Parkinson’s disease diagnosis using neural networks: Survey and comprehensive evaluation

Tanveer, M.; Rashid, Ashraf Haroon; Kumar, Rahul; Raman, Balasubramanian

doi:10.1016/j.ipm.2022.102909

Cited by 24 publications

(4 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning algorithms have the potential to assist physicians in both diagnosing Parkinson's disease and quantifying its progression by extracting valuable patterns from processed data [3] . To model the relationship between speech signal properties and UPDRS scores, various machine learning techniques have been employed such as Support Vector Machines (SVMs) [4] , [5] , [6] , Adaptive Neuro-Fuzzy Inference System [ 7 , 8 ], Support Vector Regression (SVR) [9] , Neural Networks [10] , [11] , [12] , [13] , [14] , [15] , [16] , [17] , [18] , and Gaussian Process Regression [19] .…”

Section: Methods Detailsmentioning

confidence: 99%

A combined method of optimized learning vector quantization and neuro-fuzzy techniques for predicting unified Parkinson's disease rating scale using vocal features

Zogaan,

Nilashi,

Ahmadi

et al. 2024

MethodsX

View full text Add to dashboard Cite

Section: Methods Detailsmentioning

confidence: 99%

A combined method of optimized learning vector quantization and neuro-fuzzy techniques for predicting unified Parkinson's disease rating scale using vocal features

Zogaan,

Nilashi,

Ahmadi

et al. 2024

MethodsX

View full text Add to dashboard Cite

“…CNN is a multi-layer perceptron that uses local connections and weight sharing to reduce the number of network training parameters. The CNN models have been successfully used in recent studies for automatic PD detection based on EEG signals ( Tanveer et al, 2022 ). Our proposed MCNN model was improved on the traditional CNN network LeNet-5 network ( Lecun et al, 1998 ).…”

Section: Methodsmentioning

confidence: 99%

“…With the development of deep learning methods in the last few years, more and more studies have also explored EEG-based automatic PD detection ( Tanveer et al, 2022 ). Gil-Martín et al (2019) detected PD patients by using a convolutional neural network (CNN) to analyze subjects’ the drawing movements and achieved 96.5% accuracy.…”

Section: Introductionmentioning

confidence: 99%

Parkinson’s disease detection based on multi-pattern analysis and multi-scale convolutional neural networks

Qiu

Pan

2022

Front. Neurosci.

View full text Add to dashboard Cite

Parkinson’s disease (PD) is a complex neurodegenerative disease. At present, the early diagnosis of PD is still extremely challenging, and there is still a lack of consensus on the brain characterization of PD, and a more efficient and robust PD detection method is urgently needed. In order to further explore the features of PD based on brain activity and achieve effective detection of PD patients (including OFF and ON medications), in this study, a multi-pattern analysis based on brain activation and brain functional connectivity was performed on the brain functional activity of PD patients, and a novel PD detection model based on multi-scale convolutional neural network (MCNN) was proposed. Based on the analysis of power spectral density (PSD) and phase-locked value (PLV) features of multiple frequency bands of two independent resting-state electroencephalography (EEG) datasets, we found that there were significant differences in PSD and PLV between HCs and PD patients (including OFF and ON medications), especially in the β and γ bands, which were very effective for PD detection. Moreover, the combined use of brain activation represented by PSD and functional connectivity patterns represented by PLV can effectively improve the performance of PD detection. Furthermore, our proposed MCNN model shows great potential for automatic PD detection, with cross-validation accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve all above 99%. Our study may help to further understand the characteristics of PD and provide new ideas for future PD diagnosis based on spontaneous EEG activity.

show abstract

“…Although the same nucleus as observed in PD, dystonia exhibits different rhythms. Neuronal activity in the sub-halamic nucleus is closely linked to symptoms and their treatment in patients with Parkinson's disease [13].Zhang Kun et al [14] found neural fluctuations in the subthalamic nucleus of PD with high synchrony and regularity. Excessive synchronization of nerve fluctuations in the frequency band (10~30Hz) of the local field potential in the subthalamic nucleus is closely related to symptoms such as bradykinesia and muscle stiffness.…”

Section: Local Field Potential (Lfp)mentioning

confidence: 99%

Detection methods of Parkinson's Disease based on physiological signals and machine learning methods

Xu¹

2023

HSET

View full text Add to dashboard Cite

Parkinson's disease (PD) is an extremely complex motor disorder due to the lack of dopaminergic neurons in the substantia nigra. and other dopaminergic and non-dopaminergic regions of the brain. The high rate of misdiagnosis in Parkinson's disease often causes patients to miss out on the best treatment opportunities. Since some of the symptoms of Parkinson's disease are mild in the initial stages and become severe over time, it is particularly important to correctly diagnose Parkinson's disease timely. The traditional tremor detection method of Parkinson's disease is more complex and the misdiagnosis rate is high. Methods based on physiological signals such as Local field potential (LFP), Electromyographic signal (EMG) and EEG signal et.al and research by using the machine learning strategies including the traditional machine learning and deep leaning methods are increasing. Get a precise diagnosis for Parkinson's disease, this paper analyzes physiological signals and machine learning methods that commonly used in PD detection, which may provide theoretical and practical references to future studies.

show abstract

Parkinson’s disease diagnosis using neural networks: Survey and comprehensive evaluation

Cited by 24 publications

References 102 publications

A combined method of optimized learning vector quantization and neuro-fuzzy techniques for predicting unified Parkinson's disease rating scale using vocal features

A combined method of optimized learning vector quantization and neuro-fuzzy techniques for predicting unified Parkinson's disease rating scale using vocal features

Parkinson’s disease detection based on multi-pattern analysis and multi-scale convolutional neural networks

Detection methods of Parkinson's Disease based on physiological signals and machine learning methods

Contact Info

Product

Resources

About