Research Article
Tidal Volume Variability and Respiration Rate Estimation Using a Wearable Accelerometer Sensor
@INPROCEEDINGS{10.4108/icst.mobihealth.2014.257528, author={Atena Roshan Fekr and Katarzyna Radecka and Zeljko Zilic}, title={Tidal Volume Variability and Respiration Rate Estimation Using a Wearable Accelerometer Sensor}, proceedings={4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming healthcare through innovations in mobile and wireless technologies"}, publisher={IEEE}, proceedings_a={MOBIHEALTH}, year={2014}, month={12}, keywords={respiration rate tidal volume variability accelerometer bluetooth low energy}, doi={10.4108/icst.mobihealth.2014.257528} }- Atena Roshan Fekr
Katarzyna Radecka
Zeljko Zilic
Year: 2014
Tidal Volume Variability and Respiration Rate Estimation Using a Wearable Accelerometer Sensor
MOBIHEALTH
IEEE
DOI: 10.4108/icst.mobihealth.2014.257528
Abstract
The measurement of respiration rate and tidal volume variability are critical to the diagnosis and monitoring of a wide range of breath disorders as well as being useful broader parameters of a patient’s condition. This paper presents a portable real-time platform designed to support a computationally efficient human respiratory tracking system for medical applications. The proposed system is designed particularly for patients with breathing problems (e.g. respiratory complications after surgery) or sleep disorders. We introduce the use of accelerometer sensor to detect changes in the anterior-posterior diameter of the chest; whereas these changes provide an accurate measurement of respiration rate as well as tidal volume variability. The complete system was comprised of wearable calibrated accelerometer sensor, Bluetooth Low Energy (BLE) and cloud database. The experiments are conducted with 8 subjects and the overall error in respiration rate calculation is obtained 0.2% considering SPR-BTA spirometer as the reference. We also present a method for Tidal Volume variability (TVvar) estimation while validated using Pearson correlation. The mean value of the correlation coefficient between TVvar derived from the accelerometer and spirometer for all subjects and three breath patterns is 0.87 which shows a high correspondence of two signals. Furthermore, the results indicate that the accelerometer driven TVvar achieves the average MSE 1.6E-03±3.69E-03 compared to the reference.