System and method for pain monitoring using a multidimensional analysis of physiological signals

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.

1 - 20 . (canceled) 
     
     
         21 . A method for monitoring pain of a patient, the method comprising:
 obtaining at least two physiological signals comprising electroencephalogram (EEG) and at least one signal selected from the group consisting of: Photoplethysmograph (PPG), Galvanic Skin Response (GSR), electrocardiogram (ECG), Blood pressure, blood volume change respiration, internal body temperature, skin temperature, electrooculography (EOG), pupil diameter, frontalis electromyogram (FEMG), electromyography (EMG), electro-gastro-gram (EGG), laser doppler velocimetry, end-tidal carbon dioxide, and accelerometer readings;   processing said at least two physiological signals to improve signal quality, thereby obtaining at least two processed signals;   generating a first vector, said first vector comprising at least three features extracted from said at least two physiological signals, wherein said at least three features comprise at least one feature selected from the group consisting of:   Power of alpha frequency band, Power of beta frequency band, Power of gamma frequency band, Power of delta frequency band, power of theta frequency band, Mean frequency, peak frequency, Spectral Edge Frequency, Approximate Entropy, Burst Suppression Ratio, BcSEF, WSMF, CUP, SpEn, BcSpEn, Beta Ratio, Histogram Parameters, AR parameters, Normalized slope descriptors, Barlow parameters, Wackermann parameters, Brain rate, SynchFastSlow, 80 HZ frequency amplitude and any combination thereof;   transforming said first vector into a second vector, said transformation comprising normalization; and   monitoring the pain status of the patient by applying a classification algorithm adapted to classify said second vector into a graduated scale representing the level of pain;   wherein said classification algorithm comprises an ensemble of classification and regression trees.   
     
     
         22 . The method of  claim 21 , wherein the at least three features further comprise PPG maximum rate (M) point, PPG dicrotic notch (N), PPG PP/PT/PN/NT/NM intervals, mean and std (variability) of intervals, PPG PP variability (PPG-HRV) in frequency bands: VLF, LF, MF, HF and LF/HF, area under the PPG curve (AUC), PPG spectrum envelope, PPG-HRV wavelet analysis, PPG-RSA (respiratory sinus arrhythmia), PPG mean Peak (P) amplitude, PPG Peak (P) mean amplitude, PPG Peak (P) std of amplitude, PPG Through (T) amplitude, PPG Trough (T) mean amplitude, PPG Trough (T) std of amplitude, PPG peak to peak intervals, PPG Peak-to-Peak High Frequency (P-P HF) Power, ECG Q/R/S/T/P amplitude mean and std (variability) of amplitude, ECG RR/PQ/PR/QT/RS/ST interval, mean and std (variability) of interval, ECG RR variability (ECG-HRV) in frequency bands: VLF, LF, MF, HF and LF/HF, ECG-RSA (respiratory sinus arrhythmia), ECG-HRV wavelet analysis, ECG-PPG pulse transition time (PTT), 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, GSR basal level, GSR number of peaks, temperature amplitude, mean and std of amplitude, temperature PP interval, mean and std (variability) of interval, temperature spectrum, temperature peak frequency, upper temperature peak amplitude, mean amplitude and std (variability) of amplitude, lower temperature peak amplitude mean amplitude and std (variability) of amplitude, respiratory rate, spectrum analysis of respiratory signal, mean rate and std (variability) of rate, EMG OMT/EMG spectrum analysis, EMG mean frequency, EMG peak frequency, EMG total power, BP Spectrum analysis, EMG SLOC, average/variability of end-tidal airway gasses, average of accelerometer X, Y, Z, theta, accelerometer movement analysis, coherence between 2 or more EEG/FEMG channels and combinations thereof. 
     
     
         23 . The method of  claim 21 , wherein the at least three features further comprise ECG-PPG PTT, ECG RR time intervals, ECG-HRV power of VLF, LF and HF frequency bands, respiration rate, spectrum analysis of respiratory signal, EEG/EMG spectrum analysis, BP spectrum analysis, GSR basal level, GSR number of peaks, coherence between 2 or more EEG/FEMG channels, accelerometer movement analysis; and combinations thereof. 
     
     
         24 . The method of  claim 21 , wherein the pain monitoring further comprises communicating the monitored pain to a receiving unit selected from the group consisting of: a higher processing center, person, caregiver, call center and any combination thereof. 
     
     
         25 . The method of  claim 21 , further comprising obtaining and processing a priori data, wherein the a priori data is selected from the group consisting of: environmental parameters, patient parameters, disease, stimulus, medicament and any combination thereof. 
     
     
         26 . The method according to  claim 21 , wherein the ensemble of classification and regression trees, comprises a random forest classifier or a boosting framework. 
     
     
         27 . The method of  claim 21 , wherein the classification algorithm is adapted for pain experienced with a particular disease, stimulus or medicament. 
     
     
         28 . The method of  claim 21 , wherein the patient is in a state of consciousness selected from the group consisting of: unconscious, under general anesthesia, sedated, partially sedated, awake, and semi-awake. 
     
     
         29 . 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 electroencephalogram (EEG) and at least one signal selected from the group consisting of: Photoplethysmograph (PPG), Galvanic Skin Response (GSR), electrocardiogram (ECG), Blood pressure, blood volume change, respiration, internal body temperature, skin temperature, electrooculography (EOG), pupil diameter, frontalis electromyogram (FEMG), electromyography (EMG), laser doppler velocimetry, electro-gastro-gram (EGG), end-tidal 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,
 Power of alpha frequency band, Power of beta frequency band, Power of gamma frequency band, Power of delta frequency band, power of theta frequency band, Mean frequency, peak frequency, Spectral Edge Frequency, Approximate Entropy, Burst Suppression Ratio, BcSEF, WSMF, CUP, SpEn, BcSpEn, Beta Ratio, Histogram Parameters, AR parameters, Normalized slope descriptors, Barlow parameters, Wackermann parameters, Brain rate, SynchFastSlow, 80 HZ frequency amplitude and 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. 
 
   
     
     
         30 . The system of  claim 29 , further comprising a display module for displaying the monitored pain. 
     
     
         31 . The system of  claim 29 , wherein the at least three features further comprise PPG maximum rate (M) point, PPG dicrotic notch (N), PPG PP/PT/PN/NT/NM intervals, mean and std (variability) of intervals, PPG PP variability (PPG-HRV) in frequency bands: VLF, LF, MF, HF and LF/HF, area under the PPG curve (AUC), PPG spectrum envelope, PPG-HRV wavelet analysis, PPG-RSA (respiratory sinus arrhythmia), PPG mean Peak (P) amplitude, PPG Peak (P) mean amplitude, PPG Peak (P) std of amplitude, PPG Through (T) amplitude, PPG Trough (T) mean amplitude, PPG Trough (T) std of amplitude, PPG peak to peak intervals, PPG Peak-to-Peak High Frequency (P-P HF) Power, ECG Q/R/S/T/P amplitude mean and std (variability) of amplitude, ECG RR/PQ/PR/QT/RS/ST interval, mean and std (variability) of interval, ECG RR variability (ECG-HRV) in frequency bands: VLF, LF, MF, HF and LF/HF, ECG-RSA (respiratory sinus arrhythmia), ECG-HRV wavelet analysis, ECG-PPG pulse transition time (PTT), 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, GSR basal level, GSR number of peaks, temperature amplitude, mean and std of amplitude, temperature PP interval, mean and std (variability) of interval, temperature spectrum, temperature peak frequency, upper temperature peak amplitude, mean amplitude and std (variability) of amplitude, lower temperature peak amplitude mean amplitude and std (variability) of amplitude, respiratory rate, spectrum analysis of respiratory signal, mean rate and std (variability) of rate, EMG OMT EMG spectrum analysis, EMG mean frequency, EMG peak frequency, EMG total power, BP Spectrum analysis EMG SLOC, average/variability of end-tidal airway gasses, average of accelerometer X, Y, Z, theta, accelerometer movement analysis, coherence between 2 or more EEG/FEMG channels and combinations thereof. 
     
     
         32 . The system of  claim 29 , wherein the at least three features further comprise ECG-PPG PTT, ECG RR time intervals, ECG-HRV power of VLF, LF and HF frequency bands, respiration rate, spectrum analysis of respiratory signal, EEG/EMG spectrum analysis, BP spectrum analysis, coherence between 2 or more EEG/FEMG channels, GSR basal level, GSR number of peaks, accelerometer movement analysis; and combinations thereof. 
     
     
         33 . The system according to  claim 29 , wherein the ensemble of classification and regression trees comprises a random forest classifier or a boosting framework. 
     
     
         34 . The system of  claim 29 , wherein the signal acquisition module is further adapted to obtain a priori data selected from the group consisting of: environmental parameters, patient parameters, disease, stimulus, medicament and any combination thereof, and wherein the processing module is further adapted to process the priori data. 
     
     
         35 . The system of  claim 29 , further comprising a communication module for communicating the monitored pain of the patient to a receiving unit selected from the group consisting of a higher processing center, a person, a caregiver, a call center and any combination thereof.