What If a Machine Could Read Your Brain Signals for Pain?

At some point or another most of us have been asked to rate our pain on a scale of zero to 10 during a visit to the doctor or hospital. But what if a patient is unconscious or noncommunicative and unable to rate their own pain? What if there was a piece of technology capable of communicating a patient’s pain level for them by analyzing brain activity? Researchers at MIT and elsewhere have developed just such a system. The portable device leverages an emerging neuroimaging technique called functional near infrared spectroscopy (fNIRS) in which sensors placed around the head measure oxygenated hemoglobin concentrations that indicate neuron activity. The researchers describe the method, and how it could be used to quantify pain in patients, in a paper presented at the International Conference on Affective Computing and Intelligent Interaction. For their work, the researchers use only a few fNIRS sensors on a patient’s forehead to measure activity in the prefrontal cortex, which plays a major role in pain processing. Using the measured brain signals, the researchers developed personalized machine-learning models to detect patterns of oxygenated hemoglobin levels associated with pain responses. When the sensors are in place, the models can detect whether a patient is experiencing pain with around 87% accuracy. “The way we measure pain hasn’t changed over the years,” said Daniel Lopez-Martinez...
Source: MDDI - Category: Medical Devices Authors: Tags: Design News Imaging Source Type: news