Computer Vision Software Tested on Pediatric Post-Op Pain

Pediatric pain assessment via current methods is prone to bias and underrecognition of pain severity. Writing in the June 1 online edition of the journal Pediatrics, researchers at UC San Diego describe a new computer vision algorithm that can assess pain levels from facial expressions. [To read an interview with the lead author of the study, click here for The Pain Reporter. The authors assert that the new technology could be of value for uses such as gauging pain medication dosage levels postsurgery. Speculating into the future, the technology could enhance the effectiveness of remote or robotic pain assessment.

The computer vision machine learning (CVML) model for assessment of pediatric postoperative pain was developed from videos of 50 neurotypical youth 5 to 18 years old in both endogenous/ongoing and exogenous/transient pain conditions after laparoscopic appendectomy. The researchers report that the model performed equivalently to nurses but not as well as parents in detecting pain vs no-pain conditions, but performed equivalently to parents in estimating pain severity. Demographic factors did not affect model performance.

To read about gene variants and childhood pain, click here.

To read about the need for solutions for children postsurgery, click here.

Read the journal abstract, with access to the full article, here.

 

 

Related Content