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

• US 8,512,240 B1
• Filed: 05/14/2010
• Issued: 08/20/2013
• Est. Priority Date: 11/14/2007
• Status: Active Grant

• Current Assignee: Medasense Biometrics Ltd.
• Original Assignee: Medasense Biometrics Ltd.
• Inventors: Zuckerman-Stark, Galit, Kliger, Mark
• Primary Examiner(s): Thomson, Bill
• Assistant Examiner(s): Sands, Davin K
• Application Number:
  US12/779,963
• Time in Patent Office: 1,194 Days
• Field of Search: 600/300, 600/301, 128903-905, 128/920
• US Class Current: 600/301
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 3/112 for measuring diameter of pupils
• CPC Class Codes: A61B 5/02 Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
• CPC Class Codes: A61B 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/0261 using optical means, e.g. infrared light
• CPC Class Codes: A61B 5/0295 using plethysmography, i.e. measuring the variations in the volume of a body part as modified by the circulation of blood therethrough, e.g. impedance plethysmography
• CPC Class Codes: A61B 5/0533 Measuring galvanic skin response
• CPC Class Codes: A61B 5/0836 Measuring rate of CO2 production
• CPC Class Codes: A61B 5/24 Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
• CPC Class Codes: A61B 5/33 specially adapted for cooperation with other devices
• CPC Class Codes: A61B 5/392 Detecting gastrointestinal contractions
• CPC Class Codes: A61B 5/4821 Determining level or depth of anaesthesia A61B5/1106 takes precedence
• CPC Class Codes: A61B 5/4824 Touch or pain perception evaluation A61B5/4821 takes precedence
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/726 using Wavelet transforms
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 5/7275 : Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/7282 : Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: G06N 20/00 : Machine learning
• CPC Class Codes: G16H 40/63 : for local operation
• CPC Class Codes: G16H 50/20 : for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 : for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/70 : for mining of medical data, e.g. analysing previous cases of other patients

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.

Claims

1. A method for monitoring a pain of a patient by analyzing at least two physiological signals, the method including comprising:

a. obtaining said at least two physiological signals, comprising Photoplethysmograph (PPG) and Galvanic Skin Response (GSR);

b. processing said at least two physiological signals to improve signal quality, thereby forming a plurality of processed physiological signals; and

c. extracting from said at least two physiological signals at least three features thereby forming a first vector, wherein said at least three features are selected from a group consisting at least of;

PPG mean Peak (P) amplitude, PPG peak to peak time intervals, PPG Peak-to-Peak High Frequency (PPG P-P HF) Power, GSR amplitude, and GSR peak to peak time intervals;

d. transforming said first vector into a second vector, said transformation comprises normalization; and

e. monitoring said pain of said 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.

2. The method of claim 1, wherein said pain detection monitoring further comprises:

communicating said monitored pain 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.

3. The method of claim 1, wherein said at least two physiological signals further comprise at least one signal selected from the group consisting of:

electrocardiogram (ECG), blood pressure, respiration, internal body temperature, skin temperature, electrooculography (EOG}, pupil diameter, electroencephalogram (EEG), frontalis electromyogram (FEMG), electromyography (EMG), electro-gastro-gram (EGG), laser doppler velocimetry (LDV), partial pressure of carbon dioxide, and accelerometer readings.

4. The method of claim 1, further comprising obtaining and processing a priori data, wherein said a priori data is selected from the group consisting of:

environmental parameters, patient parameters, disease, stimulus, medicament and any combination thereof.

5. The method according to claim 1, wherein said ensemble of classification and regression trees algorithm comprises a random forest classification algorithm.

6. The method according to claim 1, wherein said ensemble of classification and regression trees algorithm comprises a Boosting framework.

7. The method of claim 1, wherein said ensemble of classification and regression trees algorithm is adapted for pain experienced with a particular disease, stimulus or medicament.

8. The method of claim 1, wherein said patient is in a state of consciousness selected from the group consisting of:

unconscious, under general anesthesia, sedated, partially sedated, awake, and semi-awake.

22. The method of claim 8, adapted to facilitate pain classification in an awake patient, a partially sedated patient or a sedated patient;

wherein said first vector further comprises at least one feature selected from the group consisting of;

respiration rate, skin temperature, accelerometer variability, EMG total power, pulse transition time and any combination thereof.

23. The method of claim 8, adapted to facilitate classification in a patient under sedation or under general anesthesia;

wherein said first vector further comprises at least one feature selected from the group consisting of;

EEG power of frequency bands, PPG dicrotic notch amplitude and, pulse transition time, Coherence between 2 or more EEG/FEMG channels and any combination thereof.

24. The method of claim 8, adapted to facilitate pain classification in a patient under general anesthesia;

wherein said first vector further comprises at least one feature selected from the group consisting of;

PPG P-P variability LF power, PPG P-P variability VLF power, ECG R-R variability LF power, ECG R-R variability VLF power, pulse transition time, PPG dicrotic notch amplitude and any combination thereof.

25. The method of claim 8, adapted to facilitate pain classification in an unconscious patient;

wherein said first vector further comprises at least one feature selected from the group consisting of;

EEG power of frequency bands, EEG peak frequency, Coherence between 2 or more EEG/FEMG channels, respiration rate, skin temperature and any combination thereof.

26. The method of claim 7, adapted to facilitate pain classification in chronic pain patients;

wherein said first vector further comprises at least one feature selected from the group consisting of;

respiration rate, skin temperature, accelerometer variability, pulse transition time, EMG total power and any combination thereof.

27. The method of claim 1 wherein said first vector further comprises at least one feature selected from the group consisting of:

blood pressure, end tidal CO2 level, end tidal level of anesthetic agents, body temperature, dosages of pain reducing drugs and any combination thereof.

9. A system for monitoring a pain of a patient by analyzing at least two physiological signals comprising:

a. a signal acquisition module comprising a plurality of sensors and/or transducers for measuring and/or obtaining said at least two physiological signals from a subject, wherein said at least two physiological signals comprise Photoplethysmograph (PPG) and Galvanic Skin Response (GSR); and

b. a processing module configured to process said at least two physiological signals, said processing comprising;

i. processing said at least two physiological signals to improve signal quality thereby forming a plurality of processed physiological signals;

ii. extracting from said plurality of processed physiological signals at least three features thereby forming a first vector, wherein said at least three features are selected from a group consisting at least of;

PPG mean Peak (P) amplitude, PPG peak to peak time intervals, PPG P-P HF Power, GSR amplitude and GSR peak to peak time intervals;

iii. transforming said first vector into a second vector, said transformation comprises normalization; and

iv. monitoring said pain of said 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.

10. The system of claim 9, further comprising a display module for displaying said monitored pain.

11. The system of claim 9, wherein said signal acquisition module further comprises at least one sensor selected from the group consisting of:

ECG, blood pressure, respiration, internal body temperature, skin temperature, EOG, pupil diameter monitoring, EEG, FEMG, EMG, EGG, LDV, capnograph, and accelerometer.

12. The system according to claim 9, wherein said ensemble of classification and regression trees algorithm comprises a random forest classification algorithm.

13. The system according to claim 9, wherein said ensemble of classification and regression trees algorithm comprises a Boosting framework.

14. The system of claim 9, wherein said classification is adapted for pain experienced with a particular disease, stimulus or medicament.

15. The system of claim 9, wherein said patient is in a state of consciousness selected from the group consisting of:

unconscious, under general anesthesia, sedated, partially sedated, awake, and semi-awake.

16. The system of claim 15, adapted to facilitate pain classification in an awake patient, a partially sedated patient or a sedated patient;

wherein said first vector further comprises at least one feature selected from the group consisting of;

respiration rate, skin temperature, accelerometer variability, EMG total power, pulse transition time and any combination thereof.

17. The system of claim 15, adapted to facilitate classification in a patient under sedation or under general anesthesia;

wherein said first vector further comprises at least one feature selected from the group consisting of;

EEG power of frequency bands, PPG dicrotic notch amplitude, pulse transition time, Coherence between 2 or more EEG/FEMG channels and any combination thereof.

18. The system of claim 15, adapted to facilitate pain classification in a patient under general anesthesia;

wherein said first vector further comprises at least one feature selected from the group consisting of;

PPG Peak-to-Peak (PPG P-P) variability Low Frequency (LF) power, PPG P-P variability Very Low Frequency (VLF) power, ECG R-R variability LF power, ECG R-R variability VLF power, pulse transition time, PPG dicrotic notch amplitude and any combination thereof.

19. The system of claim 15, adapted to facilitate pain classification in an unconscious patient;

wherein said first vector further comprises at least one feature selected from the group consisting of;

EEG power of frequency bands, EEG peak frequency, Coherence between 2 or more EEG/FEMG channels, respiration rate, skin temperature and any combination thereof.

20. The system of claim 14, adapted to facilitate pain classification in chronic pain patients;

wherein said first vector further comprises at least one feature selected from the group consisting of;

respiration rate, skin temperature, accelerometer variability, pulse transition time, EMG total power and any combination thereof.

21. The system of claim 9, wherein said first vector further comprises at least one feature extracted from patient monitors selected from the group consisting of:

blood pressure, end tidal C02 level, end tidal level of anesthetic agents, body temperature, dosages of pain reducing drugs and any combination thereof.

28. The system of claim 9, wherein said 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 said processing module is further adapted to process said priori data.

29. The system of claim 9, further comprising a communication module for communicating said monitored pain of said 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.