Early diagnosis of Parkinson's disease via machine learning on speech data
@article{Hazan2012EarlyDO, title={Early diagnosis of Parkinson's disease via machine learning on speech data}, author={Hananel Hazan and Dan Hilu and L. Manevitz and Lorraine O. Ramig and Shimon Sapir}, journal={2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel}, year={2012}, pages={1-4} }
Using two distinct data sets (from the USA and Germany) of healthy controls and patients with early or mild stages of Parkinson's disease, we show that machine learning tools can be used for the early diagnosis of Parkinson's disease from speech data. This could potentially be applicable before physical symptoms appear. In addition, we show that while the training phase of machine learning process from one country can be reused in the other; different features dominate in each country…
36 Citations
Diagnosis of Parkinson's disease from continuous speech using deep convolutional networks without manual selection of features
- Computer Science2016 IEEE International Conference on the Science of Electrical Engineering (ICSEE)
- 2016
This work focuses on automating the process of diagnosis from continuous native speech by removing the necessity of a trained personal from the diagnosis process by using an adaptation of Convolutional Neural Network architecture for one-dimensional signal processing on a relatively small training set.
Robust Feature Engineering for Parkinson Disease Diagnosis: New Machine Learning Techniques
- Computer Science
- 2020
The results are promising, showing the potential for ML in detecting symptoms imperceptible to a neurologist, and showing that the features used in prior literature do not perform well when extrapolated to the much larger mPower data set.
Machine Learning Based Automatic Prediction of Parkinson’s Disease Using Speech Features
- Computer Science
- 2020
A machine learning based automatic prediction framework is presented, which can be used to build effective decision support systems for Parkinson’s disease and significant improvements have been observed post oversampling, which suggests the potential for applicability of the approach as a decision support system in real diagnostic scenarios.
Robust Feature Engineering for Parkinson Disease Diagnosis: New Machine Learning Techniques (Preprint)
- Medicine
- 2019
The results are promising, showing the potential for ML in detecting symptoms imperceptible to a neurologist on the large mPower vocal phonation data set.
Computational Diagnosis of Parkinson's Disease Directly from Natural Speech Using Machine Learning Techniques
- Computer Science2014 IEEE International Conference on Software Science, Technology and Engineering
- 2014
This work shows that early diagnosis of Parkinson's disease is possible solely from the voice signal, and conjecture that such systems can be extended to monitoring and classifying additional neurological diseases and speech pathologies.
The Diagnosis of Parkinson's Disease Based on Gait, Speech Analysis and Machine Learning Techniques
- Computer ScienceBIC
- 2021
This review presents that machine learning has good performances for the diagnosis of PD, however, it can only be a diagnosis tool to help doctors because of its limited generalization.
Multi-Class Classification in Parkinson’s Disease by Leveraging Internal Topological Structure of the Data and of the Label Space
- Computer Science2019 International Joint Conference on Neural Networks (IJCNN)
- 2019
On the Parkinson classification task, these methods obtained results which are comparable to the best accuracy on simple two class classification, which seems relatively generic and should be applicable to many data sets.
A Two-Step Framework for Parkinson’s Disease Classification: Using Multiple One-Way ANOVA on Speech Features and Decision Trees
- Computer Science
- 2020
A novel two-step classification framework to diagnose Parkinson’s Disease (PD) using speech samples using multiple one-way ANOVAs to extract vocal features from MFCCs, WTs, and TQWTs separately and a decision-tree based classifier is trained on this training set to make predictions.
Comparison of Machine Learning Techniques for the Identification of the Stages of Parkinson’s Disease
- Computer Science
- 2016
This work performs a four-class classification using the motor assessments of subjects obtained from the Parkinson’s Progressive Markers Initiative (PPMI) database and a variety of techniques like Deep Neural Network (DNN), Support Vector Machine (SVM), Deep Belief Network (DBN) etc.
Automatic detection of expressed emotion in Parkinson's Disease
- Psychology2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- 2014
The classification of emotional speech in patients with PD and the classification of PD speech is examined to assist in the future development of automated early detection systems for diagnosing patients withPD.
References
SHOWING 1-10 OF 13 REFERENCES
Quantitative acoustic measurements for characterization of speech and voice disorders in early untreated Parkinson's disease.
- PsychologyThe Journal of the Acoustical Society of America
- 2011
It was found that measurement of the fundamental frequency variations applied to two selected tasks was the best method for separating healthy from PD subjects and it has been demonstrated that 78% of early untreated PD subjects indicate some form of vocal impairment.
Vowel articulation in Parkinson's disease.
- MedicineJournal of voice : official journal of the Voice Foundation
- 2011
Variability in fundamental frequency during speech in prodromal and incipient Parkinson's disease: A longitudinal case study
- PsychologyBrain and Cognition
- 2004
Emotional speech in Parkinson's disease
- Psychology, BiologyMovement disorders : official journal of the Movement Disorder Society
- 2008
It is suggested that alterations of emotional processing contribute to speech changes in PD, especially regarding emotional prosody, in addition to motor impairment.
Classifying cognitive states of brain activity via one-class neural networks with feature selection by genetic algorithms
- Computer ScienceInt. J. Mach. Learn. Cybern.
- 2011
It is demonstrated how one-class recognition of cognitive brain functions across multiple subjects can be performed at the 90% level of accuracy via an appropriate choice of features which can be chosen automatically.
Speech and swallowing disorders in Parkinson disease
- Medicine, PsychologyCurrent opinion in otolaryngology & head and neck surgery
- 2008
A rat model for studying neuropharmacologic effects on vocalization in Parkinson disease has been developed and changes in brain activity due to LSVT LOUD provide preliminary evidence for neural plasticity.
Intensive voice treatment in Parkinson’s disease: Lee Silverman Voice Treatment
- Psychology, MedicineExpert review of neurotherapeutics
- 2011
The role of speech therapy in the landscape of exercise-based interventions for individuals with PD is examined, focusing on the intensive voice treatment protocol, Lee Silverman Voice Treatment, as an example therapy.
Task-Based Profile of Vocal Intensity Decline in Parkinson’s Disease
- Psychology, PhysicsFolia Phoniatrica et Logopaedica
- 2005
Results indicate that the DDK is particularly useful for describing intensity decay associated with PD, however, considering the inconsistent group differences across tasks, and the discrepant findings from previous studies, intensity decay is not a robust symptom of PD.
Formant centralization ratio: a proposal for a new acoustic measure of dysarthric speech.
- PhysicsJournal of speech, language, and hearing research : JSLHR
- 2010
The present findings indicate that the FCR is a sensitive, valid, and reliable acoustic metric for distinguishing dysarthric from unimpaired speech and for monitoring treatment effects, probably because of reduced sensitivity to interspeaker variability and enhanced sensitivity to vowel centralization.
Support-Vector Networks
- Computer ScienceMachine Learning
- 2004
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.