Computer Avatars Play a Part in Dementia Detection

Researchers found that it is possible to detect dementia from conversations in human-agent interaction using machine learning, according to a study published in IEEE Journal of Translational Engineering in Health and Medicine and cited by ScienceDaily . The researchers proposed machine learning algorithms for detecting signs of dementia in its early stages, developing a dementia detection system using interactive computer avatars. They created a model for machine learning based on features of speech, language, and faces from recorded dialogues with older participants. Using the technology, a computer was able to distinguish between individuals with dementia from healthy controls at a rate of 90 percent in six questions (two to three minutes per question).