Automatic extraction of abnormal lip movement features from the alternating motion rate task in amyotrophic lateral sclerosis.
Panying Rong, Yana Yunusova, Brian Richburg and 1 others
PMID 30253671WHAT IT FOUND
Lip movement during rapid /ba/ repetition changed before speaking rate and intelligibility fell in ALS.
Irregular timing of lip cycles was one of the most sensitive early signs, and slower repetition rate may help predict coming speech loss.
Key findings
01Eleven lip movement variables differed across early ALS, late ALS and healthy controls, while speaking rate and intelligibility showed no change in early ALS relative to controls.
02Jitter was the best single lip movement variable for separating ALS from controls among the 23 extracted variables.
03Syllable frequency, jitter and number of cycles predicted speech intelligibility decline, with intelligibility above 96% in early ALS and stage cutoffs of Freq < 2.79 cycles/sec, Jitter > 0.38 sec, and Ncyc < 35 cycles.
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 authors state the study was exploratory and used a significance threshold of p < 0.05 for all group comparisons. Participants had to have adequate cognitive function and no medications known to affect speech, so the results may not apply to ALS patients with frontotemporal dementia or medication-related speech changes. Only 27 of the 57 ALS participants were followed longitudinally, and session intervals varied with availability, so progression estimates are limited by uneven follow-up. The lip movement data came from electromagnetic or optical tracking, not the low-cost depth-sensing cameras discussed as future clinical tools, so clinical feasibility is not shown. The AMR task is a speechlike maximum-rate task, and the paper notes debate about whether it represents speech capacity. The study reports group differences and model associations, not tested clinical implementation or patient-important outcomes.
Declared interests
Research support is listed as NIH extramural and non-U.S. government funding; the supplied text does not report an author conflict-of-interest declaration.
The easy way to misread this
Do not conclude that a low-cost camera system can now be used in clinic to predict speech loss. This study used research-grade electromagnetic or optical tracking, and the algorithm and cutoffs were developed and tested in this exploratory dataset rather than as a clinical tool.