TY - JOUR
T1 - Signal quality and patient experience with wearable devices for epilepsy management
AU - Nasseri, Mona
AU - Nurse, Ewan
AU - Glasstetter, Martin
AU - Böttcher, Sebastian
AU - Gregg, Nicholas M.
AU - Laks Nandakumar, Aiswarya
AU - Joseph, Boney
AU - Pal Attia, Tal
AU - Viana, Pedro F.
AU - Bruno, Elisa
AU - Biondi, Andrea
AU - Cook, Mark
AU - Worrell, Gregory A.
AU - Schulze-Bonhage, Andreas
AU - Dümpelmann, Matthias
AU - Freestone, Dean R.
AU - Richardson, Mark P.
AU - Brinkmann, Benjamin H.
N1 - Funding Information:
This work was funded by the My Seizure Gauge grant provided by the Epilepsy Innovation Institute, a research program of the The Epilepsy Foundation of America's Epilepsy Innovation Institute My Seizure Gauge project. The authors thank Sherry Klingerman, Dan Crepeau, Dominique Eden, William Hart, and Shannon McCollough for technical assistance and coordination.
Funding Information:
This work was funded by the My Seizure Gauge grant provided by the Epilepsy Innovation Institute, a research program of the The Epilepsy Foundation of America's Epilepsy Innovation Institute My Seizure Gauge project. The authors thank Sherry Klingerman, Dan Crepeau, Dominique Eden, William Hart, and Shannon McCollough for technical assistance and coordination.
Publisher Copyright:
© 2020 International League Against Epilepsy
PY - 2020/11
Y1 - 2020/11
N2 - Noninvasive wearable devices have great potential to aid the management of epilepsy, but these devices must have robust signal quality, and patients must be willing to wear them for long periods of time. Automated machine learning classification of wearable biosensor signals requires quantitative measures of signal quality to automatically reject poor-quality or corrupt data segments. In this study, commercially available wearable sensors were placed on patients with epilepsy undergoing in-hospital or in-home electroencephalographic (EEG) monitoring, and healthy volunteers. Empatica E4 and Biovotion Everion were used to record accelerometry (ACC), photoplethysmography (PPG), and electrodermal activity (EDA). Byteflies Sensor Dots were used to record ACC and PPG, the Activinsights GENEActiv watch to record ACC, and Epitel Epilog to record EEG data. PPG and EDA signals were recorded for multiple days, then epochs of high-quality, marginal-quality, or poor-quality data were visually identified by reviewers, and reviewer annotations were compared to automated signal quality measures. For ACC, the ratio of spectral power from 0.8 to 5 Hz to broadband power was used to separate good-quality signals from noise. For EDA, the rate of amplitude change and prevalence of sharp peaks significantly differentiated between good-quality data and noise. Spectral entropy was used to assess PPG and showed significant differences between good-, marginal-, and poor-quality signals. EEG data were evaluated using methods to identify a spectral noise cutoff frequency. Patients were asked to rate the usability and comfort of each device in several categories. Patients showed a significant preference for the wrist-worn devices, and the Empatica E4 device was preferred most often. Current wearable devices can provide high-quality data and are acceptable for routine use, but continued development is needed to improve data quality, consistency, and management, as well as acceptability to patients.
AB - Noninvasive wearable devices have great potential to aid the management of epilepsy, but these devices must have robust signal quality, and patients must be willing to wear them for long periods of time. Automated machine learning classification of wearable biosensor signals requires quantitative measures of signal quality to automatically reject poor-quality or corrupt data segments. In this study, commercially available wearable sensors were placed on patients with epilepsy undergoing in-hospital or in-home electroencephalographic (EEG) monitoring, and healthy volunteers. Empatica E4 and Biovotion Everion were used to record accelerometry (ACC), photoplethysmography (PPG), and electrodermal activity (EDA). Byteflies Sensor Dots were used to record ACC and PPG, the Activinsights GENEActiv watch to record ACC, and Epitel Epilog to record EEG data. PPG and EDA signals were recorded for multiple days, then epochs of high-quality, marginal-quality, or poor-quality data were visually identified by reviewers, and reviewer annotations were compared to automated signal quality measures. For ACC, the ratio of spectral power from 0.8 to 5 Hz to broadband power was used to separate good-quality signals from noise. For EDA, the rate of amplitude change and prevalence of sharp peaks significantly differentiated between good-quality data and noise. Spectral entropy was used to assess PPG and showed significant differences between good-, marginal-, and poor-quality signals. EEG data were evaluated using methods to identify a spectral noise cutoff frequency. Patients were asked to rate the usability and comfort of each device in several categories. Patients showed a significant preference for the wrist-worn devices, and the Empatica E4 device was preferred most often. Current wearable devices can provide high-quality data and are acceptable for routine use, but continued development is needed to improve data quality, consistency, and management, as well as acceptability to patients.
KW - epilepsy
KW - patient experience
KW - signal quality
KW - wearable devices
UR - http://www.scopus.com/inward/record.url?scp=85085941436&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085941436&partnerID=8YFLogxK
U2 - 10.1111/epi.16527
DO - 10.1111/epi.16527
M3 - Article
C2 - 32497269
AN - SCOPUS:85085941436
SN - 0013-9580
VL - 61
SP - S25-S35
JO - Epilepsia
JF - Epilepsia
IS - S1
ER -