AIMS: Atrial fibrillation (AFib) is the most common cardiac arrhythmia, affecting eventually up to a quarter of the population. At home, ECG based Holter devices designed to detect AFib must be removed after 1-2 weeks maximum. Wrist devices are restrictive and need to be recharged on a regular, even daily, basis. Due to cost and usability constraints, today long-term at-home monitoring to detect AFib from large numbers of users is not feasible. The purpose of this small scale clinical study was to validate the usability of MEMS accelerometer based bedsensor for detection of AFib.
METHODS: A Murata accelerometer based ballistocardiogram bedsensor was attached under the hospital bed magnetically and measurement data was recorded from 20 AFib patients and 15 healthy volunteers, mainly females. The recording time was up 30 minutes. The sensor built-in algorithms automatically extracted features such as heart rate (HR), heart rate variability (HRV), relative stroke volume (SVOL), signal strength (SS) and whether the patient is in bed or not.
RESULTS: We calculated median values for each feature HR, HRV, SVOL and SS, and investigated whether it is possible to separate AFib from healthy with these features or their combinations. Areas under the curve (AUC) were 0.77 for HR, 0.97 for HRV, 0.7 for SVOL and 0.84 for SS. AUC for all features combined e.g. HR, HRV, SVOL and SS was 0.99 using Kernel SVM classifier corresponding to sensitivity of 100% and specificity of 80%. Similarly, the AUC was 0.98 for RF classifier corresponding to sensitivity of 100% and 93% specificity.
CONCLUSIONS: Based on our pilot results, the Murata bedsensor is able to detect AFib, and may be a promising solution for long-term monitoring of AFib at home settings as it requires only one-time installation and operational time can be up to years and even tens of years.