Correlation between Biomarkers of Pain in Saliva and PAINAD Scale in Elderly People with Cognitive Impairment and Inability to Communicate

Automated facial recognition system using deep learning for pain assessment in adults with cerebral palsy

Objective

Assessing pain in individuals with neurological conditions like cerebral palsy is challenging due to limited self-reporting and expression abilities. Current methods lack sensitivity and specificity, underlining the need for a reliable evaluation protocol. An automated facial recognition system could revolutionize pain assessment for such patients.The research focuses on two primary goals: developing a dataset of facial pain expressions for individuals with cerebral palsy and creating a deep learning-based automated system for pain assessment tailored to this group.

Methods

The study trained ten neural networks using three pain image databases and a newly curated CP-PAIN Dataset of 109 images from cerebral palsy patients, classified by experts using the Facial Action Coding System.

Results

The InceptionV3 model demonstrated promising results, achieving 62.67% accuracy and a 61.12% F1 score on the CP-PAIN dataset. Explainable AI techniques confirmed the consistency of crucial features for pain identification across models.

Conclusion

The study underscores the potential of deep learning in developing reliable pain detection systems using facial recognition for individuals with communication impairments due to neurological conditions. A more extensive and diverse dataset could further enhance the models' sensitivity to subtle pain expressions in cerebral palsy patients and possibly extend to other complex neurological disorders. This research marks a significant step toward more empathetic and accurate pain management for vulnerable populations.

Determination of soluble tumor necrosis factor receptor II and secretory immunoglobulin A in saliva of patients with dementia

The prevalence of pain and dementia increases with age, affecting a significant percentage of the population due to aging. Both pathologies are connected through the inflammatory process, specifically through the tumor necrosis factor. The effect of this cytokine is mediated through the modulation of its TNFRI and TNFRII receptors, which are linked to the dementia process. In addition, immunoglobulins such as secretory immunoglobulin A (sIgA) have been recognized as one of the main biomarkers of pain in saliva. sTNFRII and sIgA levels were determined in saliva samples by ELISA from healthy people and patients with dementia in GDS stages 5-7. The concentrations of these markers were also correlated with the GDS stage and sex. We observed a significant decrease (*** p ≤ 0.001) in the levels of sTNFRII (pg/mL) and a significant increase (** p ≤ 0.01) in the levels of sIgA (ng/mL) in the saliva of patients with dementia compared to the healthy control group. We did not observe a correlation with the data of the biomarkers regarding the GDS stage and sex. The results obtained for sTNFRII are consistent with those obtained by other authors on brain tissue, who conclude that unopposed neuronal TNFRI signaling, when TNFRII is selectively downregulated, leads to a more severe course of AD pathogenesis. Regarding sIgA, the elevated values of sIgA may reflect the immune status of these patients. Therefore, these biomarkers can provide us with relevant information through a non-invasive method such as saliva analysis.

Non-Invasive Objective Markers to Measure Pain: A Direction to Develop a Pain Device - A Narrative Review

Objective

To review the literature regarding non-invasive objective measurements of pain. Measuring pain is of uttermost importance, but it can be an inconvenient task, especially in terms of the interpretation of patient's information. Reiterating, there is no "standard" that provides the physician with a method to objectively quantify this problem of patient's pain. For assessing the pain, physician relies solely on unidimensional assessment tools or questionnaire-based pain assessment. Although pain is a subjective experience of the patient, but there is a need to measure pain sometimes in the individuals who cannot communicate their quality and severity of pain.

Material and Methods

The articles from PubMed and Google Scholar without any year and age limit were searched in the current narrative review. A total of 16 markers were searched and their relation to pain was studied.

Results

Studies have shown that these markers change in relation to pain and it can be considered a valuable tool for pain measurement but there are multiple factors like psychological and emotional factors which affect these markers.

Conclusion

There is lack of evidence to show which marker can be used for measuring pain accurately. This narrative review is an attempt to look into the various pain-related markers that can be used and it calls for further studies including clinical trials with different diseases and taking into accounts different factors affecting pain to give an accurate measurement of pain.

Psychometric properties of pain measurements for people living with dementia: a COSMIN systematic review

PURPOSE

Detecting pain in older people with dementia is challenging. Consequentially, pain is often under-reported and under-treated. There remains uncertainty over what measures should be promoted for use to assess pain in this population. The purpose of this paper is to answer this question.

METHODS

A search of clinical trials registered on the ClinicalTrial.gov and ISRCTN registries was performed to identify outcome measures used to assess pain in people with dementia. Following this, a systematic review of published and unpublished databases was performed to 01 November 2021 to identify papers assessing the psychometric properties of these identified measures. Each paper and measure was assessed against the COSMIN checklist. A best evidence synthesis analysis was performed to assess the level of evidence for each measure.

RESULTS

From 188 clinical trials, nine outcome measures were identified. These included: Abbey Pain Scale, ALGOPLUS, DOLOPLUS-2, Facial Action Coding System, MOBID-2, self-reported pain through the NRS or VAS/thermometer or Philadelphia Geriatric Pain Intensity Scale, PACSLAC/PACSLAC-2, Pain Assessment in Advanced Dementia (PAINAD), and Checklist for non-verbal pain behavior (CNPI). From these, 51 papers (5924 people with dementia) were identified assessing the psychometric properties of these measures. From these, there was strong- and moderate-level evidence to support the use of the facial action coding system, PACSLAC and PACSLAC-II, CNPI, DOLOPLUS-2, ALGOPLUS, MOBID, and MOBID-2 tools for the assessment of pain with people living with dementia.

CONCLUSION

Whilst these reflect measurement tools used in research, further consideration on how these reflect clinical practice should be considered.

PROSPERO REGISTRATION

CRD42021282032.