Back to results
US 9,844,332 B2Granted
Anxiety meter
AssigneeHolland Bloorview Kids Rehabilitation Hospital
InventorsAzadeh Kushki, Evdokia Anagnostou
Life of this patent
Estimating the term…
Abstract
Methods and systems for detection of anxiety using physiological signals. The detection of anxiety may take place in real-time and in a naturalistic setting. A modified Kalman filter may be used.
Claims14
A system for detection of anxiety in a subject, the system comprising:
- an output device for providing feedback about presence of absence of anxiety to the subject or another party;
- a processor coupled to the output device, the processor being configured to:
- receive at least one physiological signal, from one or more sensors coupled to the processor, that is relevant to a measurement of anxiety;
- extract at least one feature from the at least one physiological signal, wherein the at least one extracted feature has a value that is affected by the subject's anxiety level;
- process the at least one extracted feature using a modified Kalman filter, the modified Kalman filter being modified to update a state model using a first weighting of the at least one extracted feature when the at least one extracted feature has a value within a predicted noise model, and to update the state model using a second weighting of the at least one extracted feature when the at least one extracted feature has a value outside of the predicted noise model, the second weighting being less than the first weighting;
- and
- provide one or more output signals to the output device to cause the output device to indicate presence of anxiety when the at least one extracted feature has a value outside of the predicted noise model.
4 more elements
A method, implemented in an electronic device, for detecting anxiety in a subject, the method comprising:
- receiving, from one or more sensors coupled to the electronic device, at least one physiological signal from the subject that is relevant to a measurement of anxiety;
- extracting at least one feature from the at least one physiological signal, wherein the extracted feature has a value that is affected by the subject's anxiety level;
- processing the at least one extracted feature using a modified Kalman filter, the modified Kalman filter being modified to update a state model using a first weighting of the at least one extracted feature when the at least one extracted feature has a value within a predicted noise model, and to update the state model using a second weighting of the at least one extracted feature when the at least one extracted feature has a value outside of the predicted noise model, the second weighting being less than the first weighting;
- and
- providing one or more output signals to an output device of the electronic device to cause the output device to indicate presence of anxiety when the at least one extracted feature has a value outside of the predicted noise model.
2 more elements
Dependencies are inferred from the claim text.