Health Management
OwnerBao Traninventor
Life of this patent
Estimating the term…
Abstract
A method includes capturing pressure data from an optical sensor; capturing motion data; determining a predetermined health condition of a user based on the pressure and motion data; and generating one or more reports on pressure management with feedback from the motion and pressure data.
Claims19
A health monitoring system comprising:
- a sensor device configured to be coupled to a body portion of a user, the sensor device comprising:
- a plurality of light-emitting diodes (LEDs) spanning at least a portion of a visible spectrum or a near-infrared spectrum;
- at least one photodetector positioned relative to the plurality of LEDs to receive optical radiation that has interacted with tissue of the user and to generate corresponding photoplethysmographic signals;
- a temperature sensor;
- and
- a processor operatively coupled to the plurality of LEDs, the at least one photodetector, and the motion sensor, the processor configured to:
- control the plurality of LEDs to emit the optical radiation in a sequence where different wavelengths are emitted at different times;
- acquire during time intervals a plurality of photoplethysmographic samples from the at least one photodetector;
- generate, from the plurality of photoplethysmographic samples, a composite feature vector for each of the plurality of wavelengths;
- and
- apply a trained machine-learning model to the composite feature vector to estimate at least one physiological parameter of the user selected from a blood pressure parameter or a glucose-related parameter.
The health monitoring system of claim 13, wherein the remote medical improvement server is further configured to aggregate physiological parameter estimates and associated sensor features from a plurality of users, to train a population-level machine-learning model, and to distribute updated model parameters to the processor of the sensor device.
Dependencies are inferred from the claim text.