AUTOMATED DETECTION OF BRAIN DISORDERS

1 . A method for detection of pain using electroencephalogram signals comprising:

measuring electroencephalogram signals using electrodes attached to a head of a subject and circuitry to convert the electroencephalogram signals to digital data representative of the electroencephalogram signals for processing by a computer comprising a processor, memory accessible by the processor to store program instructions and data, and program instructions executable by the processor to perform:

bandpass filtering, at the computer, the digital data representative of the electroencephalogram signals to generate digital data representative of frequencies associated with spindles associated with pain;

performing, at the computer, a Hilbert transform on the digital data representative of frequencies associated with spindles associated with pain to generate digital data representative of the transformed data;

detecting, at the computer, an envelope of the digital data representative of the transformed data to generate envelope data;

detecting, at the computer, whether the envelope data exceeds a threshold to generate classification data indicating presence or absence of a spindle associated with pain; and

displaying or transmitting, at the computer, the classification data indicating the presence or absence of pain.

2 . The method of claim 1 , wherein a pass band of the bandpass filtering is about 8 Hz to 14 Hz.

3 . The method of claim 2 , wherein the Hilbert transform digital data ŝ(t) is generated according to

s

^

=

s



(

t

)

*

h



(

t

)

=

s



(

t

)

*

1

π





t

.

4 . The method of claim 3 , wherein the envelope digital data B(t) is generated according to B(t)=√{square root over (s 2 (t)+ŝ 2 (t))}, wherein s(t) is the bandpass filtered digital data.

5 . The method of claim 4 , wherein the classification data is generated by threshold detection according to:

detecting at least one peak of the envelope data using a first threshold and classifying that peak as a spindle;

when an adjacent data point of the envelope data is below the first threshold and is classified as not being a spindle, and the adjacent data point of the envelope data is above or equal to a second threshold, re-classifying that data point as a spindle; and

repeating re-classification of data point until no further data points are re-classified.

6 . A system for detection of pain using electroencephalogram signals, the system comprising:

at least one electrode attached to a head of a subject to measure electroencephalogram signals and circuitry to convert the electroencephalogram signals to digital data representative of the electroencephalogram signals;

a processor;

memory accessible by the processor;

computer program instructions stored in the memory and executable by the processor to perform:

bandpass filtering the digital data representative of the electroencephalogram signals to generate digital data representative of frequencies associated with spindles associated with pain;

performing a Hilbert transform on the digital data representative of frequencies associated with spindles associated with pain to generate digital data representative of the transformed data;

detecting an envelope of the digital data representative of the transformed data to generate envelope data;

detecting whether the envelope data exceeds a threshold to generate classification data indicating presence or absence of a spindle associated with pain; and

displaying or transmitting the classification data indicating the presence or absence of pain.

7 . The system of claim 6 , wherein a pass band of the bandpass filtering is about 8 Hz to 14 Hz.

8 . The system of claim 7 , wherein the Hilbert transform digital data ŝ(t) is generated according to

s

^

=

s



(

t

)

*

h



(

t

)

=

s



(

t

)

*

1

π





t

.

9 . The system of claim 8 , wherein the envelope digital data B(t) is generated according to B(t)=√{square root over (s 2 (t)+ŝ 2 (t))}, wherein s(t) is the bandpass filtered digital data.

10 . The system of claim 9 , wherein the classification data is generated by threshold detection according to:

detecting at least one peak of the envelope data using a first threshold and classifying that peak as a spindle;

when an adjacent data point of the envelope data is below the first threshold and is classified as not being a spindle, and the adjacent data point of the envelope data is above or equal to a second threshold, re-classifying that data point as a spindle; and

repeating re-classification of data point until no further data points are re-classified.

11 . A computer program product for detection of pain using electroencephalogram signals, the computer program product comprising a non-transitory computer readable storage having program instructions embodied therewith, the program instructions executable by a computer, to cause the computer to perform a method comprising:

measuring electroencephalogram signals using electrodes attached to a head of a subject and circuitry to convert the electroencephalogram signals to digital data representative of the electroencephalogram signals for processing by the computer comprising a processor, memory accessible by the processor to store program instructions and data, and program instructions executable by the processor to perform:

bandpass filtering, at the computer, the digital data representative of the electroencephalogram signals to generate digital data representative of frequencies associated with spindles associated with pain;

performing, at the computer, a Hilbert transform on the digital data representative of frequencies associated with spindles associated with pain to generate digital data representative of the transformed data;

detecting, at the computer, an envelope of the digital data representative of the transformed data to generate envelope data;

detecting, at the computer, whether the envelope data exceeds a threshold to generate classification data indicating presence or absence of a spindle associated with pain; and

displaying or transmitting, at the computer, the classification data indicating the presence or absence of pain.

12 . The computer program product of claim 11 , wherein a pass band of the bandpass filtering is about 8 Hz to 14 Hz.

13 . The computer program product of claim 12 , wherein the Hilbert transform digital data ŝ(t) is generated according to

s

^

=

s



(

t

)

*

h



(

t

)

=

s



(

t

)

*

1

π





t

.

14 . The computer program product of claim 13 , wherein the envelope digital data B(t) is generated according to B(t)=√{square root over (s 2 (t)+ŝ 2 (t))}, wherein s(t) is the bandpass filtered digital data.

15 . The computer program product of claim 14 , wherein the classification data is generated by threshold detection according to:

detecting at least one peak of the envelope data using a first threshold and classifying that peak as a spindle;

when an adjacent data point of the envelope data is below the first threshold and is classified as not being a spindle, and the adjacent data point of the envelope data is above or equal to a second threshold, re-classifying that data point as a spindle; and

repeating re-classification of data point until no further data points are re-classified.