Detection and classification methodology for movements in the bed that supports continuous pressure injury risk assessment and repositioning compliance.
Jonathan Duvall, Patricia Karg, David Brienza and 1 others
PMID 30598376WHAT IT FOUND
A bed load-cell system detected 97.7% of movements and classified movement types with 94.8% or higher accuracy in ten able-bodied people.
It may help monitor pressure injury risk and repositioning, but no patients were studied.
Key findings
01In ten able-bodied subjects, the E-scale detected movements with 97.7% accuracy when using a 6 or 7 second window and a 7 pound threshold.
02The movement classification algorithm was 96.4% accurate in leave-one-out testing and 96% accurate in random training set testing.
03All movements were classified correctly more than 91% of the time, and the only frequent misclassification was between independent turns in place and assisted turns.
STILL TO COME
How it was doneWhat they foundWhat it means for RNs
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 ten able-bodied people doing prescribed movements on one type of bed, so it does not show how the system works for patients who cannot move as easily. It measured movement detection and classification, not whether pressure injuries were prevented or whether patients did better. Extremity movements were the least reliably detected, with 13 of the 16 missed movements in that category. The system confused independent turns in place and assisted turns more than other movements. Assisted turns were performed by one clinician, so technique may not match other facilities.
Declared interests
The E-scale was developed at the authors' research laboratory and licensed to Nexaware, with plans of commercialization.
The easy way to misread this
Do not read the high accuracy as proof that this system prevents pressure injuries or should replace repositioning protocols. It was tested on ten able-bodied people doing prescribed movements, and the paper says there is currently no evidence that motion related to pressure injury risk can be extracted from load cell data.