A Diadochokinesis-based expert system considering articulatory features of plosive consonants for early detection of Parkinson's disease. (February 2018)

• Record Type: Journal Article
• Authors: Montaña, David; Campos-Roca, Yolanda; Pérez, Carlos J.
• Is Part Of: Computer methods and programs in biomedicine. Volume 154(2018)
• Page Start: 89
• Page End: 97
• Publication Date: 2018-02
• Subjects: Expert system -- Acoustic features -- Classification -- Diadochokinesis (DDK) -- Parkinson's disease (PD) -- Speech disorders; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2017.11.010
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: New articulatory database with lower disease stage than previous contributions. New approach for early detection of Parkinson's disease from Diadochokinesis tests. New accurate VOT extraction algorithm for both healthy and Parkinson's disease subjects. Comparison of detection performance based on /p/, /t/ and /k/ plosive consonants. High accuracy achieved based on temporal and spectral features from /k/ segments. Abstract: Background and objective: A new expert system is proposed to discriminate healthy people from people with Parkinson's Disease (PD) in early stages by using Diadochokinesis tests. Methods: The system is based on temporal and spectral features extracted from the Voice Onset Time (VOT) segments of /ka/ syllables, whose boundaries are delimited by a novel algorithm. For comparison purposes, the approach is applied also to /pa/ and /ta/ syllables. In order to develop and validate the system, a voice recording database composed of 27 individuals diagnosed with PD and 27 healthy controls has been collected. This database reflects an average disease stage of 1.85 ± 0.55 according to Hoehn and Yahr scale. System design is based on feature extraction, feature selection and Support Vector Machine learning. Results: The novel VOT algorithm, based on a simple and computationally efficient approach, demonstrates accurate estimation of VOT boundaries on /ka/ syllables for both healthy and PD-affected speakers. The PD detection approach based on /k/ plosive consonant achieves the highest discrimination capability (92.2% using 10-fold cross-validation and 94.4% in the case of leave-one-out method) in comparison to the corresponding versions based on the other two plosives (/p/ and /t/). Conclusion: A high accuracy has been obtained on a database with a lower average disease stage than previous articulatory databases presented in the literature.