Premium
P1‐027: Astrocyte‐derived proteins in the cerebrospinal fluid as biomarkers for the pathobiological staging of Alzheimer's disease
Author(s) -
Schipke Carola,
Fesche Arne,
Haas Brigitte,
Heuser Isabella,
Peters Oliver
Publication year - 2012
Publication title -
alzheimer's and dementia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 6.713
H-Index - 118
eISSN - 1552-5279
pISSN - 1552-5260
DOI - 10.1016/j.jalz.2012.05.302
Subject(s) - glial fibrillary acidic protein , biomarker , cerebrospinal fluid , astrocyte , neurodegeneration , pathophysiology , pathology , disease , alzheimer's disease , tau protein , medicine , biology , neuroscience , central nervous system , immunohistochemistry , biochemistry
they don’t typically capture inherent brain physiology and dynamic processes. The present study extends an activated EEG medical device for the physiological assessment of brain health looking at multivariate classifiers. Methods: Recent advances in wireless electroencephalography hardware have enabled the development of a novel activated EEG system (MindReader TM) to physiologically focus the assessment of brain health to various sensory circuits and cognitive tasks. The MindReader assesses brain function while actively stimulating the subject with various stimuli. Last year at AAIC Paris, BCI reported univariate results which replicated and extended the published EEG diagnostic literature. This year, multi-variate predictive statistical models were built and tested in JMP Pro v9 from SAS to assess clinical performance to accuracy classify mild AD from Control. Tree based methods (e.g. Random Forests), discriminant analysis (e.g. linear), 2-layer Neural Networks and other techniques were run on our data table of n 1⁄4 10 AD vs n 1⁄4 13 Controls. Results: Several models showed interesting 2, 3, 4 and 5-marker classifiers selected from a list of over 150 published or proprietary EEG biomarker candidates for each of m 1⁄4 16 tasks per subject. Clinical performance ranged from mediocre (60 % sensitivity, 60% specificity) to modest (75% / 72% respectively). Leave one out internal cross-validation was utilized to more accurately characterize the misclassification rate, while the best model will be presented, built on the entire data set. Conclusions: A physiologically focused battery of activated EEG tasks is able to probe elements of brain circuits not presently assessed with standard resting state (Eyes Open or Eyes Closed) quantitative EEG. The MindReader offers a novel alternative to rapidly, portably and non-invasively assess brain health and function. Multi-variate predictive models offer an opportunity to enhance classifier performance, although further work is required to develop the necessary activated EEG signatures to map the brain for its physiological defects.