Abstract
Slow and irregular oral diadochokinesis represents an important manifestation of spastic and ataxic dysarthria in multiple sclerosis (MS). We aimed to develop a robust algorithm based on convolutional neural networks for the accurate detection of syllables from different types of alternating motion rate (AMR) and sequential motion rate (SMR) paradigms. Subsequently, we explored the sensitivity of AMR and SMR paradigms based on voiceless and voiced consonants in the detection of speech impairment. The four types of syllable repetition paradigms including /ta/, /da/, /pa/-/ta/-/ka/, and /ba/-/da/-/ga/ were collected from 120 MS patients and 60 matched healthy control speakers. Our neural network algorithm was able to correctly identify the position of individual syllables with a very high average accuracy of 97.8%, with the correct temporal detection of syllable position of 87.8% for 10 ms and 95.5% for 20 ms tolerance value. We found significantly altered diadochokinetic rate and regularity in MS compared to controls across all types of investigated tasks ( ). MS patients showed slower speech for SMR compared to AMR tasks, whereas voiced paradigms were more irregular. Objective evaluation of oral diadochokinesis using different AMR and SMR paradigms may provide important information regarding speech severity and pathophysiology of the underlying disease.
Highlights
M ULTIPLE sclerosis (MS) is the most common acquired demyelinating disease of the central nervous system occurring mainly in young and middle-aged adults and affecting about 0.1% to 0.2% of the population [1]
The average accuracy for voiceless alternating motion rate (AMR)/sequential motion rate (SMR) paradigms of 99.6% was slightly higher than the average accuracy of 96.0% for voiced AMR/SMR tasks
Our pilot analyses showed a trend toward correlation ( p < 0.05, uncorrected) between the performance of DDK regularity and the extent of cerebellar but not pyramidal dysfunction, which may support the hypothesis that temporal irregularity of syllable repetition is primarily attributable to damage to the cerebellum [19], [20], [38]
Summary
M ULTIPLE sclerosis (MS) is the most common acquired demyelinating disease of the central nervous system occurring mainly in young and middle-aged adults and affecting about 0.1% to 0.2% of the population [1]. As a result of widespread brain atrophy affecting mostly white and gray matter, MS presents a wide range of neurological manifestations with motor, sensory and cognitive impairments. Previous research has shown that the severity of dysarthria is attributed to the overall severity of neurological disease [4], [5], [15]. This observation provides an opportunity to consider objective speech evaluation as a potential biomarker for monitoring disease progression in MS. Non-invasive, inexpensive, easy to apply and can be fully automated and monitored remotely, even by a smartphone application from the patient’s home [16]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Transactions on Neural Systems and Rehabilitation Engineering
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
