Middle-east Arab News Opinion | Asharq Al-awsat

New Program Measures Pain through Facial Expressions | ASHARQ AL-AWSAT English Archive 2005 -2017
Select Page
Media ID: 55382899
Caption:

Representational image. (Reuters)


San Francisco, London – A new computer program that rates how much pain someone is in just by looking at their face could help doctors decide how to treat patients.

Jeffrey Cohn at the University of Pittsburgh in the US explained that these metrics might be useful in determining real pain from faked pain, which means that the system could make the difference between prescribing potentially addictive painkillers.

The US website “New Scientist” quoted Dianbo Liu, who created the system with his colleagues at the Massachusetts Institute of Technology, as saying that objectively measuring pain levels is a tricky task.

People experience and express pain differently, so a doctor’s estimate of a patient’s pain can often differ from a self-reported pain score, he added.

In an attempt to introduce some objectivity, Liu and his team trained an algorithm on videos of people wincing and grimacing in pain. Each video consisted of a person with shoulder pain, who had been asked to perform a different movement and then rate their pain levels.

Liu said certain parts of the face are particularly revealing, noting that large amounts of movement around the nose and mouth tended to suggest higher self-reported pain scores.

The result was an algorithm that can use subtle differences in facial expressions to inform a guess about how a given person is feeling. To help make it more accurate, Liu’s system can be tweaked to take into account someone’s age, sex and skin complexion.

A study from the University of California in San Diego meanwhile found that a computer system could weed out fakers 85 percent of the time, whereas trained humans were only accurate 55 percent of the time.

However, Liu asserted that the system could never be a replacement for real doctors, and noted that he is planning to further train the algorithm with more videos of people in pain to see if that boosts its pain-rating abilities.