A new artificial intelligence language-processing tool could potentially help detect cognitive impairment and mental degenerative diseases like Alzheimer鈥檚, researchers at Boston University say.
Their , which were published in The Journal of the Alzheimer鈥檚 Association, suggest that a machine-learning computational model could identify cognitive decline through audio recordings of neuropsychological tests.
鈥淚t can form the basis of an online tool that could reach everyone and could increase the number of people who get screened early,鈥� said Ioannis Paschalidis, a professor of engineering and one of the researchers at Boston University, in a
The computational model, which does not require in-person assessments, could ultimately help clinicians triage the urgency of patients' symptoms more efficiently, allowing them to allocate resources without replacing follow-up processes for diagnosis, she said.
Using automated speech recognition software, the program transcribes interviews and, by encoding them into numbers, detects patterns that assess the likelihood and severity of a patient鈥檚 cognitive impairment. The model was trained through recordings of over 1,000 neuropsychological interviews, factoring in demographic data and official diagnoses from neurologists and neuropsychologists.
Although Boston University researchers still require further testing to qualify their model for future diagnoses worldwide, the findings suggest that the computational model could, at the very least, help clinicians move quicker.
鈥淥ur models can help clinicians assess patients in terms of their chances of cognitive decline, and then best tailor resources to them by doing further testing on those that have higher likelihood of dementia,鈥� Paschalidis said in the news release.
