Back

Statistical Evaluation of the Test Threshold for the Alzheimer's Disease EEG Coherence Marker

Radinski, C.; Perez, G.

2022-09-09 neurology
10.1101/2022.09.07.22279698 medRxiv
Show abstract

A progressive reduction in synaptic connections between neurons is one neurophysiological indicator of brain ageing and was linked to the severity of dementia. In our study, we hypothesized that if synaptic disconnection as the neuropathology of Alzheimers disease (AD) is responsible for the brains inability to integrate diverse regions into efficient networks, then electroencephalographic data may be utilized to identify Alzheimers dementia. The study explored EEG coherence, reflecting connectivity between regions, as a potential AD indicator and identified four promising EEG coherence markers. As the pattern of degeneration follows the temporal-parietal-frontal axis, the temporal gamma marker was chosen for further evaluation. We utilize conventional analysis, producing paired results such as sensitivity and specificity and the receiver operating characteristic (ROC) curve to evaluate the accuracy of the temporal gamma marker. The optimal cut-off point of 0.950 was confirmed by both methods and provided 95% correct classification indicating an almost perfect differentiation between control and impaired cognitive status. This evaluation will be used in a blinded diagnostic test accuracy study to determine the TG_marker validity in detecting AD and excluding pseudo-dementias.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.