Neurometric assessment of intraoperative anesthetic

• US 5,775,330 A
• Filed: 07/22/1996
• Issued: 07/07/1998
• Est. Priority Date: 07/22/1996
• Status: Expired due to Fees

• Current Assignee: Battelle Memorial Institute
• Original Assignee: Battelle Memorial Institute
• Inventors: Keller, Paul E., Kangas, Lars J.
• Primary Examiner(s): JAWORSKI, FRANCIS J
• Application Number:
  US08/681,196
• Time in Patent Office: 715 Days
• Field of Search: 128/731-733, 128/923, 395/22-24
• US Class Current: 600/544
• CPC Class Codes: A61B 5/1106 to assess neuromuscular blockade, e.g. to estimate depth of anaesthesia
• CPC Class Codes: A61B 5/4821 Determining level or depth of anaesthesia A61B5/1106 takes precedence
• CPC Class Codes: A61B 5/6814 Head
• CPC Class Codes: A61B 5/7257 using Fourier 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: A61M 16/01 specially adapted for anaesthetising A61M16/104, A61M16/18 take precedence
• CPC Class Codes: A61M 2230/10 Electroencephalographic signals
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: Y10S 128/923 by comparison of patient data to other data

Abstract

The present invention is a method and apparatus for collecting EEG data, reducing the EEG data into coefficients, and correlating those coefficients with a depth of unconsciousness or anesthetic depth, and which obtains a bounded first derivative of anesthetic depth to indicate trends. The present invention provides a developed artificial neural network based method capable of continuously analyzing EEG data to discriminate between awake and anesthetized states in an individual and continuously monitoring anesthetic depth trends in real-time. The present invention enables an anesthesiologist to respond immediately to changes in anesthetic depth of the patient during surgery and to administer the correct amount of anesthetic.

Claims

1. A method of monitoring an anesthetic depth of a person, comprising the steps of:

(a) placing a plurality of EEG electrodes on the person'"'"'s head;

(b) obtaining an EEG signal continuously from each of said EEG electrodes;

(c) windowing said continuous EEG signal into consecutive samples;

(d) transforming from a time domain to a frequency domain each of said consecutive samples of the EEG signal; and

(e) inputting said transformed consecutive samples into an artificial neural network having a plurality of input nodes and one output node, and correlating said transformed consecutive samples with said anesthetic depth as a scaled numeric value.

2. The method as recited in claim 1, further comprising the step of:

(f) obtaining a bounded first derivative of said correlation for obtaining a trend.

3. The method as recited in claim 2, wherein said bounded first derivative is obtained from a slope between points averaged ahead of and behind a time (t).

4. The method as recited in claim 2, wherein said anesthetic depth and said trend are updated continuously.

5. The method as recited in claim 4, wherein updated continuously is at least every second.

6. The method as recited in claim 1, wherein said transforming is with a Fourier transform obtaining real and imaginary coefficients.

7. The method as recited in claim 6, further comprising obtaining magnitude coefficients from said Fourier transform, and binning said magnitude coefficients.

8. The method as recited in claim 7, further comprising the step of adjusting the binned magnitude coefficients.

9. The method as recited in claim 8, wherein adjusting comprises the steps of:

(a) subtracting an average spectrum, coefficient by coefficient and obtaining coefficient differences.

10. The method as recited in claim 7, wherein inputting comprises the steps of:

(a) entering a binned magnitude coefficient into a particular input node of the artificial neural network.

11. The method as recited in claim 1, wherein said windowing contains at least 64 samples.

12. The method as recited in claim 1, wherein inputting comprises the steps of:

(a) entering a single magnitude coefficient into a particular input node of the artificial neural network.

13. An apparatus for monitoring an anesthetic depth of a person, comprising:

(a) a plurality of EEG electrodes on the person'"'"'s head;

(b) a signal processor that receives a spectra of EEG signal from each of said EEG electrodes, and transforms said spectra of EEG signal from a time domain to a frequency domain into magnitude coefficients; and

(c) an artificial neural network having a plurality of input nodes and one output node, said plurality of input nodes that receives said magnitude coefficients from said signal processor and correlates said magnitude coefficients with said anesthetic depth as a scaled numeric value.

14. The apparatus as recited in claim 13, further comprising:

(d) a post processor that obtains a bounded first derivative of said anesthetic depth.

15. A method of monitoring an anesthetic depth of a person, comprising the steps of:

(a) placing a plurality of EEG electrodes on the person'"'"'s head;

(b) obtaining an EEG signal continuously from each of said EEG electrodes;

(c) windowing said continuous EEG signal into consecutive samples;

(d) transforming each of said consecutive samples of the EEG signal;

(e) inputting said transformed consecutive samples into an artificial neural network and correlating said transformed signal with said anesthetic depth; and

(f) obtaining a bounded first derivative of said correlation for obtaining a trend.

16. The method as recited in claim 15, wherein said transforming is with a Fourier transform obtaining real and imaginary coefficients.

17. The method as recited in claim 16, further comprising obtaining magnitude coefficients from said Fourier transform, and binning said magnitude coefficients.

18. The method as recited in claim 15, wherein said windowing contains at least 64 samples.

19. The method as recited in claim 15, wherein said bounded first derivative is obtained from a slope between points averaged ahead of and behind a time (t).

20. The method as recited in claim 15, wherein said anesthetic depth and said trend are updated continuously.