Description
Development of just-in-time adaptive health interventions requires reliable technologies for accurate monitoring of physiological parameters in ambulatory settings. Due to high heterogeneity of analytical methods used in evaluating heart rate (HR) sensors against electrocardiographs, harmonization of findings and comparison of sensors evaluated across studies are often limited. Our analysis of suitable analytical methods using synthetic and empirical data suggests the importance of concordance correlation coefficient, limits of agreement, their regressions on HR strata and motion, and time lags in HR sensor validation studies.
Learning Objective: After participating in this session, the learner should be better able to learn to formulate an appropriate analytical approach for evaluating wearable heart rate sensors against electrocardiographs.
Authors:
Maciej Kos (Presenter)
Northeastern University
Christine Gordon, Northeastern University
Xuan Li, Northeastern University
Iman Khaghani Far, Northeastern University
Misha Pavel, Northeastern University
Holly Jimison, Northeastern University
Presentation Materials: