Carnegie Mellon University (CMU) researchers have developed new technology capable of predicting which noun, from a group of 60, a person is thinking about based on brain-activity patterns. The researchers learned that human brains analyze objects based on how they can satisfy a need, such as shelter or hunger, says Tom Mitchell, head of CMU's machine-learning department. This represents the first time scientists have identified thought patterns using concepts rather than images. The researchers hope this technology could someday help people with conditions such as autism or paranoid schizophrenia. The technology also could potentially assist those without handicaps, says Princeton University's Ken Norman. "Imagine how efficient it would be to think about something and have it appear on a computer screen," Norman says. "But we've got a very long way to go before we get to that point."