Pandemics/Epidemics (Free)
Search All Applications in Pandemics/Epidemics (Free)
Application US20190110755
Published 2019-04-18
Applied Data Quality Metrics For Physiological Measurements
A model of data quality is derived for physiological monitoring with a wearable device by comparing data from the wearable device to concurrent data acquisition from a ground truth device such as a chest strap or electrocardiography (EKG) heart rate monitor. With this comparative data, a machine learning model or the like may be derived to prospectively evaluate data quality based on the data acquisition context, as determined, for example, by other sensor data and signals from the wearable device.
Much More than Average Length Specification
View the Patent Matrix® Diagram to Explore the Claim Relationships
USPTO Full Text Publication >
- 1. A method comprising:
obtaining calibrated heart rate data from a number of subjects using one or more chest strap type sensors; obtaining uncalibrated heart rate data from the number of subjects concurrently with the calibrated heart rate data using one or more physiological monitors of a wrist-worn photoplethysmography type; obtaining feature data from one or more sensors of the one or more physiological monitors of the wrist-worn photoplethysmography type concurrently with the calibrated heart rate data and the uncalibrated heart rate data, the feature data characterizing a plurality of features of a data acquisition context for a corresponding one of the physiological monitors of the wrist-worn photoplethysmography type; associating a quality metric for the uncalibrated heart rate data with the feature data based on whether, for each data acquisition context, the uncalibrated heart rate data is within a predetermined threshold of the calibrated heart rate data; creating a quality estimator engine to evaluate a likelihood of the uncalibrated heart rate data being accurate based on the feature data; receiving second uncalibrated heart rate data and second feature data from a second physiological monitor of the wrist-worn photoplethysmography type; determining a probability that the second uncalibrated heart rate data is accurate for a window of measurements by calculating a conditional probability that the second uncalibrated heart rate data is accurate based on the second feature data over a distribution of values for the calibrated heart rate data within the window of measurements based on the quality estimator engine; and associating the probability with the window as a measure of quality for the uncalibrated heart rate data within the window.
- 12. A method comprising:
obtaining data for a number of subjects, the data including calibrated physiological data from a first type of physiological monitors assumed to be accurate, uncalibrated physiological data from a second type of physiological monitors of unknown accuracy, and feature data characterizing a timewise data acquisition context for the uncalibrated physiological data; training a quality estimator engine to determine a quality of the uncalibrated physiological data based on the feature data and a difference between the uncalibrated physiological data and the calibrated physiological data; receiving physiological data and feature data from a different one of the second type of physiological monitors; calculating a probability that the physiological data is accurate for a window of measurements by applying the quality estimator engine to a distribution of values for the physiological data and corresponding values for the feature data; and associating the probability with the window as a measure of quality for the physiological data within the window.
- 18. A computer program product comprising computer executable code embodied in a non-transitory computer readable medium that, when executing on a wearable device, performs the steps of:
receiving physiological data and feature data from one or more sensors of the wearable device, the physiological data characterizing a physiological measurement for a user of the wearable device and the feature data characterizing a timewise data acquisition context for the physiological data; storing a quality estimator engine that calculates a probability that a measurement of the physiological data is accurate based on corresponding feature data; calculating a second probability that the physiological data is accurate for a window of measurements by applying the quality estimator engine to a distribution of values for the physiological data and corresponding values for the feature data; and associating the second probability with the window as a measure of quality for the physiological data within the window.
- 20. A wearable device comprising:
a wrist strap; one or more sensors for capturing physiological data characterizing a physiological measurement for a user of the wearable device and feature data characterizing a timewise data acquisition context for the physiological data; a memory storing a quality estimator engine configured to calculate a probability that a measurement of the physiological data is accurate based on corresponding feature data; and a processor configured by computer executable code to perform the steps of receiving physiological data and feature data from the one or more sensors, calculating a second probability that the physiological data is accurate for a window of measurements by applying the quality estimator engine to a distribution of values for the physiological data and corresponding values for the feature data, and storing the second probability as a measure of quality for the physiological data within the window.
