Zero-Effort Ambient Heart Rate Monitoring Using Ballistocardiography Detected Through a Seat Cushion: Prototype Development and Preliminary Study.
Ahmed Raza Malik, Jennifer Boger
PMID 34057420WHAT IT FOUND
A seat cushion prototype could record heart-rate signals from a seated person, but usable data depended on staying still.
In 20 participants, a 1-minute still-sitting test showed 91.4% heartbeat detection accuracy against ECG. This shows engineering feasibility, not clinical usefulness.
Key findings
01Clean ballistocardiogram segments were 88.2% of recording time during watching a video, 59.3% during reading, 32.3% during conversation and 29.7% during computer use.
02A wavelet-based algorithm detected heartbeats from cushion signals with 91.4% average accuracy in 1 minute of sitting-still data from 20 participants.
03Detection accuracy was above 90% for 14 participants and below 80% for 3 participants.
STILL TO COME
How it was doneWhat they foundWhat it means for OTs
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 tested a prototype in 20 adults during simulated seated activities, not real home monitoring over time. Heartbeat-detection accuracy was tested only on 1 minute of sitting-still data, not on the shorter clean segments from video, reading, conversation or computer use. Motion greatly reduced usable ballistocardiogram data during reading, conversation and computer use. Accuracy was not the same for all participants: 3 participants had detection below 80%, and the algorithm sometimes misidentified peaks even when the signal looked reasonable. The paper does not report clinical outcomes, alert thresholds, cardiac diagnosis, or use in people with heart conditions, limited mobility or dementia.
Declared interests
The authors declared no conflicts of interest.
The easy way to misread this
Do not conclude this cushion is a validated home heart-rate monitor. The all-participant accuracy was 91.4% in a 1-minute sitting-still test, and the higher 94.66% figure excludes three participants.