Back to results
US 10,743,778 B2Granted
System and method for pain monitoring using a multidimensional analysis of physiological signals
AssigneeMedasense Biometrics Ltd.
InventorsGalit Zuckerman-Stark, Mark Kliger
Life of this patent
Estimating the term…
Abstract
The present invention is for a method and system for pain classification and monitoring optionally in a subject that is an awake, semi-awake or sedated.
Claims15
A method for monitoring pain of a patient, the method comprising:
- obtaining at least two physiological signals comprising Galvanic Skin Response and at least one signal selected from the group consisting of:
- blood volume change, PPG, continuous blood pressure, laser Doppler velocimetry, vasomotor reflex electrocardiogram (ECG), respiration, internal body temperature, skin temperature, electrooculography (EOG), pupil diameter, electroencephalogram (EEG), frontalis electromyogram (FEMG), electromyography (EMG), electro-gastro-gram (EGG), partial pressure of carbon dioxide, and accelerometer readings;
- processing the at least two physiological signals to improve signal quality, thereby obtaining at least two processed signals;
- generating a first vector, the first vector comprising at least three features extracted from the at least two physiological signals,
- wherein the at least three features comprise at least one feature selected from the group consisting of:
- GSR amplitude, mean amplitude and std (variability) of amplitude, GSR PP interval, mean and std (variability) of interval, GSR phasic EDA amplitude, spectrum of GSR signal, peak frequency, GSR wavelet analysis, GSR basal level, GSR number of peaks, or any combination thereof;
- transforming the first vector into a second vector, the transformation comprising normalization;
- and
- monitoring the pain status of the patient by applying a classification algorithm adapted to classify the second vector into a graduated scale representing at least three level of pain;
- wherein the classification algorithm comprises an ensemble of classification and regression trees;
- and
- wherein the patient is unconscious.
9 more elements
A system for monitoring a pain of an unconscious patient, the system comprising:
- a signal acquisition module comprising at least one sensor and/or transducers for measuring and/or obtaining at least two physiological signals comprising Galvanic Skin Response (GSR) and at least one signal selected from the group consisting of:
- blood volume change;
- electrocardiogram (ECG), respiration, internal body temperature, skin temperature, electrooculography (EOG), pupil diameter, electroencephalogram (EEG), frontalis electromyogram (FEMG), electromyography (EMG), electro-gastro-gram (EGG), partial pressure of carbon dioxide, and accelerometer readings;
- and
- a processing module for processing the at least two physiological signals, the processing comprising:
- i. processing the at least two physiological signals to improve signal quality, thereby forming at least two processed signals;
- ii. generating a first vector, the first vector comprising at least three features extracted from the at least two physiological signals,
- wherein the at least three features comprise at least one feature selected from the group consisting of:
- GSR amplitude, mean amplitude and std (variability) of amplitude, GSR PP interval, mean and std (variability) of interval, GSR phasic EDA amplitude, mean amplitude and std (variability) of amplitude, spectrum of GSR signal, peak frequency, GSR wavelet analysis or any combination thereof,
- iii. transforming the first vector into a second vector the transformation comprising normalization;
- and
- iv. monitoring the pain of the patient by applying a classification algorithm adapted to classify the second vector into graduated scale representing at least three level of pain;
- wherein the classification algorithm comprises an ensemble of classification and regression trees.
10 more elements
Dependencies are inferred from the claim text.