Amyotrophic lateral sclerosis (ALS) is a rapidly progressive neurodegenerative disease of the motor system that leads to the impairment of speech and swallowing functions. The lack of a biomarker typically causes a diagnostic delay. To advance the current diagnostic process, we explored the feasibility of automatic detection of patients with ALS at an early stage from highly intelligible speech. A speech dataset was collected from thirteen newly diagnosed patients with ALS and thirteen ageand gender-matched healthy controls. Convolutional Neural Networks (CNNs), including time-domain CNN and frequencydomain CNN, were used to classify the intelligible speech produced by patients with ALS and those by healthy individuals. Experimental results indicated both time-and frequency-CNN outperformed standard neural network. The best sample-level sensitivity and specificity were obtained by time-CNN (71.6% and 80.9%, respectively). When multiple samples were used to vote to estimate a person-level performance, the best result was obtained by frequency-CNN (76.9% sensitivity and 92.3% specificity). Results demonstrated the possibility of early detection of ALS from intelligible speech signals.
Purpose: Within-individual pharyngeal swallowing pressure variability differs among pharyngeal regions in healthy individuals and increases with age. It remains unknown if pharyngeal pressure variability is impacted by volitional swallowing tasks. We hypothesized that pressure variability would increase during volitional swallowing maneuvers and differ among pharyngeal regions depending on the type of swallowing task being performed. Method: Pharyngeal high-resolution manometry was used to record swallowing pressure data from 156 healthy participants during liquid (5 cc) or saliva swallows, and during volitional swallowing tasks including effortful swallow, Mendelsohn maneuver, Masako maneuver, or during postural adjustments. The coefficient of variation was used to determine pressure variability of velopharynx, tongue base, hypopharynx, and upper esophageal sphincter regions. Repeated-measures analysis of variance was used on log-transformed data to examine effects of pharyngeal region and swallowing tasks on swallow-to-swallow variability. Results: There was a significant main effect of task with greater pressure variability for the effortful swallow ( p = .002), Mendelsohn maneuver ( p < .001), Masako maneuver ( p = .002), and the head turn ( p = .006) compared with normal effort swallowing. There was also a significant main effect of region ( p < .01). In general, swallowing pressure variability was lower for the tongue base and upper esophageal sphincter regions than the hypopharynx. There was no significant interaction of task and region (effortful, p = .182; Mendelsohn, p = .365; Masako, p = .885; chin tuck, p = .840; head turn, p = .059; and inverted, p = .773). Conclusions: Pharyngeal swallowing pressure variability increases in healthy individuals during volitional swallowing tasks. Less stable swallow patterns may result when tasks are less automatic and greater in complexity. These findings may have relevance to swallowing motor control integrity in healthy aging and individuals with neurogenic dysphagia.
Amyotrophic Lateral Sclerosis (ALS) is a progressive neurological disease that leads to degeneration of motor neurons and, as a result, inhibits the ability of the brain to control muscle movements. Monitoring the progression of ALS is of fundamental importance due to the wide variability in disease outlook that exists across patients. This progression is typically tracked using the ALS functional rating scale-revised (ALSFRS-R), which is the current clinical assessment of a patient's level of functional impairment including speech and other motor tasks. In this paper, we investigated automatic estimation of the ALSFRS-R bulbar subscore from acoustic and articulatory movement samples. Experimental results demonstrated the AFSFRS-R bulbar subscore can be predicted from speech samples, which has clinical implication for automatic monitoring of the disease progression of ALS using speech information.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.