Biomarkers do not predict conversion to Alzheimer’s disease (AD) perfectly and criteria do not specify how to take individual patient characteristics into account. Consequently, biomarker use may be challenging for clinicians, especially in patients with mild cognitive impairment (MCI). As part of the ABIDE project, Van Maurik and colleagues constructed biomarker-based prognostic models (cerebrospinal fluid(CSF) model, magnetic resonance imaging (MRI) model and a combined model) that enable prediction of future Alzheimer’s disease, or any type of dementia, in patients with mild cognitive impairment. When using these models, any value can be entered for the biomarkers and patient characteristics, resulting in personalized probabilities with confidence intervals. The models could aid clinicians in interpreting biomarker values and providing individually tailored prognostic information.
Read the article in JAMA Neurology.
Read more (news item in Dutch on VUmc website)