Background: Delineation of Parkinsons disease (PD) from multiple system atrophy (MSA) can be challenging, especially in early disease stages, and clinical markers are needed for early detection of MSA. Speech characteristics have been studied as digital biomarkers in PD and ataxias, but there is only little data on MSA.
Objectives: To determine whether speech characteristics can serve as a biomarker to differentiate between MSA and PD.
Methods: 21 MSA patients and 23 PD patients underwent a battery of speech task assessments: text reading, sustained phonation and diadochokinetic tasks. Speech characteristics were extracted using the software Praat.
Results: MSA and PD speech can be described by the factors: "time and pauses", "harsh voice", and a factor containing "mixed speech characteristics". After correcting for MDS-UPDRS III, four parameters and the "time and pause" factor showed significant differences between MSA and PD. MSA could be delineated from PD with Receiver Operator Characteristic Area Under the Curve (ROC-AUC) of 0.89 by a single speech parameter together with MDS-UPDRS III.
Conclusion: MSA can be differentiated from PD with good accuracy using only MDS-UPDRS III and one speech parameter as predictors. This outlines the importance of speech assessments to delineate MSA from PD to allow for differential diagnosis in movement disorders.