Machine learning and EEG can classify passive viewing of discrete categories of visual stimuli but not the observation of pain.

Previous studies have demonstrated the potential of machine learning (ML) in classifying physical pain from non-pain states using electroencephalographic (EEG) data. However, the application of ML to EEG data to categorise the observation of pain versus non-pain images of human facial expressions or scenes depicting pain being inflicted has not been explored. The present study aimed to address this by training Random Forest (RF) models on cortical event-related potentials (ERPs) recorded while participants passively viewed faces displaying either pain or neutral expressions, as well as action scenes depicting pain or matched non-pain (neutral) scenarios. Ninety-one participants were recruited across three samples, which included a model development group (n = 40) and a cross-subject validation group (n = 51). Additionally, 25 participants from the model development group completed a second experimental session, providing a within-subject temporal validation sample. The analysis of ERPs revealed an enhanced N170 component in response to faces compared to action scenes. Moreover, an increased late positive potential (LPP) was observed during the viewing of pain scenes compared to neutral scenes. Additionally, an enhanced P3 response was found when participants viewed faces displaying pain expressions compared to neutral expressions. Subsequently, three RF models were developed to classify images into faces and scenes, neutral and pain scenes, and neutral and pain expressions. The RF model achieved classification accuracies of 75%, 64%, and 69% for cross-validation, cross-subject, and within-subject classifications, respectively, along with reasonably calibrated predictions for the classification of face versus scene images. However, the RF model was unable to classify pain versus neutral stimuli above chance levels when presented with subsequent tasks involving images from either category. These results expand upon previous findings by externally validating the use of ML in classifying ERPs related to different categories of visual images, namely faces and scenes. The results also indicate the limitations of ML in distinguishing pain and non-pain connotations using ERP responses to the passive viewing of visually similar images.

Hold me or stroke me? Individual differences in static and dynamic affective touch.

Low-threshold mechanosensory C-fibres, C-tactile afferents (CTs), respond optimally to sensations associated with a human caress. Additionally, CT-stimulation activates brain regions associated with processing affective states. This evidence has led to the social touch hypothesis, that CTs have a key role in encoding the affective properties of social touch. Thus, to date, the affective touch literature has focussed on gentle stroking touch. However, social touch interactions involve many touch types, including static, higher force touch such as hugging and holding. This study aimed to broaden our understanding of the social touch hypothesis by investigating relative preference for static vs dynamic touch and the influence of force on these preferences. Additionally, as recent literature has highlighted individual differences in CT-touch sensitivity, this study investigated the influence of affective touch experiences and attitudes, autistic traits, depressive symptomology and perceived stress on CT-touch sensitivity. Directly experienced, robotic touch responses were obtained through a lab-based study and vicarious touch responses through an online study where participants rated affective touch videos. Individual differences were determined by self-report questionnaire measures. In general, static touch was preferred over CT-non-optimal stroking touch, however, consistent with previous reports, CT-optimal stroking (velocity 1-10 cm/s) was rated most pleasant. However, static and CT-optimal vicarious touch were rated comparably for dorsal hand touch. For all velocities, 0.4N was preferred over 0.05N and 1.5N robotic touch. Participant dynamic touch quadratic terms were calculated for robotic and vicarious touch as a proxy CT-sensitivity measure. Attitudes to intimate touch significantly predict robotic and vicarious quadratic terms, as well as vicarious static dorsal hand touch ratings. Perceived stress negatively predicted robotic static touch ratings. This study has identified individual difference predictors of CT-touch sensitivity. Additionally, it has highlighted the context dependence of affective touch responses and the need to consider static, as well as dynamic affective touch.