MRI-based biomarker tool can predict progression to dementia

Gray matter shrinkage in brains could predict how quickly someone may progress from mild cognitive impairment to dementia, suggest findings published August 25 in Neurology. 

A team led by Alexandra Touroutoglou, PhD, from Harvard Medical School in Boston developed an MRI-based biomarker tool that provides prognostic information beyond baseline clinical severity. 

“These findings support the potential value of early-onset Alzheimer disease [EOAD]-signature atrophy as an MRI-based biomarker for individualized prognostication and clinical trial stratification,” the Touroutoglou team wrote. 

EOAD develops in patients prior to age 65 and typically begins with mild cognitive impairment. This often progresses to dementia, though the speed of progression varies from person to person. And there are limited ways to predict the transition from mild cognitive impairment to dementia. 

Touroutoglou and colleagues developed a brain scan biomarker called the EOAD signature, a map that can be applied to brain MRI scans to measure shrinkage in regions of the brain involved in thinking such as memory, language and reasoning. The group studied whether baseline cortical atrophy predicts progression to dementia in patients with mild cognitive impairment because of EOAD. 

The study included 130 patients with mild cognitive impairment due to EOAD and 97 cognitively normal controls. Nearly two-thirds of people with EOAD progressed from mild cognitive impairment to dementia. 

The biomarker tool showed that greater baseline atrophy within the EOAD-signature predicted faster progression to dementia. This included a hazard ratio of 1.24 per one-standard deviation increase in atrophy (p < 0.002).  

And adding EOAD-signature atrophy burden to a model including baseline clinical severity significantly improved model fit (ΔAIC = −4.5; likelihood ratio test p = 0.011). 

The study authors also highlighted that the biomarker tool outperformed analyzing only symptoms at the beginning of the study to predict progression. 

Touroutoglou said better tools are needed to predict when someone with early-onset Alzheimer’s disease may lose independence and progress from mild cognitive impairment to dementia. 

“This brain scan biomarker we developed may help predict how quickly the disease will progress in each individual, giving physicians, people with early-onset Alzheimer’s disease and their families better information about what to expect and allowing earlier clinical trial enrollment for treatments that may improve outcomes,” she said in a prepared statement. 

The authors called for future research to validate the tool in independent cohorts. This would prove generalizability and robustness across different populations and settings, they added. 

“After successful external validation, development of user-friendly implementation tools—such as web-based calculators or structured scoring sheets—should be considered to facilitate adoption in clinical practice and trial design,” the authors wrote. 

Read the full study here.