Computer Algorithm Can Sense Pain
September 14, 2011

Computer Algorithm Can Sense Pain


Researchers said on Tuesday they have developed a computer algorithm that can detect when a person feels pain.

The team at Stanford University in California used computer learning software to sort through data generated by brain scans in order to determine whether or not a person was feeling any pain.

"People have been looking for a pain detector for a very long time," Sean Mackey, MD, PhD, chief of the Division of Pain Management and associate professor of anesthesiology, said in a statement. "We're hopeful we can eventually use this technology for better detection and better treatment of chronic pain."

The team took eight subjects and put them in the brain-scanning machine.  They applied a heat probe to their forearms, causing moderate pain.

The brain patterns with and without pain were then recorded and interpreted by advanced computer algorithms to create a model of what pain looks like.

The idea was to train a linear support vector machine on one set of individuals, then later use that same computer model to accurately classify pain in a new set of individuals.

"We asked the computer to come up with what it thinks pain looks like,"  Neil Chatterjee, currently a MD/PhD student at Northwestern University, said in a press release. "Then we could measure how well the computer did." The computer was successful 81 percent of the time.

The study was published in the journal PLoS ONE on September 13.


On the Net: