Alzheimer’s is a progressive disease that affects the brain and leads to a loss of brain function.
Currently, there’s no single test that can be used to diagnose it. Instead, a doctor or specialist will get a thorough understanding of the patient’s symptoms, medical history and carry out cognitive checks, meaning it can sometimes take a long time to diagnose the condition.
However, new research from MIT’s Computer and Artificial Intelligence Laboratory has shown that AI, combined with machine-learning algorithms, may be able to help provide a diagnosis much earlier than a GP or specialist can.
Researchers at MIT have been studying a patient called David, who has not yet been diagnosed with Alzheimer’s, along with four other patients who already have a diagnosis.
An AI-powered box hangs on the wall of his room, which tracks his movements, including when he gets out of bed, goes to the bathroom and his sleeping habits. The box uses a wireless radio signal, which reflects off everything in a 30-foot radius, to collect this data.
The researchers can then use machine-learning algorithms to spot behavioural patterns. Dina Katabi the director of the MIT Wireless Center says, “As you teach it more and more, the machine learns, and the next time it sees a pattern, even if it’s too complex for a human to abstract that pattern, the machine recognizes that pattern.”
These patterns can then be matched against the symptoms of the patients who have an Alzheimer’s diagnosis. These include sleep disturbances, repeated behaviours, wandering, agitation and depression. “If you can catch these deviations early, you will be able to anticipate them and help manage them,” Ipsit Vahia, a geriatric psychiatrist at McLean Hospital and Harvard Medical School working with the researchers at MIT says.
Push Doctor’s Dr Simon Latham commented: “Clever use of artificial intelligence could speed up research into diagnosing complicated diseases such as Alzheimer’s at an earlier stage than at present. This offers the exciting possibility of finding a cure.”