It's a dilemma that's plagued doctors for centuries: When it comes to pain management, there are no reliable objective measures to determine how much a patient is actually hurting.
Doctors typically rely on self-reporting, in which patients are asked to rate their pain on a scale of zero to ten.
DNews: Trustworthiness Is Written On Our Facial Features
That can be helpful, as far as it goes, but what about cases in which you're dealing with children or others who can't always communicate their pain level effectively?
Researchers at the UC San Diego School of Medicine are hoping that facial recognition and artificial intelligence systems might help solve the problem.
In a study published this week in the journal Pediatrics, the researchers suggest that the technology can indeed help with accurate pain level assessment.
The research team used specially designed software to analyze the facial expressions of 50 kids, ages 5 to 18 years old, recovering from laparoscopic appendectomies. The video analysis data was then combined with clinical input by caregivers to determine pain level scores for each patient.
The system was shown to deliver "good-to-excellent" accuracy in assessing pain conditions, relative to existing protocols.
"Current pain assessment methods in youth are suboptimal and vulnerable to bias and underrecognition of clinical pain," the researchers write in the study's introduction. "Facial expressions are a sensitive, specific biomarker of the presence and severity of pain, and computer vision (CV) and machine-learning (ML) techniques enable reliable, valid measurement of pain-related facial expressions from video."
Smart Cat Feeder Uses Facial Recognition
The computer vision techniques used in the study are based on the Facial Action Coding System (FACS), which measures facial expressions using 46 anatomically based component movements.
The system also potentially solves another problem with pain assessment protocols. Nurses might only check on a pediatric patient every few hours, whereas a facial recognition system could provide constant monitoring. And in cases when pain comes in pulses or waves, the system can determine intervals and provide data for better administration of pain relief solutions.
via Science Daily