RESEARCH

HOME RESEARCH
Health Analytics
Predictive Model
Facial expression differences indicate pain improvement at the emergency department
Abstract
Purpose: Pain is a major symptom for patients to seek medical services, but limited evidence supports the applicability and usage of facial expressions as a pain measurement strategy in the emergency department (ED). In this study, we explored possible differences in facial expressions before and after pain management and compared these differences with those in a self-reported pain scale.
Methods: In this observational study, convenience sampling of patients admitted to the ED was conducted. Two video sessions of facial expressions were recorded for each participant, and participants rated their painon a self-reported numeric rating scale (NRS). A total of 25 facial parameters were extracted per frame. The main outcome measurements were the differences in facial parameters, and their correlation with changes in NRS scores was examined.
Results: This study included 163 participants. A stronger reduction in NRS scores was associated with differences in systolic blood pressure (sBPr = 0.247, P = 0.011) and the following changes in facial features: eye opening (left: r = -0.210, P = 0.007; right: r = -0.206, P = 0.008), eye aspect ratio (left: r = -0.382, P < 0.001; right: r = -0.305, P < 0.001), and head rotation angle (r = 0.218, P = 0.005). Pain improvement (a difference of ≥ 4 in NRS scores) was associated with differences in BP (sBP, odds ratio [OR] = 0.973, 95% confidence interval [CI]: 0.949-0.998, P = 0.034; dBP, OR = 1.078, 95% CI: 1.026-1.113, P = 0.003), eye aspect ratio (Left: β = 5.613, 95% CI: 2.234-14.104, P < 0.001; Right: β = 2.743, 95% CI: 1.395-5.391, P = 0.003), and nasolabial fold variation (β = 0.548, 95% CI: 0.306-0.982, P = 0.043), after adjustment for variables.
Conclusions: Intraindividual changes in facial expressions can be used to track clinically relevant differences in pain. Facial expressions alone cannot be used as a pain measurement strategy in the ED.
Figures
Twenty-five facial parameters were extracted per frame to represent the facial expressions of the patient.
Twenty-five facial parameters were extracted per frame to represent the facial expressions of the patient.
Keywords
Pain | Pain measurement | Analogue pain scale | Facial expression | Facial recognition
Authors
Chi-Chun Lee
Publication Date
2021/03/08
Journal
Signa Vitae
Signa Vitae
DOI
Signa Vitae