Machine-learning algorithms analyzing human communication can predict whether someone will develop Alzheimer’s disease more accurately than standard biomedical screening, say IBM and Pfizer.
IBM claims its software was capable of correctly predicting the onset of Alzheimer’s 71 per cent of the time, compared to 59 per cent for standard clinical techniques, by analyzing the descriptive abilities of people as they age for warning signs that the disease is taking hold.
“Our results demonstrate that it is possible to predict future onset of Alzheimer's disease using language samples obtained from cognitively normal individuals,” the team wrote in a paper published in The Lancet's EClinicalMedicine journal on Thursday.
Elon Musk's new idea is to hook your noggin up to an AI – but is he just insane about the brain?READ MORE
Using data from America's Framingham Heart Study, which has examined more than 5,000 Massachusetts participants and their families since 1948, the IBM-Pfizer team trained their system using the results from cognitive tests administered every four years. Speaking in short sentences with less complex grammatical structures, and a repetition of the same words, are often signals that a patient is at a higher risk of developing Alzheimer’s disease, as well as other identifiers. All of which a computer can learn to pick up on.
“The most prominent ones are lack of specificity in naming objects and actions, repetitions, and poverty of grammatical constructions,” Guillermo Cecchi, co-author of the study and an IBM principal research staff member told The Register.
Specifically, the researchers trained their system to look for signs of speech impairment by analyzing 703 language samples from 270 patients. The model was then tested on 80 participants; where the average age of the group was in the late 70s. The software was able to successfully predict the onset of Alzheimer’s before an official diagnosis correctly seven in ten times.
“Ultimately, we hope this research will take root and aid in the future development of a simple, straightforward and easily accessible tool to help clinicians assess a patient’s risk of Alzheimer’s disease through the analysis of speech and language, and in conjunction with a number of other facets of an individual’s health and biometrics,” Cecchi said. ®