Quantitative sensory testing response patterns to capsaicin- and ultraviolet-B-induced local skin hypersensitization in healthy subjects: a machine-learned analysis

Effect of repeated topical capsaicin gel administration on oral thermal quantitative sensory testing: A two-arm longitudinal study

OBJECTIVES

Few studies used thermal quantitative sensory testing to assess the effects of repeated capsaicin gel administration in the oral cavity. This study aimed to investigate thermal sensory and pain thresholds before and after repeated capsaicin gel administration.

SUBJECTS AND METHODS

Ten healthy females (22 ± 2 years) applied a capsaicin gel on the gingival mucosa twice daily for 14 days, and heat pain threshold, warm detection threshold, cold pain threshold, and cold detection threshold were assessed on the oral mucosa. Measurements were performed before and after the 14 days and were compared to a control sample (n = 10, all females, 23 ± 3 years).

RESULTS

Capsaicin increased heat pain threshold in the anterior maxilla by 2.9°C (95% CI: 1.6-4.2) (p < 0.001) and in the anterior mandible by 2.2°C (95% CI: 1.0-3.4) (p = 0.001), similar to warm detection threshold that increased by Δ1.1°C (95% CI: 0.3-1.9) (p = 0.009). No significant changes were found in the controls.

CONCLUSIONS

These findings encourage the use of thermal quantitative sensory testing in the oral cavity to assess thermal sensation, which might be useful for assessing the effects of therapies aimed at reducing pain.

Augmenting small biomedical datasets using generative AI methods based on self-organizing neural networks

Small sample sizes in biomedical research often led to poor reproducibility and challenges in translating findings into clinical applications. This problem stems from limited study resources, rare diseases, ethical considerations in animal studies, costly expert diagnosis, and others. As a contribution to the problem, we propose a novel generative algorithm based on self-organizing maps (SOMs) to computationally increase sample sizes. The proposed unsupervised generative algorithm uses neural networks to detect inherent structure even in small multivariate datasets, distinguishing between sparse "void" and dense "cloud" regions. Using emergent SOMs (ESOMs), the algorithm adapts to high-dimensional data structures and generates for each original data point k new points by randomly selecting positions within an adapted hypersphere with distances based on valid neighborhood probabilities. Experiments on artificial and biomedical (omics) datasets show that the generated data preserve the original structure without introducing artifacts. Random forests and support vector machines cannot distinguish between generated and original data, and the variables of original and generated data sets are not statistically different. The method successfully augments small group sizes, such as transcriptomics data from a rare form of leukemia and lipidomics data from arthritis research. The novel ESOM-based generative algorithm presents a promising solution for enhancing sample sizes in small or rare case datasets, even when limited training data are available. This approach can address challenges associated with small sample sizes in biomedical research, offering a tool for improving the reliability and robustness of scientific findings in this field. Availability: R library "Umatrix" (https://cran.r-project.org/package=Umatrix).

Drosophila pain sensitization and modulation unveiled by a novel pain model and analgesic drugs

In mammals, pain is regulated by the combination of an ascending stimulating and descending inhibitory pain pathway. It remains an intriguing question whether such pain pathways are of ancient origin and conserved in invertebrates. Here we report a new Drosophila pain model and use it to elucidate the pain pathways present in flies. The model employs transgenic flies expressing the human capsaicin receptor TRPV1 in sensory nociceptor neurons, which innervate the whole fly body, including the mouth. Upon capsaicin sipping, the flies abruptly displayed pain-related behaviors such as running away, scurrying around, rubbing vigorously, and pulling at their mouth parts, suggesting that capsaicin stimulated nociceptors in the mouth via activating TRPV1. When reared on capsaicin-containing food, the animals died of starvation, demonstrating the degree of pain experienced. This death rate was reduced by treatment both with NSAIDs and gabapentin, analgesics that inhibit the sensitized ascending pain pathway, and with antidepressants, GABAergic agonists, and morphine, analgesics that strengthen the descending inhibitory pathway. Our results suggest Drosophila to possess intricate pain sensitization and modulation mechanisms similar to mammals, and we propose that this simple, non-invasive feeding assay has utility for high-throughput evaluation and screening of analgesic compounds.

Preliminary Evidence for the Sequentially Mediated Effect of Racism-Related Stress on Pain Sensitivity Through Sleep Disturbance and Corticolimbic Opioid Receptor Function

Sleep disturbance predicts worse pain outcomes. Because sleep disturbance inequitably impacts Black adults - with racism as the upstream cause - understanding how racism-related stress impacts pain through sleep might help minimize racialized pain inequities. This preliminary study examined sequential mediation of the effect of racism-related stress on experimental pain through sleep disturbance and corticolimbic μOR function in pain-free non-Hispanic Black (NHB) and White (NHW) adults. Participants completed questionnaires, actigraphy, positron emission tomography, and sensory testing. We reproduced findings showing greater sleep disturbance and pain sensitivity among NHB participants; greater sleep disturbance (r = .35) and lower pain tolerance (r=-.37) were significantly associated with greater racism-related stress. In a sequential mediation model, the total effect of racism-related stress on pain tolerance (β=-.38, P = .005) weakened after adding sleep disturbance and ventromedial prefrontal cortex (vmPFC) μOR binding potential (BPND) as mediators (β = -.18, P = .16). The indirect effect was statistically significant [point estimate = -.003, (-.007, -.0003). Findings showed a potential sequentially mediated effect of racism-related stress on pain sensitivity through sleep disturbance and vmPFC μOR BPND. As policy efforts are enacted to eliminate the upstream cause of systemic racism, these results cautiously suggest that sleep interventions within racism-based trauma informed therapy might help prevent downstream effects on pain. PERSPECTIVE: This preliminary study identified the effect of racism-related stress on pain through sleep disturbance and mu-opioid receptor binding potential in the ventromedial prefrontal cortex. Findings cautiously support the application of sleep interventions within racism-based trauma-informed therapy to prevent pain inequities as policy changes function to eliminate all levels of racism.

A systematic review of porcine models in translational pain research

Translating basic pain research from rodents to humans has proven to be a challenging task. Efforts have been made to develop preclinical large animal models of pain, such as the pig. However, no consistent overview and comparison of pig models of pain are currently available. Therefore, in this review, our primary aim was to identify the available pig models in pain research and compare these models in terms of intensity and duration. First, we systematically searched Proquest, Scopus and Web of Science and compared the duration for which the pigs were significantly sensitized as well as the intensity of mechanical sensitization. We searched models within the specific field of pain and adjacent fields in which pain induction or assessment is relevant, such as pig production. Second, we compared assessment methodologies in surrogate pain models in humans and pigs to identify areas of overlap and possible improvement. Based on the literature search, 23 types of porcine pain models were identified; 13 of which could be compared quantitatively. The induced sensitization lasted from hours to months and intensities ranged from insignificant to the maximum attainable. We also found a near to complete overlap of assessment methodologies between human and pig models within the area of peripheral neurophysiology, which allows for direct comparison of results obtained in the two species. In spite of this overlap, further development of pain assessment methodologies is still needed. We suggest that central nervous system electrophysiology, such as electroencephalography, electrocorticography or intracortical recordings, may pave the way for future objective pain assessment.

Modality-specific facilitation of noninjurious sharp mechanical pain by topical capsaicin

We had previously shown that a "blunt blade" stimulator can mimic the noninjurious strain phase of incisional pain, but not its sustained duration. Here, we tested whether acute sensitization of the skin with topical capsaicin can add the sustained phase to this noninvasive surrogate model of intraoperative pain. Altogether, 110 healthy volunteers (55 male and 55 female; 26 ± 5 years) participated in several experiments using the "blunt blade" (0.25 × 4 mm) on normal skin (n = 36) and on skin pretreated by a high-concentration capsaicin patch (8%, Qutenza; n = 36). These data were compared with an experimental incision (n = 40) using quantitative and qualitative pain ratings by numerical rating scale and SES Pain Perception Scale descriptors. Capsaicin sensitization increased blade-induced pain magnitude and duration significantly (both P < 0.05), but it failed to fully match the sustained duration of incisional pain. In normal skin, the SES pattern of pain qualities elicited by the blade matched incision in pain magnitude and pattern of pain descriptors. In capsaicin-treated skin, the blade acquired a significant facilitation only of the perceived heat pain component (P < 0.001), but not of mechanical pain components. Thus, capsaicin morphed the descriptor pattern of the blade to become more capsaicin-like, which is probably explained best by peripheral sensitization of the TRPV1 receptor. Quantitative sensory testing in capsaicin-sensitized skin revealed hyperalgesia to heat and pressure stimuli, and loss of cold and cold pain sensitivity. These findings support our hypothesis that the blade models the early tissue-strain-related mechanical pain phase of surgical incisions.

Machine-learning-based knowledge discovery in rheumatoid arthritis-related registry data to identify predictors of persistent pain

Early detection of patients with chronic diseases at risk of developing persistent pain is clinically desirable for timely initiation of multimodal therapies. Quality follow-up registries may provide the necessary clinical data; however, their design is not focused on a specific research aim, which poses challenges on the data analysis strategy. Here, machine-learning was used to identify early parameters that provide information about a future development of persistent pain in rheumatoid arthritis (RA). Data of 288 patients were queried from a registry based on the Swedish Epidemiological Investigation of RA. Unsupervised data analyses identified the following 3 distinct patient subgroups: low-, median-, and high-persistent pain intensity. Next, supervised machine-learning, implemented as random forests followed by computed ABC analysis-based item categorization, was used to select predictive parameters among 21 different demographic, patient-rated, and objective clinical factors. The selected parameters were used to train machine-learned algorithms to assign patients pain-related subgroups (1000 random resamplings, 2/3 training, and 1/3 test data). Algorithms trained with 3-month data of the patient global assessment and health assessment questionnaire provided pain group assignment at a balanced accuracy of 70%. When restricting the predictors to objective clinical parameters of disease severity, swollen joint count and tender joint count acquired at 3 months provided a balanced accuracy of RA of 59%. Results indicate that machine-learning is suited to extract knowledge from data queried from pain- and disease-related registries. Early functional parameters of RA are informative for the development and degree of persistent pain.

Interpretation of cluster structures in pain-related phenotype data using explainable artificial intelligence (XAI)

BACKGROUND

In pain research and clinics, it is common practice to subgroup subjects according to shared pain characteristics. This is often achieved by computer-aided clustering. In response to a recent EU recommendation that computer-aided decision making should be transparent, we propose an approach that uses machine learning to provide (1) an understandable interpretation of a cluster structure to (2) enable a transparent decision process about why a person concerned is placed in a particular cluster.

METHODS

Comprehensibility was achieved by transforming the interpretation problem into a classification problem: A sub-symbolic algorithm was used to estimate the importance of each pain measure for cluster assignment, followed by an item categorization technique to select the relevant variables. Subsequently, a symbolic algorithm as explainable artificial intelligence (XAI) provided understandable rules of cluster assignment. The approach was tested using 100-fold cross-validation.

RESULTS

The importance of the variables of the data set (6 pain-related characteristics of 82 healthy subjects) changed with the clustering scenarios. The highest median accuracy was achieved by sub-symbolic classifiers. A generalized post-hoc interpretation of clustering strategies of the model led to a loss of median accuracy. XAI models were able to interpret the cluster structure almost as correctly, but with a slight loss of accuracy.

CONCLUSIONS

Assessing the variables importance in clustering is important for understanding any cluster structure. XAI models are able to provide a human-understandable interpretation of the cluster structure. Model selection must be adapted individually to the clustering problem. The advantage of comprehensibility comes at an expense of accuracy.

Machine-Learned Association of Next-Generation Sequencing-Derived Variants in Thermosensitive Ion Channels Genes with Human Thermal Pain Sensitivity Phenotypes

Genetic association studies have shown their usefulness in assessing the role of ion channels in human thermal pain perception. We used machine learning to construct a complex phenotype from pain thresholds to thermal stimuli and associate it with the genetic information derived from the next-generation sequencing (NGS) of 15 ion channel genes which are involved in thermal perception, including ASIC1, ASIC2, ASIC3, ASIC4, TRPA1, TRPC1, TRPM2, TRPM3, TRPM4, TRPM5, TRPM8, TRPV1, TRPV2, TRPV3, and TRPV4. Phenotypic information was complete in 82 subjects and NGS genotypes were available in 67 subjects. A network of artificial neurons, implemented as emergent self-organizing maps, discovered two clusters characterized by high or low pain thresholds for heat and cold pain. A total of 1071 variants were discovered in the 15 ion channel genes. After feature selection, 80 genetic variants were retained for an association analysis based on machine learning. The measured performance of machine learning-mediated phenotype assignment based on this genetic information resulted in an area under the receiver operating characteristic curve of 77.2%, justifying a phenotype classification based on the genetic information. A further item categorization finally resulted in 38 genetic variants that contributed most to the phenotype assignment. Most of them (10) belonged to the TRPV3 gene, followed by TRPM3 (6). Therefore, the analysis successfully identified the particular importance of TRPV3 and TRPM3 for an average pain phenotype defined by the sensitivity to moderate thermal stimuli.

[Generating knowledge from complex data sets in human experimental pain research]

Pain has a complex pathophysiology that is expressed in multifaceted and heterogeneous clinical phenotypes. This makes research on pain and its treatment a potentially data-rich field as large amounts of complex data are generated. Typical sources of such data are investigations with functional magnetic resonance imaging, complex quantitative sensory testing, next-generation DNA sequencing and functional genomic research approaches, such as those aimed at analgesic drug discovery or repositioning of drugs known from other indications as new analgesics. Extracting information from these big data requires complex data scientific-based methods belonging more to computer science than to statistics. A particular interest is currently focused on machine learning, the methods of which are used for the detection of interesting and biologically meaningful structures in high-dimensional data. Subsequently, classifiers can be created that predict clinical phenotypes from, e.g. clinical or genetic features acquired from subjects. In addition, knowledge discovery in big data accessible in electronic knowledge bases, can be used to generate hypotheses and to exploit the accumulated knowledge about pain for the discovery of new analgesic drugs. This enables so-called data-information-knowledge-wisdom (DIKW) approaches to be followed in pain research. This article highlights current examples from pain research to provide an overview about contemporary data scientific methods used in this field of research.

Machine-learned analysis of the association of next-generation sequencing-based human TRPV1 and TRPA1 genotypes with the sensitivity to heat stimuli and topically applied capsaicin

Heat pain and its modulation by capsaicin varies among subjects in experimental and clinical settings. A plausible cause is a genetic component, of which TRPV1 ion channels, by their response to both heat and capsaicin, are primary candidates. However, TRPA1 channels can heterodimerize with TRPV1 channels and carry genetic variants reported to modulate heat pain sensitivity. To address the role of these candidate genes in capsaicin-induced hypersensitization to heat, pain thresholds acquired before and after topical application of capsaicin and TRPA1/TRPV1 exomic sequences derived by next-generation sequencing were assessed in n = 75 healthy volunteers and the genetic information comprised 278 loci. Gaussian mixture modeling indicated 2 phenotype groups with high or low capsaicin-induced hypersensitization to heat. Unsupervised machine learning implemented as swarm-based clustering hinted at differences in the genetic pattern between these phenotype groups. Several methods of supervised machine learning implemented as random forests, adaptive boosting, k-nearest neighbors, naive Bayes, support vector machines, and for comparison, binary logistic regression predicted the phenotype group association consistently better when based on the observed genotypes than when using a random permutation of the exomic sequences. Of note, TRPA1 variants were more important for correct phenotype group association than TRPV1 variants. This indicates a role of the TRPA1 and TRPV1 next-generation sequencing-based genetic pattern in the modulation of the individual response to heat-related pain phenotypes. When considering earlier evidence that topical capsaicin can induce neuropathy-like quantitative sensory testing patterns in healthy subjects, implications for future analgesic treatments with transient receptor potential inhibitors arise.