Boston University study: Artificial Intelligence can now predict if you will suffer from Alzheimer's disease

Artificial Intelligence continues to contribute to the world of medicine with a new advance that could transform the early diagnosis of Alzheimer's disease.

Researchers at Boston University have developed a sophisticated AI algorithm that analyzes speech patterns in people with mild cognitive impairment (MCI) to predict progression to Alzheimer’s disease.

This innovative study, published in the prestigious journal Alzheimer & Dementia, reveals an accuracy of 78.5% in predicting the disease within 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,” says Ioannis (Yannis) Paschalidis, director of the BU Rafik B. Hariri Institute for Computing and Computational Science & Engineering. “It shows the power of AI.”

The study involved 166 participants, whose ages ranged from 63 to 97 years.

Using advanced machine learning techniques, the algorithm was able to identify specific signals in speech that indicate possible progression towards Alzheimer's.

In addition, the model incorporates factors such as the age and sex of the participants, thus improving its predictive accuracy.

Early detection of Alzheimer's is essential to intervene with treatments that can slow the progression of the disease.

Although there is currently no definitive cure, available therapies can mitigate symptoms and improve patients' quality of life.

The ability of this AI algorithm to predict the disease in its early stages represents a significant opportunity for early intervention and proactive management of Alzheimer’s.

Identifying patients in the early stages of the disease facilitates their participation in clinical trials, which is crucial for the development of more effective treatments. The Boston University study highlights that, despite the low quality of the voice recordings used to train the algorithm, remarkable accuracy was achieved.

This suggests that with higher quality data, the accuracy of the model could improve further, enhancing its usefulness in the clinical setting.

This breakthrough in using AI for Alzheimer's prediction not only offers hope to patients and their families, but also opens new avenues for medical research.

“We hope, as everyone does, that there will be more and more Alzheimer’s treatments made available,” says Paschalidis, a BU College of Engineering Distinguished Professor of Engineering and founding member of the Faculty of Computing & Data Sciences. “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.”