpose

The purpose of this study was to introduce an orthogonal experimental design (OED) to improve the efficiency of building and optimizing models for freezing of gait (FOG) prediction.

Methods

A random forest (RF) model was developed to predict FOG by using acceleration signals and angular velocity signals to recognize possible precursor signs of FOG (preFOG). An OED was introduced to optimize the feature extraction parameters.

Results

The main effects and interaction among the feature extraction hyperparameters were analyzed. The false-positive rate, hit rate, and mean prediction time (MPT) were 27%, 68%, and 2.99 s, respectively.

Conclusion

The OED was an effective method for analyzing the main effects and interactions among the feature extraction parameters. It was also beneficial for optimizing the feature extraction parameters of the FOG prediction model.

Data-Driven Prediction of Freezing of Gait Events From Stepping Data

Freezing of gait (FoG) is typically a symptom of advanced Parkinson's disease (PD) that negatively influences the quality of life and is often resistant to pharmacological interventions. Novel treatment options that make use of auditory or sensory cues might be optimized by prediction of freezing events. These predictions might help to trigger external sensory cues—shown to improve walking performance—when behavior is changed in a manner indicative of an impending freeze (i.e., when the user needs it the most), rather than delivering cue information continuously. A data-driven approach is proposed for predicting freezing events using Random Forrest (RF), Neural Network (NN), and Naive Bayes (NB) classifiers. Vertical forces, sampled at 100 Hz from a force platform were collected from 9 PD subjects as they stepped in place until they at least had one freezing episode or for 90 s. The F1 scores of RF/NN/NB algorithms were computed for different IL (input to the machine learning algorithm), and GL (how early the freezing event is predicted). A significant negative correlation between the F1 scores and GL, highlighting the difficulty of early detection is found. The IL that maximized the F1 score is approximately equal to 1.13 s. This indicates that the physiological (and therefore neurological) changes leading to freezing take effect at-least one step before the freezing incident. Our algorithm has the potential to support the development of devices to detect and then potentially prevent freezing events in people with Parkinson's which might occur if left uncorrected.

Prediction of Freezing of Gait in Parkinson's Disease from Foot Plantar-Pressure Arrays using a Convolutional Neural Network

Freezing of gait (FOG) is a sudden cessation of locomotion in advanced Parkinson's disease (PD). A FOG episode can lead to falls, decreased mobility, and decreased overall quality of life. Prediction of FOG episodes provides an opportunity for intervention and freeze prevention. A novel method of FOG prediction that uses foot plantar pressure data acquired during gait was developed and evaluated, with plantar pressure data treated as 2D images and classified using a convolutional neural network (CNN). Data from five people with PD and a history of FOG were collected during walking trials. FOG instances were identified and data preceding each freeze were labeled as Pre-FOG. Left and right foot FScan pressure frames were concatenated into a single 60x42 pressure array. Each frame was considered as an independent image and classified as Pre-FOG, FOG, or Non-FOG, using the CNN. From prediction models using different Pre-FOG durations, shorter Pre-FOG durations performed best, with Pre-FOG class sensitivity 94.3%, and specificity 95.1%. These results demonstrated that foot pressure distribution alone can be a good FOG predictor when treating each plantar pressure frame as a 2D image, and classifying the images using a CNN. Furthermore, the CNN eliminated the need for feature extraction and selection.Clinical Relevance- This research demonstrated that foot plantar pressure data can be used to predict freezing of gait occurrence, using a convolutional neural network deep learning technique. This had the added advantage of eliminating the need for feature extraction and selection.

Prediction of Freezing of Gait in Patients With Parkinson's Disease by Identifying Impaired Gait Patterns

Freezing of gait (FoG) prediction, combined with rhythmic laser cues, may help Parkinson's disease (PD) patients overcome FoG episodes. This study aimed to utilize the impaired gait patterns preceding FoG to build a machine-learning-based model for FoG prediction. Acceleration signals were collected using an accelerometer attached to the lower back of 12 PD patients with FoG while they were performing designed FoG-provoking walking tasks. Step-based impaired gait features and conventional FoG detection features were extracted from the signals, based on which two FoG prediction models were built using AdaBoost to validate if the use of the impaired gait features can better predict FoG. For the correct labeling of the gait prior to FoG (pre-FoG), the personalized pre-FoG phase was defined according to the slope of the impaired gait pattern. The impaired gait features were relabeled based on the pre-FoG phase upon which the personalized labeled FoG prediction model was built. This was compared with the model built using unified labeling. Results showed that impaired gait features could better predict FoG than conventional FoG detection features with low time latency, and personalized labeling could further improve the FoG prediction accuracy. Using impaired gait features and personalized labeling, we built a FoG prediction model with 0.93 sec of latency. Compared to using conventional features and unified labeling, our model achieved 5.7% higher accuracy (82.7%) in patient-dependent test and 9.8% higher accuracy (77.9%) in patient-independent test. Therefore, using the impaired gait patterns is a promising approach to accurately predict FoG with low latency.

Toward a Wearable System for Predicting Freezing of Gait in People Affected by Parkinson's Disease

Some wearable solutions exploiting on-body acceleration sensors have been proposed to recognize Freezing of Gait (FoG) in people affected by Parkinson Disease (PD). Once a FoG event is detected, these systems generate a sequence of rhythmic stimuli to allow the patient restarting the gait. While these solutions are effective in detecting FoG events, they are unable to predict FoG to prevent its occurrence. This paper fills in the gap by presenting a machine learning-based approach that classifies accelerometer data from PD patients, recognizing a pre-FOG phase to further anticipate FoG occurrence in advance. Gait was monitored by three tri-axial accelerometer sensors worn on the back, hip and ankle. Gait features were then extracted from the accelerometer's raw data through data windowing and non-linear dimensionality reduction. A k-nearest neighbor algorithm (k-NN) was used to classify gait in three classes of events: pre-FoG, no-FoG and FoG. The accuracy of the proposed solution was compared to state-of-the-art approaches. Our study showed that: (i) we achieved performances overcoming the state-of-the-art approaches in terms of FoG detection, (ii) we were able, for the very first time in the literature, to predict FoG by identifying the pre-FoG events with an average sensitivity and specificity of, respectively, 94.1% and 97.1%, and (iii) our algorithm can be executed on resource-constrained devices. Future applications include the implementation on a mobile device, and the administration of rhythmic stimuli by a wearable device to help the patient overcome the FoG.

Prediction of Gait Freezing in Parkinsonian Patients: A Binary Classification Augmented With Time Series Prediction

This paper presents a novel technique to predict freezing of gait in advanced stage Parkinsonian patients using movement data from wearable sensors. A two-class approach is presented which consists of autoregressive predictive models to project the feature time series, followed by machine learning based classifiers to discriminate freezing from nonfreezing based on the predicted features. To implement and validate our technique a set of time domain and frequency domain features were extracted from the 3D acceleration data, which was then analyzed using information theoretic and feature selection approaches to determine the most discriminative features. Predictive models were trained to predict the features from their past values, then fed into binary classifiers based on support vector machines and probabilistic neural networks which were rigorously cross validated. We compared the results of this approach with a three-class classification approach proposed in previous literature, in which a pre-freezing class was introduced and the problem of prediction of the gait freezing incident was reduced to solving a three-class classification problem. The two-class approach resulted in a sensitivity of 93±4%, specificity of 91±6%, with an expected prediction horizon of 1.72 s. Our subject-specific gait freezing prediction algorithm outperformed existing algorithms, yields consistent results across different subjects and is robust against the choice of classifier, with slight variations in the selected features. In addition, we analyzed the merits and limitations of different families of features to predict gait freezing.

Prediction of Freezing of Gait in Parkinson's Disease Using Statistical Inference and Lower-Limb Acceleration Data

The freezing of gait (FoG) is a common type of motor dysfunction in advanced Parkinson's disease (PD) associated with falls. Over the last decade, a significant amount of studies has been focused on detecting FoG episodes in clinical and home environments. Yet, there remains a paucity of techniques regarding real-time prediction of FoG before its occurrence. In this paper, a new algorithm was employed to define the best combination of sensor position, axis, sampling window length, and features to predict FoG. We hypothesized that gait deterioration before FoG onsets can be discriminated from normal gait using statistical analysis of features from successive windows of data collected from lower-limb accelerometers. We defined a new performance measure, "predictivity", to compare the number of correctly predicted FoG events among different combinations. We characterized the system performance using data from 10 PD patients, who experienced FoG while performing several walking tasks in a lab environment. The analysis of 120 different combinations revealed that prediction of FoG can be realized by using an individual shank sensor and sample entropy calculated from the horizontal forward axis with window length of 2 s (88.8%, 92.5%, and 89.0% for average predictivity, sensitivity, and specificity, respectively).

Non-invasive detection of the freezing of gait in Parkinson's disease using spectral and wavelet features

In this study, we have analyzed the accelerometer data recorded during gait analysis of Parkinson disease patients for detecting freezing of gait (FOG) episodes. The proposed method filters the recordings for noise reduction of the leg movement changes and computes the wavelet coefficients to detect FOG events. Publicly available FOG database was used and the technique was evaluated using receiver operating characteristic (ROC) analysis. Results show a higher performance of the wavelet feature in discrimination of the FOG events from the background activity when compared with the existing technique.

Home detection of freezing of gait using support vector machines through a single waist-worn triaxial accelerometer

Among Parkinson’s disease (PD) symptoms, freezing of gait (FoG) is one of the most debilitating. To assess FoG, current clinical practice mostly employs repeated evaluations over weeks and months based on questionnaires, which may not accurately map the severity of this symptom. The use of a non-invasive system to monitor the activities of daily living (ADL) and the PD symptoms experienced by patients throughout the day could provide a more accurate and objective evaluation of FoG in order to better understand the evolution of the disease and allow for a more informed decision-making process in making adjustments to the patient’s treatment plan. This paper presents a new algorithm to detect FoG with a machine learning approach based on Support Vector Machines (SVM) and a single tri-axial accelerometer worn at the waist. The method is evaluated through the acceleration signals in an outpatient setting gathered from 21 PD patients at their home and evaluated under two different conditions: first, a generic model is tested by using a leave-one-out approach and, second, a personalised model that also uses part of the dataset from each patient. Results show a significant improvement in the accuracy of the personalised model compared to the generic model, showing enhancement in the specificity and sensitivity geometric mean (GM) of 7.2%. Furthermore, the SVM approach adopted has been compared to the most comprehensive FoG detection method currently in use (referred to as MBFA in this paper). Results of our novel generic method provide an enhancement of 11.2% in the GM compared to the MBFA generic model and, in the case of the personalised model, a 10% of improvement with respect to the MBFA personalised model. Thus, our results show that a machine learning approach can be used to monitor FoG during the daily life of PD patients and, furthermore, personalised models for FoG detection can be used to improve monitoring accuracy.

Gait Monitoring for Early Neurological Disorder Detection Using Sensors in a Smartphone: Validation and a Case Study of Parkinsonism

BACKGROUND

Diagnosing brain disorders, such as Parkinson's disease (PD) or Alzheimer's disease, is often difficult, especially in the early stages. Moreover, it has been estimated that nearly 40% of people with PD may not be diagnosed. Traditionally, the diagnosis of neurological disorders, such as PD, often required a doctor to observe the patient over time to recognize signs of rigidity in movement.

MATERIALS AND METHODS

The pedestrian dead reckoning (PDR) system is a self-contained technique that has been widely used for indoor localization. In this work we propose a PDR-based method to continuously monitor and record the patient's gait characteristics using a smartphone. Seventeen patients were studied over a period of 1 year. During the year it became apparent that 1 of the patients was actually developing PD. To the best of our knowledge, our work is the first attempt to use sensors in a smartphone to help identify patients in their early stages of neurological disease.

RESULTS

On average, the accuracy of our step length estimation was about 98%. Using a binary classification method-namely, support vector machine-we carried out a case study and showed that it was feasible to identify changes in the walking patterns of a PD patient with an accuracy of 94%.

CONCLUSIONS

Using 1 year of gait trace data obtained from the users' phones, our work provides a first step to experimentally show the possibility of applying smartphone sensor data to provide early warnings to potential PD patients to encourage them to seek medical assistance and thus help doctors diagnose this disease earlier.

Hausdorff J, Tröster G. A Wearable Assistant for Gait Training for Parkinson’s Disease with Freezing of Gait in Out-of-the-Lab Environments

People with Parkinson’s disease (PD) suffer from declining mobility capabilities, which cause a prevalent risk of falling. Commonly, short periods of motor blocks occur during walking, known as freezing of gait (FoG). To slow the progressive decline of motor abilities, people with PD usually undertake stationary motor-training exercises in the clinics or supervised by physiotherapists. We present a wearable system for the support of people with PD and FoG. The system is designed for independent use. It enables motor training and gait assistance at home and other unsupervised environments. The system consists of three components. First, FoG episodes are detected in real time using wearable inertial sensors and a smartphone as the processing unit. Second, a feedback mechanism triggers a rhythmic auditory signal to the user to alleviate freeze episodes in an assistive mode. Third, the smartphone-based application features support for training exercises. Moreover, the system allows unobtrusive and long-term monitoring of the user’s clinical condition by transmitting sensing data and statistics to a telemedicine service.

We investigate the at-home acceptance of the wearable system in a study with nine PD subjects. Participants deployed and used the system on their own, without any clinical support, at their homes during three protocol sessions in 1 week. Users’ feedback suggests an overall positive attitude toward adopting and using the system in their daily life, indicating that the system supports them in improving their gait. Further, in a data-driven analysis with sensing data from five participants, we study whether there is an observable effect on the gait during use of the system. In three out of five subjects, we observed a decrease in FoG duration distributions over the protocol days during gait-training exercises. Moreover, sensing data-driven analysis shows a decrease in FoG duration and FoG number in four out of five participants when they use the system as a gait-assistive tool during normal daily life activities at home.