Senior with dementia

(HealthDay News) — A model that incorporates demographic information, brain imaging test results, and genetic biomarkers can accurately predict the five-year risk for dementia from Alzheimer disease (AD), according to a study published online Sept. 30 in Alzheimer’s & Dementia.

Sarah M. Hartz, M.D., Ph.D., from the Washington University School of Medicine in St. Louis, and colleagues analyzed longitudinal data from more than 10,000 cognitively unimpaired older adults to develop a model that can predict five-year dementia risk.

The researchers found that in an independent dataset, the model achieved an area under the receiver operating characteristic curve (AUC) of 0.79 for five-year prediction of AD dementia. When clinical and cognitive variables (AUC, 0.79) and the apolipoprotein E genotype (AUC, 0.76) were added to the demographic model, accuracy remained similar. However, when the risk computed from the demographic model was incorporated with hazard ratios computed from independent data for amyloid positron emission tomography status and magnetic resonance imaging hippocampal volume (AUC, 0.84) and for plasma amyloid beta (Aβ)42/Aβ40 (AUC, 0.82), accuracy improved.

“This approach allows for improved accuracy and communication of AD risk among cognitively unimpaired older adults,” the authors write.

One author disclosed financial ties to the laboratory where plasma Aβ40 and Aβ42 levels were quantified.

Abstract/Full Text (subscription or payment may be required)