Automatic and Early Detection of Parkinson’s Disease by Analyzing Acoustic Signals Using Classification Algorithms Based on Recursive Feature Elimination Method

Abstract

Parkinson’s disease (PD) is a neurodegenerative condition generated by the dysfunction of brain cells and their 60–80% inability to produce dopamine, an organic chemical responsible for controlling a person’s movement. This condition causes PD symptoms to appear. Diagnosis involves many physical and psychological tests and specialist examinations of the patient’s nervous system, which causes several issues. The methodology method of early diagnosis of PD is based on analysing voice disorders. This method extracts a set of features from a recording of the person’s voice. Then machine-learning (ML) methods are used to analyse and diagnose the recorded voice to distinguish Parkinson’s cases from healthy ones. This paper proposes novel techniques to optimize the techniques for early diagnosis of PD by evaluating selected features and hyperparameter tuning of ML algorithms for diagnosing PD based on voice disorders. The dataset was balanced by the synthetic minority oversampling technique (SMOTE) and features were arranged according to their contribution to the target characteristic by the recursive feature elimination (RFE) algorithm. We applied two algorithms, t-distributed stochastic neighbour embedding (t-SNE) and principal component analysis (PCA), to reduce the dimensions of the dataset. Both t-SNE and PCA finally fed the resulting features into the classifiers support-vector machine (SVM), K-nearest neighbours (KNN), decision tree (DT), random forest (RF), and multilayer perception (MLP). Experimental results proved that the proposed techniques were superior to existing studies in which RF with the t-SNE algorithm yielded an accuracy of 97%, precision of 96.50%, recall of 94%, and F1-score of 95%. In addition, MLP with the PCA algorithm yielded an accuracy of 98%, precision of 97.66%, recall of 96%, and F1-score of 96.66%.

Hybrid Techniques of Facial Feature Image Analysis for Early Detection of Autism Spectrum Disorder Based on Combined CNN Features

“…Applying t-SNE to select the most important features and reduce the dimensionality of facial features extracted by VGG16, ResNet101, and MobileNet models for autism analysis brings several significant advantages: While deep learning models like VGG16, ResNet101, and MobileNet are powerful at extracting meaningful features from images, the features they produce often be high-dimensional and redundant. High dimensionality increases computation time and even introduces noise or irrelevant information into the analysis [ 38 ]. Applying t-SNE effectively reduces the dimensionality of the extracted features while preserving the most important information.…”

Pre-asthma: a useful concept for prevention and disease-modification? A EUFOREA paper. Part 1—allergic asthma

“…Parkinson's, a disease caused by a lack of dopamine, is often present for several years before the diagnosis is made. Machine learning applied to voice recordings can be used to detect Parkinson's disease automatically and early, allowing earlier treatment and better quality of life for sufferers ( 11 ).…”

A New Wrist-Worn Tool Supporting the Diagnosis of Parkinsonian Motor Syndromes

“…Proposed biomarkers include clinical, imaging, biofluidic-base, and inflammation-related biomarkers for preclinical, prodromal, and clinical stages [ 9 , 10 ]. Some of the proposed tools and methods for the early detection of PD are based on analysing voice disorders [ 11 , 12 ], handwriting [ 13 ], olfactory testing [ 14 ], and accelerometery data [ 15 ]. Other proposed solutions based on the use of Artificial Intelligence include convolutional neural networks for eye tracking and facial expression analysis [ 16 ], Machine Learning-assisted speech analysis [ 17 ], and deep learning models for various modalities such as brain analysis and motion symptoms [ 18 ].…”

“…However, there are currently no means to identify prodromal PD with 100% certainty [ 19 ], neither standardized international criteria supporting PD diagnosis at a preclinical stage [ 10 ] nor confirmed biomarkers to provide early detection of PD efficiently [ 11 , 20 ]. On the other hand, an increasing number of studies have revealed that a combination of biomarkers can improve the diagnostic accuracy of individual biomarkers [ 9 , 10 ].…”