Classification of Game Demand and the Presence of Experimental Pain Using Functional Near-Infrared Spectroscopy

Pain tolerance can be increased by the introduction of an active distraction, such as a computer game. This effect has been found to moderated game demand, i.e., demand = higher pain tolerance. A study was performed classify level and presence using implicit measures from functional Near-InfraRed Spectroscopy (fNIRS) heart rate features electrocardiogram (ECG). Twenty participants played racing that configured induce low (Easy) or high (Hard) levels demand. Both Easy Hard were with without experimental cold pressor test protocol. Eight channels fNIRS data recorded montage frontal central-parietal sites located on midline. Features generated these data, subset which selected for classification RELIEFF method. Classifiers (Easy vs. Hard) (pain no-pain) developed five methods: Support Vector Machine (SVM), k-Nearest Neighbour (kNN), Naive Bayes (NB) Random Forest (RF). These models validated ten fold cross-validation procedure. The SVM approach derived only method classified at than chance (accuracy 0.66, F1 0.68). It not possible no-pain level. results demonstrate viability utilising difficulty classifying when another task is present.