BU Researchers Look To Quantify The Risk Of Alzheimer's Disease Progression

Scientist holding a petri dish with a brain scan illustrating research into dementia, alzheimers and other brain disorders.

Photo: Andrew Brookes / Cultura / Getty Images

BOSTON (WBZNewsRadio) - As the cost of caring for those suffering from Alzheimer's disease continues to rise, researchers at Boston University have developed what they call a "deep learning framework," that can help identify people suffering from mild cognitive impairment and provide early intervention before the diagnosis progresses into Alzheimer's disease.

Boston University has been leading the world in Alzheimer's Research since 1996, with the creation of the Boston University Alzheimer's Disease Research Center (BU ADRC). The research conducted within it's walls aims to reduce the human and economic costs of the disease through the advancement of knowledge.

It's one of just 33 AD research centers in the U.S. funded by the National Institute of Health to further Alzheimer's disease research.

A current working theory related to the disease and repeated drug failures in Alzheimer's treatment, is patients enrolled in experimental therapies end up in the trial too late in the disease process. Based on that theory, it's more important than ever to identify those at risk of developing the illness.

“Quantifying the risk of progression to Alzheimer’s disease (AD) could help identify persons who could benefit from early interventions,” says corresponding author Vijaya B. Kolachalama, PhD, FAHA, associate professor of medicine at Boston University Chobanian & Avedisian School of Medicine.

Researchers looked at a group of patients diagnosed with mile cognitive impairment and separated individuals based on their brain fluid amyloid-β levels. Then the group looked specifically at gray matter volume patterns to pinpoint risk groups.

“By utilizing advances in interpretable machine learning, we demonstrated that brain regions relevant to AD such as the medial temporal lobe are among the most important regions for predicting progression risk, thereby assuring that our findings are consistent with established medical knowledge,” added Kolachalama. “We utilized survival-based deep neural networks in conjunction with minimally processed structural MRI, a widely available, non-invasive technique. Further, by employing state-of-the-art deep learning methods in conjunction with SHapley Additive exPlanations (SHAP), a method based on cooperative game theory and used to increase transparency and interpretability of machine learning models, we were able to identify regions particularly important for predicting increased progression risk.”

According to BU, the estimated cost of caring for Alzheimer's patients around the world will surpass $1 trillion in just a few years.

Follow WBZ NewsRadio: Facebook | Twitter | Instagram | iHeartmedia App | TikTok

Sponsored Content

Sponsored Content