Psychometric Evaluation of the Electronic Pain Assessment Tool: An Innovative Instrument for Individuals with Moderate-to-Severe Dementia

Artificial Intelligence-Driven Diagnostic Processes and Comprehensive Multimodal Models in Pain Medicine

Pain diagnosis remains a challenging task due to its subjective nature, the variability in pain expression among individuals, and the difficult assessment of the underlying biopsychosocial factors. In this complex scenario, artificial intelligence (AI) can offer the potential to enhance diagnostic accuracy, predict treatment outcomes, and personalize pain management strategies. This review aims to dissect the current literature on computer-aided diagnosis methods. It also discusses how AI-driven diagnostic strategies can be integrated into multimodal models that combine various data sources, such as facial expression analysis, neuroimaging, and physiological signals, with advanced AI techniques. Despite the significant advancements in AI technology, its widespread adoption in clinical settings faces crucial challenges. The main issues are ethical considerations related to patient privacy, biases, and the lack of reliability and generalizability. Furthermore, there is a need for high-quality real-world validation and the development of standardized protocols and policies to guide the implementation of these technologies in diverse clinical settings.

Behaviours and psychological symptoms of childhood dementia: two cases of psychosocial interventions

Childhood dementias are a group of rare, fatal neurodegenerative disorders, characterised by global cognitive decline, loss of previously acquired developmental skills and behaviours and psychological symptoms of dementia (BPSD). Batten disease, or neuronal ceroid lipofuscinosis, and Sanfilippo syndrome, or mucopolysaccharidosis type III, are two of the more common forms of childhood dementia disorders worldwide. While psychosocial interventions are the best available therapeutic approach for BPSD management in adult-onset dementia, there is very limited literature or clinical experience in the context of childhood dementia. To address this gap, we conducted a descriptive case analysis of BPSD profiles, associated contributing factors and targeted psychosocial interventions in two cases with childhood dementia disorders (Sanfilippo syndrome and CLN3 (juvenile onset) Batten disease) who were referred to Dementia Support Australia, a national dementia behaviour support service in Australia. Primary BPSD identified in these disorders included physical and verbal aggression and irritability/lability. In these cases, contributing factors to the development of BPSD were not monolithic, encompassing pain, caregiver's approach and over or under-stimulation. Improvement in BPSD were observed using the Neuropsychiatric Inventory-Quesionnaire and globally noted as per the qualitative feedback reported by family and caregivers. Person-centred, multimodal psychosocial interventions were recognised as effective therapies in resolving BPSD in these cases. In conclusion, the case studies described the nature and presentation of BPSD in two common forms of childhood dementia and demonstrated the potential benefits of person-centred psychosocial interventions (delivered through national dementia-specific support programs) in alleviating BPSD such as irritability and aggression in these disorders.

Pain prevalence, intensity, and association with neuropsychiatric symptoms of dementia in immigrant and non-immigrant aged care residents in Australia

Pain recognition for culturally diverse people is complex as pain experience is subjective and influenced by cultural background. We compared the prevalence, intensity, and association of pain with neuropsychiatric symptoms (NPS) between immigrants and non-immigrants living with dementia in residential aged care homes (RACHs) who were referred to two Dementia Support Australia programs. Immigrant status was defined by the documented country of birth. Pain and NPS were assessed using PainChek® and the Neuropsychiatric Inventory, respectively. Subgroup analyses were also completed for English-speaking and non-English-speaking immigrants. A total of 17,637 referrals [immigrants, n = 6340; non-immigrants, n = 11,297] from 2792 RACHs were included. There were no significant differences for the prevalence of pain across all groups. Immigrants were slightly more likely to have moderate pain or severe pain than non-immigrants. Non-English-speaking immigrants had 0.5 points higher total pain scores on average (Cohen's d = 0.10 [0.05, 0.15], p < 0.001) than non-immigrants. Total pain score had a significant effect on total NPS severity scores in all groups. While pain prevalence is similar across groups, higher pain intensities are more common among immigrants living with dementia. Increased care staff awareness, education, and training about the potential effect of culture on pain expression is needed.

Association between pain and cognitive and daily functional impairment in older institutional residents: a cross-sectional study

BACKGROUND

Pain is often neglected in disabled older population, especially in Taiwan where the population of institutional residents is rapidly growing. Our study aimed to investigate pain prevalence and associated factors among institutional residents to improve pain assessment and management.

METHODS

This nationwide study recruited 5,746 institutional residents in Taiwan between July 2019 and February 2020. Patient self-report was considered the most valid and reliable indicator of pain. A 5-point verbal rating scale was used to measure pain intensity, with a score ranging from 2 to 5 indicating the presence of pain. Associated factors with pain, including comorbidities, functional dependence, and quality of life, were also assessed.

RESULTS

The mean age of the residents was 77.1 ± 13.4 years, with 63.1% of them aged over 75 years. Overall, 40.3% of the residents reported pain, of whom 51.2% had moderate to severe pain. Pain was more common in residents with comorbidities and significantly impacted emotions and behavior problems, and the mean EQ5D score, which is a measure of health-related quality of life (p < .001). Interestingly, pain was only related to instrumental activities of daily living (IADL) and not activities of daily living (ADL). On the other hand, dementia was significantly negatively associated with pain (p < .001), with an estimated odds of 0.63 times (95% CI: 0.53-0.75) for the presence of pain when compared to residents who did not have dementia.

CONCLUSIONS

Unmanaged pain is common among institutional residents and is associated with comorbidities, IADL, emotional/behavioral problems, and health-related quality of life. Older residents may have lower odds of reporting pain due to difficulty communicating their pain, even through the use of a simple 5-point verbal rating scale. Therefore, more attention and effort should be directed towards improving pain evaluation in this vulnerable population .

Comparing clinico-demographics and neuropsychiatric symptoms for immigrant and non-immigrant aged care residents living with dementia: a retrospective cross-sectional study from an Australian dementia-specific support service

BACKGROUND

Neuropsychiatric symptoms of dementia such as agitation and aggression are common in people living with dementia. The presentation of neuropsychiatric symptoms is influenced by the cultural background of people living with dementia. Further, identifying factors contributing to neuropsychiatric symptoms may be complicated if people living with dementia are immigrants or from non-English-speaking backgrounds. Most of what is known about differences in neuropsychiatric symptoms between racial and ethnic groups living with dementia come from community-based samples. This study investigated differences in clinico-demographics and neuropsychiatric symptoms between immigrants and non-immigrants living with dementia in residential aged care homes who were referred to two Dementia Support Australia programs.

METHODS

This was a retrospective observational cross-sectional study from 2018 to 2022 using data extracted from the Dementia Support Australia database. Immigrant status was identified by documented country of birth. We conducted exploratory subgroup analyses for English-speaking or non-English-speaking immigrants in comparison to non-immigrants. Neuropsychiatric Inventory and PainChek® were used to assess neuropsychiatric symptoms of dementia and pain, respectively.

RESULTS

Of the 23,889 referrals, 36% were immigrants living with dementia. Immigrants were 0.8 years older than non-immigrants on average. Immigrants had a slightly higher prevalence of mixed dementia (9.5%) than non-immigrants (8.2%). Overall, the groups had no difference in the severity of neuropsychiatric symptoms and associated caregiver distress. However, there was a significant difference in the total number of neuropsychiatric inventory domains (Cohen's d = -0.06 [-0.09, - 0.02], p <.001) between non-English-speaking immigrants and non-immigrants. Immigrants were more likely to present with agitation/aggression, while non-immigrants were more likely to present with hallucinations. Factors contributing to neuropsychiatric symptoms were common between the groups, with language barriers and cultural considerations frequently endorsed for immigrants.

CONCLUSION

This study reveals a mixed picture of neuropsychiatric symptoms between immigrants and non-immigrants. However, due to the exploratory nature of the hypotheses, our findings need to be replicated in future studies to confirm any conclusions. There is a need for increased awareness on the impact of culture and language on neuropsychiatric symptoms for people receiving residential care. Future studies investigating neuropsychiatric symptoms in different immigrant groups will help increase our understanding of neuropsychiatric symptoms for all people.

Technology-guided assessment of vocalisations and their diagnostic value as pain indicators for people living with dementia

BACKGROUND

during pain assessment in persons unable to self-report, such as people living with dementia, vocalisations are commonly used as pain indicators. However, there is a lack of evidence from clinical practice regarding their diagnostic value and relationship with pain. We aimed to explore vocalisations and pain in people with dementia undergoing pain assessments in clinical practice settings.

METHODS

a total of 22,194 pain assessments were reviewed in people with dementia (n = 3,144) from 34 different Australian aged care homes and two dementia specific programs. Pain assessments were conducted by 389 purposely trained health care professionals and cares using PainChek pain assessment tool. Vocalised expressions were determined based on nine vocalisation features included in the tool. Linear mixed models were used to examine the relationship of pain scores with vocalisation features. Using a single pain assessment for each of the 3,144 people with dementia, additional data analysis was conducted via Receiver Operator Characteristic (ROC) analysis and Principal Component Analysis.

RESULTS

vocalisation scores increased with increasing pain intensity. High pain scores were more likely with the presence of sighing and screaming (8 times). The presence of vocalisation features varied depending on the intensity of pain. The ROC optimal criterion for the voice domain yielded a cut-off score of ≥2.0 with a Youden index of 0.637. The corresponding sensitivity and specificity were 79.7% [confidence interval (CI): 76.8-82.4%] and 84.0% (CI: 82.5-85.5%), respectively.

CONCLUSION

we describe vocalisation features during presence of different levels of pain in people with dementia unable to self-report, therefore providing evidence in regard to their diagnostic value in clinical practice.

Assessing pain using facial recognition software among Aboriginal aged care residents with cognitive impairment: A retrospective cohort study

OBJECTIVE

To assess the observed pain behaviours of Aboriginal residents with cognitive impairment in aged care facilities and compare these results with a matched national sample of non-Aboriginal residents.

METHODS

Observed pain behaviours of Aboriginal residents (N = 87) with cognitive impairment in aged care facilities across the Northern Territory of Australia were assessed using PainChek® Adult and compared with data from a matched national sample of non-Aboriginal residents (N = 420). Pain scores were derived from inbuilt automated facial recognition and analysis software plus a series of digital checklists requiring manual input by care staff.

RESULTS

The median total pain score for the Aboriginal residents was 2 (IQR 1-4) and for the matched external residents was 3 (IQR 2-5). In a multivariable negative binomial regression model, this difference in total pain score was statistically significant (p < 0.001). The pain score derived from the automated facial recognition and analysis component of the PainChek® Adult app was not statistically different between the two groups when adjusted for multiple observations and context of observation (odds ratio = 1.06, 95% confidence interval 0.97-1.16, p = 0.169).

CONCLUSIONS

We found under-reporting of observed pain signs and behaviours for Aboriginal aged care residents by assessors. Further training in the assessment of pain in Aboriginal and Torres Strait Islander aged care residents may be necessary and a continuing shift in clinical practice to using technology and point-of-care assessment.

Clinico-demographics of people with younger-onset dementia and neuropsychiatric symptoms referred to an Australian dementia support service: A comparison study with older-onset dementia

OBJECTIVE

Younger-onset dementia accounts for about 5-10% of all dementias in Australia. Little data is available on neuropsychiatric symptoms in people with younger-onset dementia compared to those with older-onset dementia. This study aims to compare the types of neuropsychiatric symptoms and their clinico-demographic characteristics of people with younger-onset dementia and older-onset dementia who are referred to a specific dementia support service.

METHODS

A 2-year retrospective observational cross-sectional analysis was undertaken on referrals with neuropsychiatric symptoms from Dementia Support Australia programmes. Neuropsychiatric symptoms were measured using the Neuropsychiatric Inventory total severity scores and distress scores. Contributing factors to neuropsychiatric symptoms for dementia groups were examined. Logistic regression was used to examine the relationship between individual neuropsychiatric symptoms and having older-onset dementia vs younger-onset dementia.

RESULTS

Of the 15,952 referrals, about 5% (n = 729, mean age: 60.7 years, standard deviation = 5.4) were individuals with younger-onset dementia. Referrals with older-onset dementia were more likely to be female (56%), whereas referrals with younger-onset dementia were more likely to be male (54%). There was a four times greater rate of frontotemporal dementia for those with younger-onset dementia (16.0%, n = 117) compared to those with older-onset dementia (2.8%, n = 427), χ² (1) = 366.2, p < 0.001. Referrals with younger-onset dementia were more likely to be referred from community settings and those with older-onset dementia were more likely to be from residential aged care. Overall, there was no difference in the severity and distress of neuropsychiatric symptoms between the two groups. Contributing factors to neuropsychiatric symptoms were different between the groups, with pain being more frequently endorsed for individuals with older-onset dementia whereas communication difficulties were more commonly identified for those with younger-onset dementia.

CONCLUSION

Clinico-demographics of referrals with younger-onset dementia differ from those with older-onset dementia. There were some differences in the characteristics of neuropsychiatric symptoms between younger-onset dementia and older-onset dementia. Our findings have implications for service provision and support for people with dementia at different ages.

The influence of Alzheimer's disease stigma on pain assessment in older persons

INTRODUCTION

Pain of nursing homes residents with Alzheimer's disease remains under detected compared to their cognitively intact counterparts. Communication difficulties may partly explain this poor quality of care but the influence of stigmatization on pain assessment has never been explored.

RESEARCH QUESTION

The objective of this research was to analyze whether a diagnosis label of Alzheimer's disease or the stage of the disease may bias pain assessment scores and empathic reactions of health care staff in nursing homes.

METHODS

Two studies were conducted based on a similar experimental between-subjects design with a video showing an older adult woman experiencing undefined pain. Different labels and vignettes were manipulated to characterize the subject of the video. In the first study, 84 certified nursing assistants were asked to watch the video and then to assess the pain intensity and their empathic reaction. Participants were randomized in two conditions that varied the disease label (Alzheimer's disease vs no diagnosis). In the second study, 67 certified nursing assistants were enrolled who did not participate in the first study. They watched the same video as in the first study and assessed the pain intensity and their empathic reaction. They were randomized in two conditions that varied the stage of the Alzheimer's disease (mild stage vs severe stage).

RESULTS

Alzheimer's disease label had no influence on assessment scores. In contrast, the stage of the disease had a significant effect on the health care staff assessments with severe stage associated with lower pain intensity scores and empathic reactions.

CONCLUSION

These results confirm that the Alzheimer's disease stigma is a real phenomenon that tends to be mainly elicited by the symptoms of the acute phase of the disease. These findings are crucial to better understand the stigma related to Alzheimer's disease and to enhance the pain management of this frail population.

Effectiveness of nurse-led volunteer support and technology-driven pain assessment in improving the outcomes of hospitalised older adults: protocol for a cluster randomised controlled trial

INTRODUCTION

Hospitalised older adults are prone to functional deterioration, which is more evident in frail older patients and can be further exacerbated by pain. Two interventions that have the potential to prevent progression of frailty and improve patient outcomes in hospitalised older adults but have yet to be subject to clinical trials are nurse-led volunteer support and technology-driven assessment of pain.

METHODS AND ANALYSIS

This single-centre, prospective, non-blinded, cluster randomised controlled trial will compare the efficacy of nurse-led volunteer support, technology-driven pain assessment and the combination of the two interventions to usual care for hospitalised older adults. Prior to commencing recruitment, the intervention and control conditions will be randomised across four wards. Recruitment will continue for 12 months. Data will be collected on admission, at discharge and at 30 days post discharge, with additional data collected during hospitalisation comprising records of pain assessment and volunteer support activity. The primary outcome of this study will be the change in frailty between both admission and discharge, and admission and 30 days, and secondary outcomes include length of stay, adverse events, discharge destination, quality of life, depression, cognitive function, functional independence, pain scores, pain management intervention (type and frequency) and unplanned 30-day readmissions. Stakeholder evaluation and an economic analysis of the interventions will also be conducted.

ETHICS AND DISSEMINATION

Ethical approval has been granted by Human Research Ethics Committees at Ramsay Health Care WA|SA (number: 2057) and Edith Cowan University (number: 2021-02210-SAUNDERS). The findings will be disseminated through conference presentations, peer-reviewed publications and social media.

TRIAL REGISTRATION NUMBER

ACTRN12620001173987.

Faces of Pain in Dementia: Learnings From a Real-World Study Using a Technology-Enabled Pain Assessment Tool

Pain is common in people living with dementia (PLWD), including those with limited verbal skills. Facial expressions are key behavioral indicators of the pain experience in this group. However, there is a lack of real-world studies to report the prevalence and associations of pain-relevant facial micro-expressions in PLWD. In this observational retrospective study, pain-related facial features were studied in a sample of 3,144 PLWD [mean age 83.3 years (SD = 9.0); 59.0% female] using the Face domain of PainChek®, a point-of-care medical device application. Pain assessments were completed by 389 users from two national dementia-specific care programs and 34 Australian aged care homes. Our analysis focused on the frequency, distribution, and associations of facial action units [AU(s)] with respect to various pain intensity groups. A total of 22,194 pain assessments were completed. Of the AUs present, AU7 (eyelid tightening) was the most frequent facial expression (48.6%) detected, followed by AU43 (closing eyes; 42.9%) and AU6 (cheek raising; 42.1%) during severe pain. AU20 (horizontal mouth stretch) was the most predictive facial action of higher pain scores. Eye-related AUs (AU6, AU7, AU43) and brow-related AUs (AU4) were more common than mouth-related AUs (e.g., AU20, AU25) during higher pain intensities. No significant effect was found for age or gender. These findings offer further understanding of facial expressions during clinical pain in PLWD and confirm the usefulness of artificial intelligence (AI)-enabled real-time analysis of the face as part of the assessment of pain in aged care clinical practice.

Pain in Dementia: Prevalence and Association With Neuropsychiatric Behaviors

CONTEXT

Pain is linked to behaviors and psychological symptoms of dementia (BPSD); however, it often remains underrecognized in this population.

OBJECTIVES

We aimed to investigate the prevalence and intensity of pain in people living in aged care homes with BPSD and by dementia subtypes and the association between pain intensity and BPSD.

METHODS

A 1-year retrospective cross-sectional analysis was conducted on BPSD and the presence of pain in referrals to a national BPSD support service using the Neuropsychiatric Inventory and PainChek®, respectively. Referrals were categorized into two groups: pain group and no pain group.

RESULTS

Of the 479 referrals (81.9 ± 8.3 years old) included in the analysis, two-thirds (65.6%) had pain identified, with almost half (48.4%) of these categorized as experiencing moderate-severe pain. Pain was highly prevalent (range: 54.6-78.6%) in all subtypes of dementia, particularly in mixed dementia and dementia with Lewy bodies. Compared with the no pain group, the pain group had 25.3% more neuropsychiatric behaviors, 33.6% higher total severity of these behaviors, and 31.4% higher total distress caused to caregivers. For all results, effect sizes were small to medium (η²p = 0.04-0.06). Despite a high prevalence of aggressive or agitated behaviors across the entire group, the pain group was 3.8 times more likely to experience these behaviors than referrals not in pain.

CONCLUSION

There is a strong need to consider the possibility of pain as a contributor to behavioral changes in aged care residents living with dementia.

Evaluation of the Psychometric Properties of PainChek® in UK Aged Care Residents with advanced dementia

BACKGROUND

The aim of this study was to further validate PainChek®, an electronic pain assessment instrument, with a population living with dementia in a UK care home.

METHOD

This study utilised a correlational design to evaluate the psychometric properties of PainChek® when compared to the Abbey Pain Scale (APS). Blinded paired pain assessments were completed at rest and immediately post-movement by a researcher and a nurse. A total of 22 participants with a diagnosis of moderate-to-severe dementia and a painful condition were recruited using opportunity sampling.

RESULTS

Overall, 302 paired assessments were collected for 22 participants. Out of these 179 were conducted during rest and 123 were immediately post-movement. The results demonstrated a positive significant correlation between overall PainChek® pain scores and overall APS pain scores (r = 0.818, N = 302, p < .001, one-tailed), satisfactory internal consistency (α = 0.810), moderate single measure intraclass correlation (ICC = 0.680) and substantial inter-rater agreement (κ = 0.719).

CONCLUSIONS

PainChek® has demonstrated to be a valid and reliable instrument to assess the presence and severity of pain in people with moderate-to-severe dementia living in aged care.

Prevalence of frailty and pain in hospitalised adult patients in an acute hospital: a protocol for a point prevalence observational study

INTRODUCTION

Frailty and pain are associated with adverse patient clinical outcomes and healthcare system costs. Frailty and pain can interact, such that symptoms of frailty can make pain assessment difficult and pain can exacerbate the progression of frailty. The prevalence of frailty and pain and their concurrence in hospital settings are not well understood, and patients with cognitive impairment are often excluded from pain prevalence studies due to difficulties assessing their pain. The aim of this study is to determine the prevalence of frailty and pain in adult inpatients, including those with cognitive impairment, in an acute care private metropolitan hospital in Western Australia.

METHODS AND ANALYSIS

A prospective, observational, single-day point prevalence, cross-sectional study of frailty and pain intensity of all inpatients (excluding day surgery and critical care units) will be undertaken. Frailty will be assessed using the modified Reported Edmonton Frail Scale. Current pain intensity will be assessed using the PainChek smart-device application enabling pain assessment in people unable to report pain due to cognitive impairment. Participants will also provide a numerical rating of the intensity of current pain and the worst pain experienced in the previous 24 hours. Demographic and clinical information will be collected from patient files. The overall response rate of the survey will be reported, as well as the percentage prevalence of frailty and of pain in the sample (separately for PainChek scores and numerical ratings). Additional statistical modelling will be conducted comparing frailty scores with pain scores, adjusting for covariates including age, gender, ward type and reason for admission.

ETHICS AND DISSEMINATION

Ethical approval has been granted by Ramsay Health Care Human Research Ethics Committee WA/SA (reference: 2038) and Edith Cowan University Human Research Ethics Committee (reference: 2020-02008-SAUNDERS). Findings will be widely disseminated through conference presentations, peer-reviewed publications and social media.

TRIAL REGISTRATION NUMBER

ACTRN12620000904976.

A novel pain assessment tool incorporating automated facial analysis: interrater reliability in advanced dementia

OBJECTIVES

Regardless of its severity, dementia does not negate the experience of pain. Rather, dementia hinders self-reporting mechanisms in affected individuals because they lose the ability to do so. The primary aim of this study was to examine the interrater reliability of the electronic Pain Assessment Tool (ePAT) among raters when assessing pain in residents with moderate-to-severe dementia. Secondly, it sought to examine the relationship between total instrument scores and facial scores, as determined by automated facial expression analysis.

STUDY DESIGN

A 2-week observational study.

SETTING

An accredited, high-care, and dementia-specific residential aged care facility in Perth, Western Australia.

PARTICIPANTS

Subjects were 10 residents (age range: 63.1-84.4 years old) predominantly with severe dementia (Dementia Severity Rating Scale score: 46.3±8.4) rated for pain by 11 aged care staff. Raters (female: 82%; mean age: 44.1±12.6 years) consisted of one clinical nurse, four registered nurses, five enrolled nurses, and one care worker.

MEASUREMENTS

ePAT measured pain using automated detection of facial action codes and recordings of pain behaviors.

RESULTS

A total of 76 assessments (rest =38 [n=19 pairs], movement =38 [n=19 pairs]) were conducted. At rest, raters' agreement was excellent on overall total scores (coefficient of concordance =0.92 [95% CI: 0.85-0.96]) and broad category scores (κ=1.0). Agreement was moderate (κ=0.59) on categorical scores upon movement, while it was exact in 68.4% of the cases. Agreement in actual pain category scores gave κw=0.72 (95% CI: 0.58-0.86) at rest and κw=0.69 (95% CI: 0.50-0.87) with movement. All raters scored residents with higher total scores post-mobilization compared to rest. More facial action unit codes were also detected during pain (mean: 2.5 vs 1.9; p<0.0012) and following mobilization (mean: 2.5 vs 1.7; p<0.0001) compared to no pain and rest, respectively.

CONCLUSIONS

ePAT, which combines automated facial expression analysis and clinical behavioral indicators in a single observational pain assessment tool, demonstrates good reliability properties, which supports its appropriateness for use in residents with advanced dementia.

A Technical Note on the PainChek™ System: A Web Portal and Mobile Medical Device for Assessing Pain in People With Dementia

Background: Pain in dementia is predominant particularly in the advanced stages or in those who are unable to verbalize. Uncontrolled pain alters the course of behaviors in patients with dementia making them perturbed, unsettled, and devitalized. Current measures of assessing pain in this population group are inadequate and underutilized in clinical practice because they lack systematic evaluation and innovative design.

Objective: To describe a novel method and system of pain assessment using a combination of technologies: automated facial recognition and analysis (AFRA), smart computing, affective computing, and cloud computing (Internet of Things) for people with advanced dementia.

Methods and Results: Cognification and affective computing were used to conceptualize the system. A computerized clinical system was developed to address the challenging problem of identifying pain in non-verbal patients with dementia. The system is composed of a smart device enabled app (App) linked to a web admin portal (WAP). The App “PainChek™” uses AFRA to identify facial action units indicative of pain presence, and user-fed clinical information to calculate a pain intensity score. The App has various functionalities including: pain assessment, pain monitoring, patient profiling, and data synchronization (into the WAP). The WAP serves as a database that collects the data obtained through the App in the clinical setting. These technologies can assist in addressing the various characteristics of pain (e.g., subjectivity, multidimensionality, and dynamicity). With over 750 paired assessments conducted, the App has been validated in two clinical studies (n = 74, age: 60–98 y), which showed sound psychometric properties: excellent concurrent validity (r = 0.882–0.911), interrater reliability (Kw = 0.74–0.86), internal consistency (α = 0.925–0.950), and excellent test-retest reliability (ICC = 0.904), while it possesses good predictive validity and discriminant validity. Clinimetric data revealed high accuracy (95.0%), sensitivity (96.1%), and specificity (91.4%) as well as excellent clinical utility (0.95).

Conclusions: PainChek™ is a comprehensive and evidence-based pain management system. This novel approach has the potential to transform pain assessment in people who are unable to verbalize because it can be used by clinicians and carers in everyday clinical practice.

Clinimetric properties of the electronic Pain Assessment Tool (ePAT) for aged-care residents with moderate to severe dementia

Purpose

Accurate pain assessment is critical to detect pain and facilitate effective pain management in dementia patients. The electronic Pain Assessment Tool (ePAT) is a point-of-care solution that uses automated facial analysis in conjunction with other clinical indicators to evaluate the presence and intensity of pain in patients with dementia. This study aimed to examine clini-metric properties (clinical utility and predictive validity) of the ePAT in this population group.

Methods

Data were extracted from a prospective validation (observational) study of the ePAT in dementia patients who were ≥65 years of age, living in a facility for ≥3 months, and had Psychogeriatric Assessment Scales - cognitive scores ≥10. The study was conducted in two residential aged-care facilities in Perth, Western Australia, where residents were sampled using purposive convenience strategy. Predictive validity was measured using accuracy statistics (sensitivity, specificity, positive predictive value, and negative predictive value). Positive and negative clinical utility index (CUI) scores were calculated using Mitchell's formula. Calculations were based on comparison with the Abbey Pain Scale, which was used as a criterion reference.

Results

A total of 400 paired pain assessments for 34 residents (mean age 85.5±6.3 years, range 68.0-93.2 years) with moderate-severe dementia (Psychogeriatric Assessment Scales - cognitive score 11-21) were included in the analysis. Of those, 303 episodes were classified as pain by the ePAT based on a cutoff score of 7. Unadjusted prevalence findings were sensitivity 96.1% (95% CI 93.9%-98.3%), specificity 91.4% (95% CI 85.7%-97.1%), accuracy 95.0% (95% CI 92.9%-97.1%), positive predictive value 97.4% (95% CI 95.6%-99.2%), negative predictive value 87.6% (95% CI 81.1%-94.2%), CUI⁺ 0.936 (95% CI 0.911-0.960), CUI^- 0.801 (95% CI 0.748-0.854).

Conclusion

The clinimetric properties demonstrated were excellent, thus supporting the clinical usefulness of the ePAT when identifying pain in patients with moderate-severe dementia.