Predicting rapid cognitive decline in Alzheimer's disease patients using quantitative EEG markers and neuropsychological test scores

Annu Int Conf IEEE Eng Med Biol Soc. 2016 Aug:2016:6078-6081. doi: 10.1109/EMBC.2016.7592115.

Abstract

Alzheimer's Disease (AD) can take different courses: some patients remain relatively stable while others decline rapidly within a given period of time. Losing more than 3 Mini-Mental State Examination (MMSE) points in one year is classified as rapid cognitive decline (RCD). This study used neuropsychological test scores and quantitative EEG (QEEG) markers obtained at a baseline examination to identify if an AD patient will be suffering from RCD. Data from 68 AD patients of the multi-centric cohort study PRODEM-Austria were applied. 15 of the patients were classified into the RCD group. RCD versus non-RCD support vector machine (SVM) classifiers using QEEG markers as predictors obtained 72.1% and 77.9% accuracy ratings based on leave-one-out validation. Adding neuropsychological test scores of Boston Naming Test improved the classifier to 80.9% accuracy, 80% sensitivity, and 81.1% specificity. These results indicate that QEEG markers together with neuropsychological test scores can be used as RCD predictors.

MeSH terms

  • Alzheimer Disease / diagnosis*
  • Biomarkers / analysis*
  • Cognitive Dysfunction / diagnosis*
  • Cohort Studies
  • Electroencephalography*
  • Humans
  • Neuropsychological Tests*
  • Sensitivity and Specificity

Substances

  • Biomarkers