Abstract
Pain diagnosis for nonverbal patients represents a challenge in clinical settings. Neuroimaging methods, such as functional magnetic resonance imaging and functional near-infrared spectroscopy (fNIRS), have shown promising results to assess neuronal function in response to nociception and pain. Recent studies suggest that neuroimaging in conjunction with machine learning models can be used to predict different cognitive tasks. The aim of this study is to expand previous studies by exploring the classification of fNIRS signals (oxyhaemoglobin) according to temperature level (cold and hot) and corresponding pain intensity (low and high) using machine learning models. Toward this aim, we used the quantitative sensory testing to determine pain threshold and pain tolerance to cold and heat in 18 healthy subjects (three females), mean age±standard deviation (31.9±5.5). The classification model is based on the bag-of-words approach, a histogram representation used in document classification based on the frequencies of extracted words and adapted for time series; two learning algorithms were used separately, K-nearest neighbor (K-NN) and support vector machines (SVM). A comparison between two sets of fNIRS channels was also made in the classification task, all 24 channels and 8 channels from the somatosensory region defined as our region of interest (RoI). The results showed that K-NN obtained slightly better results (92.08%) than SVM (91.25%) using the 24 channels; however, the performance slightly dropped using only channels from the RoI with K-NN (91.53%) and SVM (90.83%). These results indicate potential applications of fNIRS in the development of a physiologically based diagnosis of human pain that would benefit vulnerable patients who cannot self-report pain.
Highlights
Pain is a subjective experience, and no objective clinically available diagnostic test exists to measure it
In an functional near-infrared spectroscopy (fNIRS) study, Pourshoghi et al.[21] used a support vector machines (SVM) classifier to classify low pain and high pain from healthy subjects after a cold pressor test with 94% accuracy. These results show that pain recognition and classification is plausible using neuroimaging methods, the results from these studies advocate for the use of machine learning techniques to predict human pain
The major contributions of this study are (1) heat and cold pain are differentiated using fNIRS signals (HbO) as well as their corresponding pain intensity using machine learning techniques; (2) we report the investigation of two state-ofthe-art classifiers to distinguish between thermal noxious stimuli; and (3) we investigated the accuracy of our classifiers with respect to the region of interest (8 channels) or whole head probe (24 channels)
Summary
Pain is a subjective experience, and no objective clinically available diagnostic test exists to measure it. In clinical practice, there are two main approaches for the assessment of pain: self-reported and clinical judgment. Self-reported methods try to rate patient’s pain by verbal or numeric self-rating scales, such as visual analogue scales, verbal descriptor scales, numerical rating scales, or the MacGill pain questionnaire. Pain assessment by clinical judgment is based on testing and learning from observations of the type, significance, and context of the patient’s pain perception. Self-report is the most accepted method and provides the most valid assessment in clinical practice. When self-reports are unavailable or in doubt, observational measures can be used as a complement or substitute.[1]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 call
