Innovative machine learning method predicts thought processes

Neuroscientists at the University of California, Los Angeles, are using computerized machine learning (ML) methods to analyze and predict mental states. In a new study, researchers used a functional MRI to observe brain activity as cigarette smokers watched a video meant to induce nicotine cravings, a neutral video or no video at all. From this data, ML algorithms were able to anticipate changes in subjects' underlying neurocognitive structure, predicting with a high degree of accuracy (up to 90 percent) what they were watching and if they were experiencing cravings. Neuroscientists hope to someday use these ML methods in a biofeedback context, showing subjects real-time brain readouts to let them know when they are experiencing cravings and how intense those cravings are, in the hopes of training them to control the cravings. But, since this clearly changes the thought process and cognitive state for the subject, they may face special challenges in trying to decode a moving target.