A wavelet-based approach to monitoring Parkinson's disease symptoms

  title={A wavelet-based approach to monitoring Parkinson's disease symptoms},
  author={Avishai Wagner and Naama Fixler and Yehezkel S. Resheff},
  journal={2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
Parkinson's disease is a neuro-degenerative disorder affecting tens of millions of people worldwide. Lately, there has been considerable interest in systems for at-home monitoring of patients, using wearable devices which contain inertial measurement units. We present a new wavelet-based approach for analysis of data from single wrist-worn smart-watches, and show high detection performance for tremor, bradykinesia, and dyskinesia, which have been the major targets for monitoring in this context… 

Figures and Tables from this paper

Task-Oriented Intelligent Solution to Measure Parkinson's Disease Tremor Severity
The findings of this study suggest that a recommended system consists of support vector machine (SVM) classifier combined with BorderlineSMOTE oversampling technique and data collection while performing set of recommended tasks, which are sitting, stairs up and down, walking straight, walking while counting, and standing.
Body-Worn Sensors for Remote Monitoring of Parkinson’s Disease Motor Symptoms: Vision, State of the Art, and Challenges Ahead
A roadmap with clear recommendations for addressing challenges and future directions is proposed to bring us closer to the implementation and widespread adoption of remote monitoring with body-worn sensors for improving the clinical care, evaluation, and monitoring of PD.
Real-Time Schizophrenia Monitoring Using Wearable Motion Sensitive Devices
Results are presented showing correlations between features of activity in various daily time-windows, and measures derived from the psychiatrist’s clinical assessment or abnormal events in the patients’ routine.
Topic models for automated motor analysis in schizophrenia patients
This paper uses topic models for unsupervised analysis of movement activity of schizophrenia patients in a closed ward setting and designs a classifier which correctly classified up to 80% of the clinical sub-population based on motor features.
ARIMA-based motor anomaly detection in schizophrenia inpatients
The use of ARIMA-based anomaly detection for monitoring of patient motor activity in a closed ward hospital setting is described and the utility of the approach is demonstrated in several intriguing case studies.
Early Detection of Parkinson’s Disease Using Deep Learning and Machine Learning
A comparison between the proposed deep learning model and twelve machine learning and ensemble learning methods based on relatively small data shows the superior detection performance of the designed model, which achieves the highest accuracy, 96.45% on average.


Home monitoring of patients with Parkinson's disease via wearable technology and a web-based application
The work herein presented shows that wearable sensors combined with a web-based application provide reliable quantitative information that can be used for clinical decision making.
Quantitative wearable sensors for objective assessment of Parkinson's disease
This review discusses promising wearable technology, addresses which parameters should be prioritized in such assessment strategies, and reports about studies that have already investigated daily life issues in PD using this new technology.
Detecting and monitoring the symptoms of Parkinson's disease using smartphones: A pilot study.
Clinically deployable Kinesia™ technology for automated tremor assessment
In this study, PD subjects performed the tremor subset of the UPDRS motor section while wearing Kinesia, a wireless system for automated assessment of Parkinson's disease tremor and indicated high clinical acceptance.
Quantification of limb bradykinesia in patients with Parkinson’s disease using a gyrosensor — Improvement and validation
The convenient sensor system, action tremor elimination, and performance indices suggested in this study are expected to be useful in clinical situations.
Correlation between Kinesia system assessments and clinical tremor scores in patients with essential tremor
It is concluded that the Kinesia system may, therefore, have a utility in quantitative assessments of ET when combined with standard clinical assessment.
SHIMMER: A new tool for temporal gait analysis
Temporal gait parameters derived from a tri-axial gyroscope contained in the SHIMMER are compared against those acquired simultaneously using the CODA motion analysis system and suggest that the SH IMMER is a versatile cost effective tool for use in temporal gait analysis.
Movement Disorder Society‐sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS‐UPDRS): Scale presentation and clinimetric testing results
  • C. GoetzB. Tilley N. Lapelle
  • Psychology, Medicine
    Movement disorders : official journal of the Movement Disorder Society
  • 2008
The combined clinimetric results of this study support the validity of the MDS‐UPDRS for rating PD.
Clustering Noisy Signals with Structured Sparsity Using Time-Frequency Representation
The sparse K-means algorithm is extended by incorporating structured sparsity, and the scattering transform is used, which corresponds to a convolutional network with filters given by a wavelet operator, and use the network's structure in sparse clustering.
Clustering Functional Data using Wavelets
Two methods for detecting patterns and clusters in high dimensional time-dependent functional data based on wavelet-based similarity measures that jointly designs both the feature selection in the wavelet domain and the classification distance are presented.