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

Abstract

ObjectivesRegardless 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 designA 2-week observational study.SettingAn accredited, high-care, and dementia-specific residential aged care facility in Perth, Western Australia.ParticipantsSubjects 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.MeasurementsePAT measured pain using automated detection of facial action codes and recordings of pain behaviors.ResultsA 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.ConclusionsePAT, 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.

Pain in Dementia: Prevalence and Association With Neuropsychiatric Behaviors

“…A strength of this study is that the DSA service used the PainChek® device, a dementia-specific multidomain pain assessment tool (with strong psychometrics) that combines various technologies such as AI and smart automation. (36,71,72) Although there is an J o u r n a l P r e -p r o o f overlap between pain behaviours and BPSD, the device is unique in that it has a pain scale which includes items with clear operational definitions circumventing any ambiguity associated with interpretation during assessments. (72) Despite that, we cannot rule out completely that some neuropsychiatric symptoms (e.g.…”

“…(36,71,72) Although there is an J o u r n a l P r e -p r o o f overlap between pain behaviours and BPSD, the device is unique in that it has a pain scale which includes items with clear operational definitions circumventing any ambiguity associated with interpretation during assessments. (72) Despite that, we cannot rule out completely that some neuropsychiatric symptoms (e.g. agitation) were misinterpreted as pain behaviours.…”

“…dental infections, urinary tract infections, or previously documented chronic conditions in medical history e.g. arthritis (72). p values in bold font are statistically significant.…”

Moving beyond categorization to understand affective influences on real world health decisions

“…Greater understanding of complex affective states is important for the translation of affective sciences to real-world contexts and interventions. Although this difficult task is beyond the scope of this paper, key areas requiring greater research include identifying individual-and situation-level factors that influence the extent to which different types Novel induction approaches might involve concurrently activating different types of affective influences and leveraging emerging methods and technologies to model affect the way it is experienced in the real world, such as multiphase optimization strategy (Collins, Murphy, & Strecher, 2007), ecological momentary assessment, (Shiffman, Stone, & Hufford, 2008) implicit measures (Payne, Cheng, Govorun, & Stewart, 2005), and nonverbal assessments of emotions and arousal (Atee, Hoti, Parsons, & Hughes, 2018;Herr, Bjoro, & Decker, 2006;. New induction approaches might also involve inductions of blended affective states (rather than concurrently activated categories of affective states) and more precise measurement of such affective states.…”

“…Novel induction approaches might involve concurrently activating different types of affective influences and leveraging emerging methods and technologies to model affect the way it is experienced in the real world, such as multiphase optimization strategy (Collins, Murphy, & Strecher, ), ecological momentary assessment, (Shiffman, Stone, & Hufford, ) implicit measures (Payne, Cheng, Govorun, & Stewart, ), and nonverbal assessments of emotions and arousal (Atee, Hoti, Parsons, & Hughes, ; Herr, Bjoro, & Decker, ; Xu et al, ). New induction approaches might also involve inductions of blended affective states (rather than concurrently activated categories of affective states) and more precise measurement of such affective states.…”