Session Information
Date: Sunday, October 7, 2018
Session Title: Huntington's Disease
Session Time: 1:45pm-3:15pm
Location: Hall 3FG
Objective: To construct an automatic classifier distinguishing healthy controls from Huntington’s disease (HD) gene carriers using quantitative electroencephalography (qEEG) and to derive qEEG features that correlate specifically with commonly used clinical and cognitive markers in HD research. This is done with the aim of assessing biomarker potential.
Background: Establishing markers for measuring disease progression in HD is needed, both before and after disease manifestation. Assessing the efficacy of any proposed therapy aimed at slowing down or halting disease progression as early as possible depends on having reliable disease measures. Through registration of physiologic activity of neurons, qEEG may provide a quantification method for possible (sub)cortical dysfunction occurring prior to or concomitant with motor or cognitive disturbances observed in HD.
Methods: Twenty-six HD gene carriers (49.7 ± 8.5 years) and 25 healthy controls (52.7 ± 8.7 years) were recruited. EEG was recorded using 19 electrodes for three minutes with subjects at rest. An EEG index was created by applying statistical pattern recognition to a large set of EEG features, which was subsequently tested using 10-fold cross-validation. The index resulted in a continuous variable ranging from 0 to 1, where a low value indicates a subject with electrophysiological behavior consistent with that expected in a control subject, while a high value being consistent with that expected in an HD subject. qEEG features that correlate specifically with commonly used clinical and cognitive markers in HD research were derived. Spectral power analyses were performed.
Results: A classification index was created with a specificity = 83%, sensitivity = 83% and accuracy = 83%, with an area under the curve = 0.9. qEEG analysis on subsets of electrophysiological features resulted in two highly significant correlations with cognitive and clinical scores. Finally, significant differences were found in spectral power analysis.
Conclusions: These results suggest that qEEG related modalities can serve as biomarkers in HD. The indices correlating with modalities changing with the progression of the disease may lead to tools based on qEEG that can help monitor efficacy in intervention studies.
To cite this abstract in AMA style:
O. Odish, K. Johnsen, P. van Someren, R. Roos, G. van Dijk. Assessing the potential of EEG as a biomarker in Huntington’s disease using machine learning automatic classification [abstract]. Mov Disord. 2018; 33 (suppl 2). https://www.mdsabstracts.org/abstract/assessing-the-potential-of-eeg-as-a-biomarker-in-huntingtons-disease-using-machine-learning-automatic-classification/. Accessed December 1, 2024.« Back to 2018 International Congress
MDS Abstracts - https://www.mdsabstracts.org/abstract/assessing-the-potential-of-eeg-as-a-biomarker-in-huntingtons-disease-using-machine-learning-automatic-classification/