A new artificial intelligence language processing tool could help detect cognitive decline and degenerative mental diseases like Alzheimer’s, say researchers at Boston University.
Their findings, published in the Journal of the Alzheimer’s Association, show that a machine-learning computational model can identify cognitive decline through recordings of neuropsychological tests.
“It could form the basis of an online tool that can reach everyone and can increase the number of people,” said Ioannis Paschalidis, a professor of engineering and one of the researchers at Boston University. early screening”.
Computational modeling, which does not require direct assessment, could help clinicians classify the urgency of a patient’s symptoms more effectively, allowing them to allocate resources without need to replace follow-up procedures for diagnosis.
Using automatic speech recognition software, the program transcribes the interviews and, by encoding them into numbers, detects patterns that assess the likelihood and severity of depression. reduced patient awareness. The model was trained through recording more than 1,000 neuropsychological interviews, including formal demographic and diagnostic data from neuroscientists and neuropsychologists.
Although the Boston University researchers still require further testing to qualify their model for future diagnoses worldwide, the findings suggest that the computational model at least can help clinicians move faster.
“Our models can help doctors assess patients for their potential for cognitive decline and then tailor the best resources for them by performing more testing on those who are likely to decline. higher risk of dementia,” Paschalidis said in the press release.
