Investigation of Physical Pain Existence And Intensity Through Electroencephalogram Analysis
Pain is a complex subjective unpleasant experience that can potentially cause tissue damage. Its complex nature makes it severely hard to be measured objectively. Hence, the main method used, clinically, for assessing pain is self-report; however, this method is not possibly adapted in a huge number...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2021
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Pain is a complex subjective unpleasant experience that can potentially cause tissue damage. Its complex nature makes it severely hard to be measured objectively. Hence, the main method used, clinically, for assessing pain is self-report; however, this method is not possibly adapted in a huge number of vulnerable populations or by noncommunicative patients such as those with disorders of speech and consciousness. Thus, the availability of an objective measure of the subjective pain perception that complements the self-report pain assessments is a great significant demand in several clinical applications. This study aims to provide a clue for the betterment of the collective scientific understanding of the brain’s activities inflicted by physical pain and helps in building a reliable automated prediction of pain. To serve this purpose, a careful experiment protocol has been designed to collect the needed data and a comprehensive analysis was carried out to allow the identification and quantification of the physical nociceptive pain. A novel approach to objectively quantify the subjective perception of pain has been proposed. Signal processing techniques were integrated with machine learning principles to learn brain signals associated with pain and classify them into one of four pain intensities (no pain, low, moderate, and high). The signal processing revealed a negative correlation between the Alpha frequency band power and the pain intensity, and the developed classifier could achieve an accuracy of 90.05%. A graphical user interface was designed for the system to provide easier user interaction. Further relative correlations and conclusions were made, and they are demonstrated herewith in this report along with some recommendations for future works. |
|---|