Identification of the cause of fall during the pre-impact fall period.
Sho Sasaki, Hiroaki Yamamoto, Kodai Kitagawa and 1 others
PMID 35400837WHAT IT FOUND
A waist sensor identified fall causes like tripping or slipping with 83% accuracy, but only in the 0.5 seconds before impact.
This was tested on simulated falls in young adults, not real falls in older people, so it is not ready for clinical care.
Key findings
01The algorithm classified five types of fall causes with 83.0% accuracy when analyzing data from 0.5 seconds before impact.
02Accuracy dropped as the time window before impact increased, meaning the system needs to detect motion very close to the fall.
03The authors state the current accuracy is insufficient for real-world care, as they believe a reliability of 90% or greater is required.
STILL TO COME
How it was doneWhat they foundWhat it means for PTsWhat it means for OTsWhat 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 simulated falls performed by young, healthy adults, not actual falls in older people who are at risk of injury. The authors note that models trained on healthy young people may not work for older adults or those needing care. The classification accuracy (around 80-83%) is below the 90% threshold the authors say is needed for safe clinical use.
Declared interests
There are no conflicts of interest to be disclosed in this study.
The easy way to misread this
Do not assume this technology can currently identify fall risks in your older patients. The study used simulated falls in young adults and the accuracy was too low for clinical use, and the system only works if it analyzes motion in the final half-second before impact.