UNIGE document Chapitre d'actes
previous document  unige:128625  next document
add to browser collection
Title

Multivariate and predictive modelling of neural variability in mild cognitive impairment

Authors
Meuli, Reto
Kober, Tobias
Published in 2018 International Workshop on Pattern Recognition in Neuroimaging (PRNI). Singapore - 12-14 June 2018 - IEEE. 2018
Abstract Brain signal variability has been proposed as an index of the brain's cognitive capacity. In this work, we examined neural variability by calculating the standard deviation of single trial activation estimates during memory encoding in 30 patients with mild cognitive impairment (MCI) and 31 elderly controls. We deployed a random forest (RF) classifier, using variability maps as features to distinguish MCI patients from controls, and obtained classification accuracies of up to 86%. We then used partial least squares correlation to identify variability patterns associated with task performance and compared them to the weight maps obtained with the RF classifier.
Keywords Task analysisCorrelationEncodingTrainingMatrix decompositionBrain modelingStandardsTrial-by-trial activation variabilityMemory encodingMild cognitive impairmentClassificationPartial least squares
Identifiers
ISBN: 978-1-5386-6859-7
Full text
Structures
Research groups Traitement d'images médicales (893)
Neuropsychologie et neurologie comportementale (951)
Citation
(ISO format)
KEBETS, Valeria et al. Multivariate and predictive modelling of neural variability in mild cognitive impairment. In: 2018 International Workshop on Pattern Recognition in Neuroimaging (PRNI). Singapore. [s.l.] : IEEE, 2018. doi: 10.1109/PRNI.2018.8423963 https://archive-ouverte.unige.ch/unige:128625

75 hits

0 download

Update

Deposited on : 2020-01-10

Export document
Format :
Citation style :