A team of researchers at Stevens Institute of Technology in the U.S. has developed a tool to enable accurate and faster diagnosis of Alzheimer’s disease using artificial intelligence (AI).
The tool detects subtle differences in the way Alzheimer’s sufferers use language, a statement by the institute said. This method eliminates the need for expensive scans and in-person testing.
People with the disease often use vague language like “My stomach feels bad because I haven’t eaten” instead of “I’m hungry.” The AI engine uses attention mechanism and neural network to identify well-known telltale signs of Alzheimer’s and detect subtle linguistic patterns previously overlooked.
The research team trained the algorithm using both healthy subjects and those suffering from Alzheimer’s.
The tool addresses the important question of reliability of AI systems in the medical field, said K P Subbalakshmi, founding director of Stevens Institute of Artificial Intelligence and head researcher of this project.
The team aims to use this method to understand how other neurological conditions including asphasia, stroke and depression affect language use.