Detecting Pain During Cognitive Tasks via Visibility Graphs of Cortical Signals

Detecting pain is critical for developing adaptive systems in clinical and assistive settings, allowing for timely interventions. This work presents an approach to detect the presence of physical pain during the performance of cognitive tasks from cortical signals. Cortical signals from the motor and prefrontal cortices are acquired using functional near in-frared spectroscopy (fNIRS) during two cognitive tasks, per-formed in the absence and presence of physical pain. Visibil-ity graphs (VGs) of these signals are constructed, and graph metrics of averaged clustering coefficient <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(C)$</tex> and edge den-sity <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(D)$</tex> are extracted. Statistical analysis reveals differences in these metrics for graphs corresponding to tasks performed under no-pain (NP) versus with-pain (WP) conditions, partic-ularly for signals obtained from the motor cortex. The graph metrics were then used as features to a support vector machine (SVM), achieving an accuracy exceeding 80% in distinguishing between tasks performed with and without pain. Our findings suggest that metrics from VGs of cortical sig-nals may serve as potential biomarkers for pain during cog-nitive tasks. This approach could be especially beneficial for non-verbal patients using assistive brain-computer interfaces.