Researchers have made a significant breakthrough in the early diagnosis of Alzheimer’s disease — using artificial intelligence.

The researchers at Boston University developed an advanced AI algorithm capable of analyzing speech patterns in individuals with mild cognitive impairment (MCI) to predict the progression to Alzheimer’s disease, according to a new study.

Published in the journal Alzheimer & Dementia, the study demonstrates the algorithm’s impressive accuracy of 78.5 percent over a six-year period.

“We wanted to predict what would happen in the next six years—and we found we can reasonably make that prediction with relatively good confidence and accuracy,” Ioannis Paschalidis, director of the BU Rafik B. Hariri Institute for Computing and Computational Science & Engineering, said in the study. “It shows the power of AI.”

The research involved 166 participants aged between 63 and 97 years. Using state-of-the-art machine learning techniques, the AI was able to detect specific speech signals that indicate a potential advance towards Alzheimer’s. The model also incorporated demographic factors such as age and sex, enhancing its predictive precision.

Early detection of Alzheimer’s is vital for timely intervention with treatments that can decelerate disease progression. Although a definitive cure remains elusive, existing therapies can alleviate symptoms and improve patients’ quality of life. The new AI algorithm’s ability to detect Alzheimer’s in its nascent stages represents a crucial step forward for early intervention and proactive disease management.

“We hope, as everyone does, that there will be more and more Alzheimer’s treatments made available,” Mr. Paschalidis said. “If you can predict what will happen, you have more of an opportunity and time window to intervene with drugs, and at least try to maintain the stability of the condition and prevent the transition to more severe forms of dementia.”