Computer Program Could Help Spot Pain Fakers

A joint study by researchers at the University of California, San Diego, the University at Buffalo, and the University of Toronto has found that a computer vision system can distinguish between real or faked expressions of pain more accurately than humans can.

The researchers employed the computer expression recognition toolbox (CERT), an end-to-end system for fully automated facial-expression recognition that operates in real time assessing the accuracy of machine versus human vision.

The program could be used in the future to uncover pain malingering, when a patient or claimant fabricates or exaggerates symptoms of pain for an ulterior motive.

The study, “Automatic Decoding of Deceptive Pain Expressions,” was published in the latest issue of Current Biology.

Study participants were asked to assess whether expressions of pain were real or fake by viewing video clips of individuals, some of whom were subjected to the cold presser test in which a hand is immersed in ice water to measure pain tolerance, and of others who faked their painful expressions.

Researchers noted the computer system managed to detect distinctive, dynamic features of facial expressions, while humans weren’t able to discriminate between real and faked expressions. Even after training, humans were only accurate 55 percent of the time while the computer was accurate 85 percent of the time.

The single most predictive feature of falsified expressions, the study showed, was how and when the mouth opens and closes. Fakers’ mouths open with less variation and too regularly.