Abstract
We introduce the application of functional data analysis (fDA) on functional near-infrared spectroscopy (fNIRS) signals for the development of an accurate and clinically practical assessment method of pain perception. We used the cold pressor test to induce different levels of pain in healthy subjects while the fNIRS signal was recorded from the frontal regions of the brain. We applied fDA on the collected fNIRS data to convert discrete samples into continuous curves. This method enabled us to represent the curves as a linear combination of basis functions. We utilized bases coefficients as features that represent the shape of the signals (as opposed to extracting defined features from signal) and used them to train a support vector machine to classify the signals based on the level of induced pain. We achieved 94% of accuracy to classify low-pain and high-pain signals. Moreover applying hierarchical clustering on the coefficients, we found three clusters in the data which represented low-pain (one cluster) and high-pain groups (two clusters) with an accuracy of 91.2%. The center of these clusters can represent the prototype fNIRS response of that pain level.
Highlights
During the past two decades, neurophysiological techniques that measure cerebral metabolism and circulation changes have been widely employed to open a window into human cerebral responses to pain with a long-term goal of obtaining a more direct measurement of pain perception
There has been shown a relation between subjects' report of an ongoing pain and blood oxygen level dependent (BOLD) signal acquired by functional magnetic resonance imaging (fMRI).[1]
The rest of the paper is organized as follows: in Sec. 2, we shortly describe the methodology behind our measurement system, the mathematical techniques that we have employed for classification and feature selection, the functional data analysis (fDA) framework that we have applied on the functional near-infrared spectroscopy (fNIRS) signal and our experiment protocol; in Sec. 3, we present the application of fDA on the fNIRS data collected during a cold pressor test and demonstrate both classification and clustering results
Summary
During the past two decades, neurophysiological techniques that measure cerebral metabolism and circulation changes have been widely employed to open a window into human cerebral responses to pain with a long-term goal of obtaining a more direct measurement of pain perception. There has been shown a relation between subjects' report of an ongoing pain and blood oxygen level dependent (BOLD) signal acquired by fMRI.[1] Similar relation has been reported between subjects' self-report and functional near-infrared spectroscopy (fNIRS) parameters.[2,3,4,5,6,7,8] For example, Lee et al.[4] reported that as the intensity of the noxious pressure stimuli increases, the HbO2 in the frontal cortex increases as well, consistent with an increase in the perceived pain. Applying machine-learning techniques on neuroimaging data in the field of pain assessment has shown promising results in recent years. Marquand et al.[9] showed that using fMRI data from an individual, one could train a support vector machine (SVM) to predict the same individual’s pain.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
