Tongue and Lip Acceleration as a Measure of Speech Decline in Amyotrophic Lateral Sclerosis.
Kristin J Teplansky, Alan Wisler, Jordan R Green and 4 others
PMID 35760064WHAT IT FOUND
Tongue acceleration variability correlates with speech decline in ALS, explaining up to 32% of variance.
This measure detects motor control issues earlier than standard speed or displacement metrics, offering a precise tool for monitoring bulbar function.
Key findings
01Variability of tongue and lower lip acceleration significantly correlates with intelligible speaking rate, with tongue tip acceleration explaining 32.2% of the variance.
02Displacement variability showed no significant relationship with speech severity, whereas acceleration variability did, suggesting acceleration is a more sensitive marker for early motor decline.
03Tongue sensors provided the most relevant predictive information for ALS-induced dysarthria compared to lip sensors in machine learning models.
STILL TO COME
How it was doneWhat they foundWhat it means for SLPs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The study used only four repetitions per phrase, whereas the standard spatiotemporal index formulation typically requires 15 repetitions, which may affect reliability. The sample size was 50 participants, and the machine learning differences between acceleration and speed models were not statistically significant in rigorous cross-validation. Jaw movement was not recorded, so it is unclear how much jaw motion contributed to the observed tongue and lip variability. This was a cross-sectional analysis; it did not track individual participants over time to confirm that acceleration changes predict future decline.
Declared interests
The authors declared no conflicts of interest.
The easy way to misread this
Do not assume that tongue acceleration is currently a validated clinical tool for individual patient monitoring. The study demonstrates a statistical correlation in a research setting using specialized equipment, but it does not establish that this measure is ready for routine clinical use or that it outperforms existing standard assessments in practice.