Machine learning- and statistical-based voice analysis of Parkinson's disease patients: A survey. (1st June 2023)

• Record Type: Journal Article
• Authors: Amato, Federica; Saggio, Giovanni; Cesarini, Valerio; Olmo, Gabriella; Costantini, Giovanni
• Is Part Of: Expert systems with applications. Volume 219(2023)
• Publication Date: 2023-06-01
• Subjects: Parkinson's disease -- Acoustic features -- Machine learning -- Voice analysis; AI Artificial Intelligence -- AT Amplitude Tremor -- BBE Bark Band Energies -- CNN Convolutional Neural Network -- D2 Correlation Dimension -- DBS Deep Brain Stimulation -- DDK Diadochokinetic -- DFA Detrended Fluctuation Analysis -- F0 Fundamental Frequency -- FT Frequency Tremor -- HNR Harmonic to Noise Ratio -- LLE Largest Lyapunov Exponent -- LPC Linear Prediction Coefficients -- MFCC Mel-Frequency Cepstral Coefficients -- ML Machine Learning -- NHR Noise to Harmonic Ratio -- PD Parkinson's Disease -- PLP Perceptual linear prediction -- RASTA Relative Spectral Transform -- RBD REM sleep behavior disorders -- RPDE Recurrence Period Density Entropy -- SVM Support Vector Machine -- UCI University of California Irvine -- UPDRS Unified Parkinson's Disease Rating Scale -- VOT Voice Onset Time -- VSA Vowel Space Area; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2023.119651
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: The preliminary diagnosis and evaluation of the presence and/or severity of Parkinson's disease is crucial in controlling the progress of the disease. Real-time, non-invasive methodologies based on machine learning-enhanced voice analysis are gathering more interest as the potential of this field unveils. Specifically, acoustic features are employed in many machine learning techniques, and could also function as indicators of the overall state of the subjects' voice: this review aims at identifying the most widely employed and promising feature-based machine learning methodologies, evidencing baselines and state-of-the-art solutions. A total of 102 works plus 5 review articles were selected from the IEEE Xplore, PubMed, Elsevier, and Web of Science electronic databases. A statistical assessment is performed identifying the most frequently used features as well as those deemed as most effective; an overview of algorithms, public datasets, toolboxes, and general metadata is also performed. According to our results, Jitter, Shimmer, Harmonic-to-Noise Ratio, Fundamental Frequency, and Mel Frequency Cepstral Coefficients are the mostly adopted features. In addition, it is worth noting a fair prevalence of glottal-like models and additional filtering options, such as Detrended Fluctuation Analysis. © 2017 Elsevier Inc. All rights reserved.