Key result
A signal quality modified Kalman filter using pulse arrival time achieved higher blood pressure measurement accuracy compared with a straightforward PAT-based linear regression model.
Why the study?
Does a signal quality modified Kalman filter improve the accuracy of continuous blood pressure estimation compared to a standard PAT-based linear regression model in physiological data segments?
Does a signal quality modified Kalman filter improve the accuracy of continuous blood pressure estimation compared to a standard PAT-based linear regression model in physiological data segments?
Answers are grounded in this paper and cite their sources.
A signal quality modified Kalman filter improves the accuracy of continuous cuff-less blood pressure estimation using pulse arrival time compared to standard linear regression models.
The present study designs an algorithm to increase the accuracy of continuous blood pressure (BP) estimation. Pulse arrival time (PAT) has been widely used for continuous BP estimation. However, because of motion artifact and physiological activities, PAT-based methods are often troubled with low BP estimation accuracy. This paper used a signal quality modified Kalman filter to track blood pressure changes. A Kalman filter guarantees that BP estimation value is optimal in the sense of minimizing the mean square error. We propose a joint signal quality indice to adjust the measurement noise covariance, pushing the Kalman filter to weigh more heavily on measurements from cleaner data. Twenty 2 h physiological data segments selected from the MIMIC II database were used to evaluate the performance. Compared with straightforward use of the PAT-based linear regression model, the proposed model achieved higher measurement accuracy. Due to low computation complexity, the proposed algorithm can be easily transplanted into wearable sensor devices.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2017) studied Blood pressure estimation (n=20). Signal quality modified Kalman filter with pulse arrival time vs. PAT-based linear regression model was evaluated on Blood pressure estimation accuracy. A signal quality modified Kalman filter using pulse arrival time achieved higher blood pressure measurement accuracy compared with a straightforward PAT-based linear regression model.
Synapse has enriched 10 related papers. Consider them for comparative context: