Connect with us
  • Elysium

Dementia news

Data-led approach targets early Alzheimer’s intervention

Deep learning framework can help maximise outcomes for those with mild cognitive impairment



A data-driven strategy to highlight a person’s risk of progression from mild cognitive impairment to Alzheimer’s disease has been devised, which could help identify those who could benefit from early interventions. 

With dementia cases growing significantly worldwide, and the projected cost of caring for people with Alzheimer’s expected to exceed $1trillion globally in a few years, neurodegenerative disease is a hugely significant issue in both health and financial terms. 

However, with advances being made in drug development and therapies, one fear is that patients undergoing experimental treatments are selected too late for them to gain maximum benefit from the intervention. 

Therefore, the need to identify patients at high risk of progression from cognitive decline to Alzheimer’s at an early stage is vital. 

To help identify those people who could benefit from early interventions, researchers from Boston University have developed a deep learning framework that can stratify individuals with mild cognitive impairment (MCI) based on their risk of advancing to Alzheimer’s.

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

In the research, the team studied data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and National Alzheimer’s Coordinating Center (NACC), separating individuals with MCI into groups based on their brain fluid amyloid-β levels. 

They studied gray matter volume patterns within these groups to identify risk groups, validating their findings with expert assessments, and developed models that combined neural networks with survival analysis to predict the progress from MCI to Alzheimer’s disease. 

The researchers then linked their model predictions with biological evidence, confirming Alzheimer’s diagnoses with post-mortem data.

“By utilising advances in interpretable machine learning, we demonstrated that brain regions relevant to Alzheimer’s, 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,” said Dr Kolachalama.

According to the researchers, these findings represent innovation at the intersection of neurology and computer science, while underscoring model conformity with biological evidence using routinely collected information such as structural MRI to quantify risk of progression from MCI to Alzheimer’s.

“We utilised 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,” added Dr Kolachalama.