Credit score: Unsplash/CC0 Public Area
A brand new examine led by UCLA investigators exhibits that Verbal Response Time (VRT), the period of time it takes an individual to reply verbally, could be a marker of sleepiness in older adults. The examine, which measured members’ voice information by standardized cognitive assessments, exhibits how VRT can passively detect extreme sleepiness, particularly amongst older people utilizing sedative medicines.
The work, “Predicting subjective sleepiness during auditory cognitive testing using voice signaling analysis,” is printed within the journal Sleep Science and Apply.
Sleepiness is a significant contributor to security dangers in every day life, however is commonly underreported or unnoticed, particularly amongst older adults. Extreme sleepiness contributes to motorcar crashes, cognitive impairment, and falls, particularly in older adults utilizing sedative medicines like benzodiazepine receptor agonists (BZRAs). Present strategies to evaluate sleepiness are sometimes intrusive or impractical for real-world use. This examine supplies a scalable approach to detect sleepiness to assist determine at-risk people earlier than accidents or well being declines happen.
Researchers studied adults aged 55 and older with a historical past of insomnia and BZRA use, recruited from a deprescribing medical trial. Members accomplished reminiscence assessments through a cellular app, which recorded their verbal responses. The group measured verbal response time (VRT), the delay between the beginning of recording and the primary spoken phrase, evaluating it to members’ self-reported sleepiness.
The researchers then used superior instruments to check the hyperlink between how shortly individuals began talking and the way sleepy they felt. Additionally they examined whether or not a pc mannequin may precisely predict somebody’s sleepiness primarily based on their voice.
The mannequin efficiently predicted members’ self-reported sleepiness primarily based on their voice recordings. Individuals who took longer to begin talking after a immediate additionally reported feeling sleepier. The pc mannequin used within the examine was capable of accurately determine totally different ranges of sleepiness with robust accuracy, reaching an F1-score of 0.80 ± 0.08. (The F1-score is a measure of how properly the mannequin balances accuracy and consistency; 1.0 is ideal, and 0 means it failed.)
The voice evaluation technique additionally reliably detected when somebody was talking versus silent, with 92.5% accuracy. The outcomes recommend that voice timing may very well be a helpful, low-effort approach to monitor sleepiness—particularly outdoors of medical settings.
“This study shows that something as simple as how quickly someone starts speaking can tell us a lot about their level of alertness,” stated Dr. Tue T. Te, lead creator of the examine and a researcher on the David Geffen Faculty of Medication at UCLA and the VA Higher Los Angeles Healthcare System. “It opens the door to using voice as a passive, scalable tool for monitoring sleepiness during everyday activities.”
The group plans to broaden this strategy to bigger and extra numerous populations and discover integration into on a regular basis applied sciences like smartphones and telehealth platforms. Future analysis might also examine how voice-based markers can monitor medicine results or detect early indicators of cognitive decline.
Extra info:
Tue T. Te et al, Predicting subjective sleepiness throughout auditory cognitive testing utilizing voice signaling evaluation, Sleep Science and Apply (2025). DOI: 10.1186/s41606-025-00141-y
Offered by
College of California, Los Angeles
Quotation:
Verbal response time reveals hidden sleepiness in older adults (2025, July 9)
retrieved 9 July 2025
from https://medicalxpress.com/information/2025-07-response-reveals-hidden-sleepiness-older.html
This doc is topic to copyright. Aside from any honest dealing for the aim of personal examine or analysis, no
half could also be reproduced with out the written permission. The content material is offered for info functions solely.
