Software "Reads" Pain Levels via Children's Facial Expressions

Image courtesy of the UC San Diego School of Medicine
Image courtesy of the UC San Diego School of Medicine

A new method for measuring pediatric pain levels using novel facial pattern recognition software has been developed by researchers at the University of California, San Diego School of Medicine and is described in a study published in Pediatrics.

The new software was developed using data collected from the prior software Computer Expression Recognition Toolbox, which uses computer vision techniques to analyze facial expressions based on the Facial Action Coding System (FACS) using 46 anatomically based component movements. This new software improves upon older software by translating the facial movement data into a pain score that is then compared to the child's self-reporting and the parent and nurse by proxy pain estimates. Researchers sought to evaluate the software's accuracy at pain measurement and filmed pain-related facial expressions of 50 young people aged 5–18 who had undergone laparoscopic appendectomies at three different visits post-surgery: within 24 hours after appendectomy, one calendar day after the first visit, and at a follow-up visit 2–4 weeks after surgery. Pain rating by parents and nurses were collected along with the facial video recordings and self-reported pain ratings.

RELATED: Medical Clowns May Benefit Pediatric Surgical Outcomes

The software showed good-to-excellent accuracy in assessing pain conditions while operating in real-time and continuously, indicating that the technology performed equivalent to parents and better than nurses; it also demonstrated strong correlations with patient self-reported pain ratings. No bias in pain assessment by ethnicity, race, gender, or age in the patient cohort studied was demonstrated.

While the software requires additional testing for other forms of clinical pain in children, the technology could help to alert clinicians of pediatric patient pain as it occurs rather than during scheduled assessments for timely interventions.

For more information visit UCSD.edu.