How this AI tool can detect Alzheimer’s by analyzing subtle linguistic patterns
We may be one step closer to an artificial intelligence (AI) tool capable of diagnosing Alzheimer’s disease faster and more accurately, according to a new study conducted by Stevens Institute of Technology.
“This is a real breakthrough. We’re opening an exciting new field of research, and making it far easier to explain to patients why the A.I. came to the conclusion that it did, while diagnosing patients. This addresses the important question of trustability of A.I .systems in the medical field,” said K.P. Subbalakshmi, the lead researcher.
The new AI tool involves the analyzation of subtle linguistic patterns characteristic of people with a neurodegenerative disease. Alzheimer’s typically affects an individual’s use of language and so researchers developed an algorithm able to distinguish healthy people from Alzheimer’s patients.
The AI system gradually assesses and learns structural and thematic relationships between sentences, producing highly accurate results.
“Our A.I. software is the most accurate diagnostic tool currently available while also being explainable. This is absolutely state-of-the-art,” Subbalakshmi added in a news release.
“If other researchers identify new markers of Alzheimer’s, we can simply plug those into our architecture to generate even better results.”
Since the AI tool was only tested using the English language, Subbalakshmi aims to scour new data and begin testing in other languages for future research.