Artificial intelligence and especially deep learning methods have achieved outstanding results for various applications in the past few years. Pain recognition is one of them, as various models have been proposed to replace the previous gold standard with an automated and objective assessment. While the accuracy of such models could be increased incrementally, the understandability and transparency of these systems have not been the main focus of the research community thus far. Thus, in this work, several outcomes and insights of explainable artificial intelligence applied to the electrodermal activity sensor data of the PainMonit and BioVid Heat Pain Database are presented. For this purpose, the importance of hand-crafted features is evaluated using recursive feature elimination based on impurity scores in Random Forest (RF) models. Additionally, Gradient-weighted class activation mapping is applied to highlight the most impactful features learned by deep learning models. Our studies highlight the following insights: (1) Very simple hand-crafted features can yield comparative performances to deep learning models for pain recognition, especially when properly selected with recursive feature elimination. Thus, the use of complex neural networks should be questioned in pain recognition, especially considering their computational costs; and (2) both traditional feature engineering and deep feature learning approaches rely on simple characteristics of the input time-series data to make their decision in the context of automated pain recognition.

Multiple attempts to quantify pain objectively using single measures of physiological body responses have been performed in the past, but the variability across participants reduces the usefulness of such methods. Therefore, this study aims to evaluate whether combining multiple autonomic parameters is more appropriate to quantify the perceived pain intensity of healthy subjects (HSs) and chronic back pain patients (CBPPs) during experimental heat pain stimulation. HS and CBPP received different heat pain stimuli adjusted for individual pain tolerance via a CE-certified thermode. Different sensors measured physiological responses. Machine learning models were trained to evaluate performance in distinguishing pain levels and identify key sensors and features for the classification task. The results show that distinguishing between no and severe pain is significantly easier than discriminating lower pain levels. Electrodermal activity is the best marker for distinguishing between low and high pain levels. However, recursive feature elimination showed that an optimal subset of features for all modalities includes characteristics retrieved from several modalities. Moreover, the study’s findings indicate that differences in physiological responses to pain in HS and CBPP remain small.

Offset analgesia (OA) is believed to reflect the efficiency of the endogenous pain modulatory system. However, the underlying mechanisms are still being debated. Previous research suggested both, central and peripheral mechanisms, with the latter involving the influence of specific A-delta-fibers. Therefore, this study aimed to investigate the influence of a non-ischaemic A-fiber conduction blockade on the OA response in healthy participants. A total of 52 participants were recruited for an A-fiber conduction blockade via compression of the superficial radial nerve. To monitor fiber-specific peripheral nerve conduction capacity, quantitative sensory testing was performed continuously. Before, during and after the A-fiber block, an individualized OA-paradigm was applied to the dorsum of both hands (blocked and control side were randomized). Pain intensity of each heat stimulus was evaluated by an electronic visual analogue scale. A successful A-fiber conduction blockade was achieved in thirty participants. Offset analgesia has been verified within time (before, during, after blockade), and condition (blocked and control side) (p < 0.01, d > 0.5). Repeated measurements ANOVA showed no significant interaction effects between OA within condition and time (p = 0.24, η²_p = 0.05). Hence, no significant effect of A-fiber blockade was detected on OA during noxious heat stimulation. The results suggest that peripheral A-fiber afferents may play a minor role in OA compared to alternative central mechanisms or other fibers. However, further studies are needed to substantiate a central rather than peripheral influence on OA. PERSPECTIVE: This article presents the observation of offset analgesia before, during and after a successful A-fiber conduction blockade in healthy volunteers. A better understanding of the mechanisms of offset analgesia and endogenous pain modulation in general may help to explain the underlying aspects of pain disorders.