Differential Diagnosis Between Parkinson's Disease and Multiple System Atrophy Using Digital Speech Analysis - Part 2

Overview

Parkinson's disease (PD) is the second most common neurodegenerative disease. Multiple system atrophy (MSA) is a relentlessly progressing rare neurodegenerative disease of unknown etiology. The differential diagnosis between the MSA-Parkinsonism (MSA-P) subtype and PD can be very challenging in early disease stages, while early diagnostic certitude is important for the patient because of the diverging prognosis. At the time being, there exists no validated objective biomarker to guide the clinician. Dysarthria is a common early symptom in both diseases and of different origin. The ambition and the originality of this project are to develop a digital voice-based tool for objective discrimination between PD and MSA-P.

The team will build a corpus of voice samples of patients with both diseases and healthy volunteers. This corpus will consist of sustained vowels, pseudo-words, repetition of syllables, utterances of a standard text and spontaneous speech. Voice recordings will be performed using a high quality digital recorder (H4n) and the EVA-2 workstations. EVA-2 is a state-of-the-art system dedicated to pathological voice recording and analysis, which also allows the measurement of aerodynamic features such as intra-oral and subglottal pressure. An electroglottograph (EGG), a non-invasive device, will also be used in conjunction with the recordings to provide the ground truth of glottal opening and closure instants (OGI and GCI) during utterances. The use of an EGG can be very useful given that OGI and GCI provide valuable information about the voice short-time dynamics. The team will also perform a laryngostroboscopic examination to highlight defects in vocal cord mobility, a defect in vocal cord mating in phonation, abnormal vocal cord movements or supraglottic structures. The primary objective is to compare a global score assessing vocal performance between MSA-P, PD and healthy volunteers. Secondary objectives are 1) to compare an acoustic index, assessing the subsystems of speech production, between MSA-P, PD and healthy volunteers, 2) to compare an acoustic index, assessing types of dysarthria, between MSA-P and PD patients, and 3) to compare perceptual assessment, performed by a panel of experts, of voice alteration between MSA-P and PD patients. The final goal of this study is to evaluate the validity of the vocal markers that were identified in the previous study (Voice4PD-MSA-I, exploratory cohort). The validation will only consider data collected in the present study in order to assess the performance of the classifiers developed in the exploratory cohort.