Deep Learning Approaches for Detecting Freezing of Gait in Parkinson’s Disease Patients through On-Body Acceleration Sensors

Freezing of gait (FOG) is one of the most incapacitating motor symptoms in Parkinson’s disease (PD). The occurrence of FOG reduces the patients’ quality of live and leads to falls. FOG assessment has usually been made through questionnaires, however, this method can be subjective and could not provide an accurate representation of the severity of this symptom. The use of sensor-based systems can provide accurate and objective information to track the symptoms’ evolution to optimize PD management and treatments. Several authors have proposed specific methods based on wearables and the analysis of inertial signals to detect FOG in laboratory conditions, however, its performance is usually lower when being used at patients’ homes. This study presents a new approach based on a recurrent neural network (RNN) and a single waist-worn triaxial accelerometer to enhance the FOG detection performance to be used in real home-environments. Also, several machine and deep learning approaches for FOG detection are evaluated using a leave-one-subject-out (LOSO) cross-validation. Results show that modeling spectral information of adjacent windows through an RNN can bring a significant improvement in the performance of FOG detection without increasing the length of the analysis window (required to using it as a cue-system).

Download Full-text

DeepFoG: An IMU-Based Detection of Freezing of Gait Episodes in Parkinson’s Disease Patients via Deep Learning

Frontiers in Robotics and AI ◽

10.3389/frobt.2021.537384 ◽

2021 ◽

Vol 8 ◽

Author(s):

Thomas Bikias ◽

Dimitrios Iakovakis ◽

Stelios Hadjidimitriou ◽

Vasileios Charisis ◽

Leontios J. Hadjileontiadis

Keyword(s):

Quality Of Life ◽

Parkinson’S Disease ◽

Parkinson's Disease ◽

Deep Learning ◽

Life Stress ◽

Freezing Of Gait ◽

Measurement Unit ◽

Effective Interventions ◽

Risk Of Falls

Freezing of Gait (FoG) is a movement disorder that mostly appears in the late stages of Parkinson’s Disease (PD). It causes incapability of walking, despite the PD patient’s intention, resulting in loss of coordination that increases the risk of falls and injuries and severely affects the PD patient’s quality of life. Stress, emotional stimulus, and multitasking have been encountered to be associated with the appearance of FoG episodes, while the patient’s functionality and self-confidence are constantly deteriorating. This study suggests a non-invasive method for detecting FoG episodes, by analyzing inertial measurement unit (IMU) data. Specifically, accelerometer and gyroscope data from 11 PD subjects, as captured from a single wrist-worn IMU sensor during continuous walking, are processed via Deep Learning for window-based detection of the FoG events. The proposed approach, namely DeepFoG, was evaluated in a Leave-One-Subject-Out (LOSO) cross-validation (CV) and 10-fold CV fashion schemes against its ability to correctly estimate the existence or not of a FoG episode at each data window. Experimental results have shown that DeepFoG performs satisfactorily, as it achieves 83%/88% and 86%/90% sensitivity/specificity, for LOSO CV and 10-fold CV schemes, respectively. The promising performance of the proposed DeepFoG reveals the potentiality of single-arm IMU-based real-time FoG detection that could guide effective interventions via stimuli, such as rhythmic auditory stimulation (RAS) and hand vibration. In this way, DeepFoG may scaffold the elimination of risk of falls in PD patients, sustaining their quality of life in everyday living activities.

Download Full-text

Improved Deep Learning Technique to Detect Freezing of Gait in Parkinson’s Disease Based on Wearable Sensors

Electronics ◽

10.3390/electronics9111919 ◽

2020 ◽

Vol 9 (11) ◽

pp. 1919

Author(s):

Bochen Li ◽

Zhiming Yao ◽

Jianguo Wang ◽

Shaonan Wang ◽

Xianjun Yang ◽

...

Keyword(s):

Neural Network ◽

Parkinson’S Disease ◽

Parkinson's Disease ◽

Deep Learning ◽

Cross Validation ◽

Freezing Of Gait ◽

Detection Performance ◽

Operating Efficiency ◽

The Impact ◽

Fog Detection

Freezing of gait (FOG) is a paroxysmal dyskinesia, which is common in patients with advanced Parkinson’s disease (PD). It is an important cause of falls in PD patients and is associated with serious disability. In this study, we implemented a novel FOG detection system using deep learning technology. The system takes multi-channel acceleration signals as input, uses one-dimensional deep convolutional neural network to automatically learn feature representations, and uses recurrent neural network to model the temporal dependencies between feature activations. In order to improve the detection performance, we introduced squeeze-and-excitation blocks and attention mechanism into the system, and used data augmentation to eliminate the impact of imbalanced datasets on model training. Experimental results show that, compared with the previous best results, the sensitivity and specificity obtained in 10-fold cross-validation evaluation were increased by 0.017 and 0.045, respectively, and the equal error rate obtained in leave-one-subject-out cross-validation evaluation was decreased by 1.9%. The time for detection of a 256 data segment is only 0.52 ms. These results indicate that the proposed system has high operating efficiency and excellent detection performance, and is expected to be applied to FOG detection to improve the automation of Parkinson’s disease diagnosis and treatment.

Download Full-text

Effects of music-based movement therapy on motor function, balance, gait, mental health, and quality of life for patients with Parkinson’s disease: A systematic review and meta-analysis

Clinical Rehabilitation ◽

10.1177/0269215521990526 ◽

2021 ◽

pp. 026921552199052

Author(s):

Zonglei Zhou ◽

Ruzhen Zhou ◽

Wen Wei ◽

Rongsheng Luan ◽

Kunpeng Li

Keyword(s):

Quality Of Life ◽

Mental Health ◽

Parkinson’S Disease ◽

Parkinson's Disease ◽

Motor Function ◽

Meta Analysis ◽

Freezing Of Gait ◽

Movement Therapy ◽

Walking Velocity

Objective: To conduct a systematic review evaluating the effects of music-based movement therapy on motor function, balance, gait, mental health, and quality of life among individuals with Parkinson’s disease. Data sources: A systematic search of PubMed, Embase, Cochrane Library, Web of Science, PsycINFO, CINAHL, and Physiotherapy Evidence Database was carried out to identify eligible papers published up to December 10, 2020. Review methods: Literature selection, data extraction, and methodological quality assessment were independently performed by two investigators. Publication bias was determined by funnel plot and Egger’s regression test. “Trim and fill” analysis was performed to adjust any potential publication bias. Results: Seventeen studies involving 598 participants were included in this meta-analysis. Music-based movement therapy significantly improved motor function (Unified Parkinson’s Disease Rating Scale motor subscale, MD = −5.44, P = 0.002; Timed Up and Go Test, MD = −1.02, P = 0.001), balance (Berg Balance Scale, MD = 2.02, P < 0.001; Mini-Balance Evaluation Systems Test, MD = 2.95, P = 0.001), freezing of gait (MD = −2.35, P = 0.039), walking velocity (MD = 0.18, P < 0.001), and mental health (SMD = −0.38, P = 0.003). However, no significant effects were observed on gait cadence, stride length, and quality of life. Conclusion: The findings of this study show that music-based movement therapy is an effective treatment approach for improving motor function, balance, freezing of gait, walking velocity, and mental health for patients with Parkinson’s disease.

Download Full-text

Group-based music intervention in Parkinson’s disease – findings from a mixed-methods study

Clinical Rehabilitation ◽

10.1177/0269215520907669 ◽

2020 ◽

Vol 34 (4) ◽

pp. 533-544

Author(s):

Petra Pohl ◽

Ewa Wressle ◽

Fredrik Lundin ◽

Paul Enthoven ◽

Nil Dizdar

Keyword(s):

Quality Of Life ◽

Parkinson’S Disease ◽

Parkinson's Disease ◽

Freezing Of Gait ◽

Intervention Group ◽

Group Differences ◽

Control Group ◽

Music Intervention ◽

Post Intervention

Objective: To evaluate a group-based music intervention in patients with Parkinson’s disease. Design: Parallel group randomized controlled trial with qualitative triangulation. Setting: Neurorehabilitation in primary care. Subjects: Forty-six patients with Parkinson’s disease were randomized into intervention group ( n = 26), which received training with the music-based intervention, and control group ( n = 20) without training. Interventions: The intervention was delivered twice weekly for 12 weeks. Main measures: Primary outcome was Timed-Up-and-Go subtracting serial 7’s (dual-task ability). Secondary outcomes were cognition, balance, concerns about falling, freezing of gait, and quality of life. All outcomes were evaluated at baseline, post-intervention, and three months post-intervention. Focus groups and individual interviews were conducted with the intervention group and with the delivering physiotherapists. Results: No between-group differences were observed for dual-task ability. Between-group differences were observed for Falls Efficacy Scale (mean difference (MD) = 6.5 points; 95% confidence interval (CI) = 3.0 to 10.0, P = 0.001) and for Parkinson Disease Questionnaire-39 items (MD = 8.3; 95% CI = 2.7 to 13.8, P = 0.005) when compared to the control group post-intervention, but these were not maintained at three months post-intervention. Three themes were derived from the interviews: Expectations versus Results, Perspectives on Treatment Contents, and Key Factors for Success. Conclusion: Patient-reported outcomes and interviews suggest that the group-based music intervention adds value to mood, alertness, and quality of life in patients with Parkinson’s disease. The study does not support the efficacy in producing immediate or lasting gains in dual-tasking, cognition, balance, or freezing of gait.

Download Full-text

Deep learning for freezing of gait detection in Parkinson’s disease patients in their homes using a waist-worn inertial measurement unit

Knowledge-Based Systems ◽

10.1016/j.knosys.2017.10.017 ◽

2018 ◽

Vol 139 ◽

pp. 119-131 ◽

Cited By ~ 55

Author(s):

Julià Camps ◽

Albert Samà ◽

Mario Martín ◽

Daniel Rodríguez-Martín ◽

Carlos Pérez-López ◽

...

Keyword(s):

Parkinson’S Disease ◽

Parkinson's Disease ◽

Deep Learning ◽

Inertial Measurement Unit ◽

Freezing Of Gait ◽

Measurement Unit ◽

Inertial Measurement

Download Full-text

The major impact of freezing of gait on quality of life in Parkinson’s disease

Journal of Neurology ◽

10.1007/s00415-014-7524-3 ◽

2014 ◽

Vol 262 (1) ◽

pp. 108-115 ◽

Cited By ~ 58

Author(s):

Courtney C. Walton ◽

James M. Shine ◽

Julie M. Hall ◽

Claire O’Callaghan ◽

Loren Mowszowski ◽

...

Keyword(s):

Quality Of Life ◽

Parkinson’S Disease ◽

Parkinson's Disease ◽

Freezing Of Gait

Download Full-text

A Deep Learning Approach for Classification and Diagnosis of Parkinson’s Disease

10.21203/rs.3.rs-254647/v1 ◽

2021 ◽

Author(s):

Monika Jyotiyana ◽

Nishtha Kesswani ◽

Munish Kumar

Keyword(s):

Parkinson’S Disease ◽

Parkinson's Disease ◽

Deep Learning ◽

Nearest Neighbor ◽

Health Sector ◽

Classification Model ◽

Support Vector ◽

Learning Approaches ◽

K Nearest Neighbor ◽

Linear Discriminant

Abstract Deep learning techniques are playing an important role in the classification and prediction of diseases. Undoubtedly deep learning has a promising future in the health sector, especially in medical imaging. The popularity of deep learning approaches is because of their ability to handle a large amount of data related to the patients with accuracy, reliability in a short span of time. However, the practitioners may take time in analyzing and generating reports. In this paper, we have proposed a Deep Neural Network-based classification model for Parkinson’s disease. Our proposed method is one such good example giving faster and more accurate results for the classification of Parkinson’s disease patients with excellent accuracy of 94.87%. Based on the attributes of the dataset of the patient, the model can be used for the identification of Parkinsonism's. We have also compared the results with other existing approaches like Linear Discriminant Analysis, Support Vector Machine, K-Nearest Neighbor, Decision Tree, Classification and Regression Trees, Random Forest, Linear Regression, Logistic Regression, Multi-Layer Perceptron, and Naive Bayes.

Download Full-text

A Technological Review of Wearable Cueing Devices Addressing Freezing of Gait in Parkinson’s Disease

Sensors ◽

10.3390/s19061277 ◽

2019 ◽

Vol 19 (6) ◽

pp. 1277 ◽

Cited By ~ 14

Author(s):

Dean Sweeney ◽

Leo Quinlan ◽

Patrick Browne ◽

Margaret Richardson ◽

Pauline Meskell ◽

...

Keyword(s):

Quality Of Life ◽

Parkinson’S Disease ◽

Parkinson's Disease ◽

Freezing Of Gait ◽

Review Of The Literature ◽

What Works ◽

Home Based ◽

What Works Clearinghouse ◽

Technical Operation

Freezing of gait is one of the most debilitating symptoms of Parkinson’s disease and is an important contributor to falls, leading to it being a major cause of hospitalization and nursing home admissions. When the management of freezing episodes cannot be achieved through medication or surgery, non-pharmacological methods such as cueing have received attention in recent years. Novel cueing systems were developed over the last decade and have been evaluated predominantly in laboratory settings. However, to provide benefit to people with Parkinson’s and improve their quality of life, these systems must have the potential to be used at home as a self-administer intervention. This paper aims to provide a technological review of the literature related to wearable cueing systems and it focuses on current auditory, visual and somatosensory cueing systems, which may provide a suitable intervention for use in home-based environments. The paper describes the technical operation and effectiveness of the different cueing systems in overcoming freezing of gait. The “What Works Clearinghouse (WWC)” tool was used to assess the quality of each study described. The paper findings should prove instructive for further researchers looking to enhance the effectiveness of future cueing systems.

Download Full-text

Wearable-Sensor-based Detection and Prediction of Freezing of Gait in Parkinson’s Disease: A Review

Sensors ◽

10.3390/s19235141 ◽

2019 ◽

Vol 19 (23) ◽

pp. 5141 ◽

Cited By ~ 5

Author(s):

Pardoel ◽

Kofman ◽

Nantel ◽

Lemaire

Keyword(s):

Parkinson’S Disease ◽

Parkinson's Disease ◽

Current Knowledge ◽

Wearable Sensors ◽

Freezing Of Gait ◽

Machine Learning Algorithms ◽

Model Generalization ◽

Feature Extraction And Selection ◽

Prediction Approach ◽

Fog Detection

Freezing of gait (FOG) is a serious gait disturbance, common in mid- and late-stage Parkinson’s disease, that affects mobility and increases fall risk. Wearable sensors have been used to detect and predict FOG with the ultimate aim of preventing freezes or reducing their effect using gait monitoring and assistive devices. This review presents and assesses the state of the art of FOG detection and prediction using wearable sensors, with the intention of providing guidance on current knowledge, and identifying knowledge gaps that need to be filled and challenges to be considered in future studies. This review searched the Scopus, PubMed, and Web of Science databases to identify studies that used wearable sensors to detect or predict FOG episodes in Parkinson’s disease. Following screening, 74 publications were included, comprising 68 publications detecting FOG, seven predicting FOG, and one in both categories. Details were extracted regarding participants, walking task, sensor type and body location, detection or prediction approach, feature extraction and selection, classification method, and detection and prediction performance. The results showed that increasingly complex machine-learning algorithms combined with diverse feature sets improved FOG detection. The lack of large FOG datasets and highly person-specific FOG manifestation were common challenges. Transfer learning and semi-supervised learning were promising for FOG detection and prediction since they provided person-specific tuning while preserving model generalization.

Download Full-text

Improvement of freezing of gait in patients with Parkinson’s disease by music exercise therapy: a study protocol for a randomized controlled trial

Trials ◽

10.1186/s13063-021-05258-w ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Kun-Peng Li ◽

Zong-Lei Zhou ◽

Ru-Zhen Zhou ◽

Yan Zhu ◽

Zeng-Qiao Zhang

Keyword(s):

Quality Of Life ◽

Parkinson’S Disease ◽

Parkinson's Disease ◽

Randomized Controlled Trial ◽

Clinical Efficacy ◽

Exercise Therapy ◽

Controlled Trial ◽

Freezing Of Gait ◽

Randomized Controlled

Abstract Background Progression of freezing of gait, a common pathological gait in Parkinson’s disease, is an important risk factor for diagnosing the disease and has been shown to predispose patients to easy falls, loss of independent living ability, and reduced quality of life. Treating Parkinson’s disease with freezing of gait is very difficult, while the use of medicine and operation has been ineffective. Music exercise therapy, which entails listening to music as you exercise, has been proposed as a treatment technology that can change patients’ behavior, emotions, and physiological activity. In recent years, music exercise therapy has been widely used in treatment of motor disorders and neurological diseases and achieved remarkable results. Results from our earlier pilot study revealed that music exercise therapy can improve the freezing of gait of Parkinson’s patients and improve their quality of life. Therefore, we aim to validate clinical efficacy of this therapy on freezing of gait of Parkinson’s patients using a larger sample size. Methods/design This three-arm randomized controlled trial will evaluate clinical efficacy of music exercise therapy in improving the freezing of gait in Parkinson’s patients. We will recruit a total of 81 inpatients with Parkinson’s disease, who meet the trial criteria. The patients will randomly receive music exercise with and without music as well as routine rehabilitation therapies, followed by analysis of changes in their gait and limb motor function after 4 weeks of intervention. We will first use a three-dimensional gait analysis system to evaluate changes in patients’ gait, followed by assessment of their limb function, activity of daily living and fall risk. Discussion The findings of this trial are expected to affirm the clinical application of this therapy for future management of the disease. Trial registration Chinese Clinical Trial Registry ChiCTR1900026063. Registered on September 20, 2019

Download Full-text