Facial expression differences indicate pain improvement at the emergency department

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.

Pain; Pain measurement; Analogue pain scale; Facial expression; Facial recognition

[1] Debono DJ, Hoeksema LJ, Hobbs RD. Caring for patients with chronic pain: pearls and pitfalls. Journal of the American Osteopathic Association. 2013;113: 620-627.

[2] Turk DC, Dworkin RH. What should be the core outcomes in chronic pain clinical trials? Arthritis Research & Therapy. 2004; 6: 151-154.

[3] Apfelbaum JL, Chen C, Mehta SS, Gan TJ. Postoperative pain experience: results from a national survey suggesting postoperative pain continues to be undermanaged. Anesthesia and Analgesia. 2003; 97: 534-540.

[4] Bullard MJ, Unger B, Spence J, Grafstein E. Revisions to the Canadian Emergency Department Triage and Acuity Scale (CTAS) adult guidelines. Canadian Journal of Emergency Medicine. 2008; 10: 136-151. (In French)

[5] Ng CJ, Hsu KH, Kuan JT, Chiu TF, Chen WK, Lin HJ, et al. Comparison between Canadian triage and acuity scale and Taiwan triage system in emergency departments. Journal of the Formosan Medical Association. 2010; 109: 828-837.

[6] Ng CJ, Yen ZS, Tsai JC, Chen LC, Lin SJ, Sang YY, et al. TTAS national working group. Validation of the Taiwan triage and acuity scale: a new computerized five-level triage system. Emergency Medicine Journal. 2011; 28: 1026-1231.

[7] Eriksson K, Wikstro¨m L, A rested K, Fridlund B, Brostr¨om A. Numeric rating scale: patients’ perceptions of its use in postoperative pain assessments. Applied Nursing Research. 2014; 27: 41-46.

[8] Castarlenas E, S´anchez-Rodr´ıguez E, Vega Rde L, Roset R, Mir´o J. Agreement between verbal and electronic versions of the numerical rating scale (nrs-11) when used to assess pain intensity in adolescents. The Clinical Journal of Pain. 2015; 31: 229-234.

[9] Herr K, Titler M. Acute pain assessment and pharmacological manage-ment practices for the older adult with a hip fracture: review of ED trends. Journal of Emergency Nursing. 2009; 35: 312-320.

[10] Encandela JA. Social science and the study of pain since Zborowski: a need for a new agenda. Social Science and Medicine. 1993; 36: 783-791.

[11] Main CJ, Spanswick CC. Pain management: an interdisciplinary approach. Toronto: Churchill Livingstone. 2000.

[12] Hale C, Hadjistavropoulos T. Emotional components of pain. Pain Research & Management. 1997; 2: 217-225.

[13] Hadjistavropoulos HD, Craig KD, Hadjistavropoulos T, Poole GD. Subjective judgments of deception in pain expression: accuracy and errors. Pain. 1996; 65 : 251-258.

[14] Hill ML, Craig KD. Detecting deception in pain expressions: the structure of genuine and deceptive facial displays. Pain. 2002; 98: 135-144.

[15] Prkachin KM, Solomon PE. The structure, reliability and validity of pain expression: evidence from patients with shoulder pain. Pain. 2008; 139: 267- 274.

[16] Baltrusaitis T, Robinson P, Morency LP. Constrained local neural fields for robust facial landmark detection in the wild. IEEE International Conference on Computer Vision Workshops. 2013; 354-361.

[17] Tzimiropoulos G, Alabort-i Medina J, Zafeiriou S, Pantic M. Generic active appearance models revisited, in Computer Vision-ACCV 2012. Springer. 2012; 650-663.

[18] Kulkarni S, Reddy N, Hariharan S. Facial expression (mood) recognition from facial images using committee neural networks. Nature Biomedical Engineering. 2009; 10: 16.

[19] Littlewort GC, Bartlett MS, Lee K. Automatic coding of facial expressions displayed during posed and genuine pain, Image and Vision Computing. 2009; 27: 1797-1803.

[20] Lu G, Yang C, Chen M, X Li. Sparse representation based facial expression classification for pain assessment in neonates, in Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), 2016 12th International Conference on. IEEE. 2016; 1615-1619.

[21] Kaltwang S, Rudovic O, Pantic M. Continuous pain intensity estimation from facial expressions. Advances in Visual Computing. 2012; 368-377.

[22] Aung MS, Kaltwang S, Romera-Paredes B, Martinez B, Singh A, Cella M, et al. The automatic detection of chronic pain-related expression: requirements, challenges and the multimodal emopain dataset. IEEE Transactions on Affective Computing. 2016; 7: 435-451.

[23] Olugbade TA, Aung M, Bianchi-Berthouze N, Marquardt N, Williams AC. Bi-modal detection of painful reaching for chronic pain rehabilitation systems, in Proceedings of the 16th International Conference on Multimodal Interaction. Association for Computing Machinery. 2014; 455-458.

[24] Lucey P, Cohn JF, Matthews I, Lucey S, Sridharan S, Howlett J, et al. Automatically detecting pain in video through facial action units, systems, man, and cybernetics, part b: cybernetics. IEEE Transactions on. 2011; 41: 664-674.

[25] Rathee N, Ganotra D. A novel approach for pain intensity detection based on facial feature deformations, Journal of Visual Communication and Image Representation. 2015; 247-254.

[26] Werner P, Al-Hamadi A, Niese R, Walter S, Gruss S, Traue HC. Towards pain monitoring: facial expression, head pose, a new database, an automatic system and remaining challenges. British Machine Vision Conference. 2013; 119-1.

[27] France CR, Froese SA, Stewart JC. Altered central nervous system processing of noxious stimuli contributes to decreased nociceptive responding in individuals at risk for hypertension. Pain. 2002; 98: 101-108.

[28] Fagius J, Karhuvaara S, Sundlof G. The cold pressor test: effects on sympathetic nerve activity in human muscle and skin nerve fascicles. Acta Physiologica Scandinavica. 1989; 137: 325-334.

[29] Nordin M, Fagius J. Effect of noxious stimulation on sympathetic vasoconstrictor outflow to human muscles. Journal of Physiology. 1995; 489: 885-894.

[30] Maixner W, Gracely RH, Zuniga JR, Humphrey CB, Bloodworth GR. Cardiovascular and sensory responses to forearm ischemia and dynamic hand exercise. American Journal of Physiology. 1990; 259: R1156-R1163.

[31] Dworkin BR, Filewich RJ, Miller NE, Craigmyle N, Pickering TG. Baroreceptor activation reduces reactivity to noxious stimulation: impli-cations for hypertension. Science. 1979; 205: 1299-1301.

[32] Ashraf AB, Lucey S, Cohn JF, Chen T, Ambadar Z, Prkachin MK, et al. The painful face-pain expression recognition using active appearance models. Image and Vision Computing. 2009; 27: 1788-1796.

[33] Kaltwang S, Rudovic O, Pantic M. “Continuous pain intensity estimation from facial expressions,” in Advances in Visual Computing. Springer. 2012; 368-377.

[34] LittlewortGC, Bartlett MS, Lee K. Automatic coding of facial expressions displayed during posed and genuine pain. Image and Vision Computing. 2009; 27: 1797-1803.

[35] Lucey P, Cohn JF, Prkachin KM, Solomon PE, Chew fS, Matthews I. Painful monitoring: automatic pain monitoring using the unbc-mcmaster shoulder pain expression archive database. Image and Vision Computing. 2012; 30: 197-205.

[36] Carr DB, Jaco AK, Cahpman CR, Ferrell B, Field HL, Heidrich G. Acute pain management: operative or medical procedures and trauma. US Public Health Service, Agency for Health Care Policy and Research. 1992; 11: 391-414.

[37] Kunz M, Mylius V, Schepelmann K, Lautenbacher S. On the relationship between self-report and facial expression of pain. Journal of Pain. 2004; 5: 368-76.

[38] Kenshalo DR. The skin senses: proceedings of the first International Symposium on the Skin Senses, held at the Florida State University in Tallahassee, Florida. Sensory, motivational and central control determinants of chronic pain: a new conceptual model. Charles C Thomas 1968; 423-439.

[39] Skevington SM. Psychology of pain. Chichester, UK: Wiley. 1995; 18.

[40] Craig AD. Pain mechanisms: labeled lines versus convergence in central processing. Annual Review of Neuroscience. 2003; 26: 1-30.