Zandbagleh, A., Mirzakuchaki, S., Daliri, M.R., Premkumar, P., Carretié, L. and Sanei, S. ORCID: 0000-0002-3437-2801, 2022. Tensor factorization approach for ERP-based assessment of schizotypy in a novel auditory oddball task on perceived family stress. Journal of Neural Engineering. ISSN 1741-2560
|
Text
1623627_a2328_Sanei.pdf - Post-print Download (1MB) | Preview |
Abstract
Objective. Schizotypy, a potential phenotype for schizophrenia, is a personality trait that depicts psychosis-like signs in the normal range of psychosis continuum. Family communication may affect the social functioning of people with schizotypy. Greater family stress, such as irritability, criticism and less praise, is perceived at a higher level of schizotypy. This study aims to determine the differences between people with high and low levels of schizotypy using electroencephalography (EEG) during criticism, praise and neutral comments. EEGs were recorded from twenty-nine participants in the general community who varied from low schizotypy (LS) to high schizotypy (HS) during a novel emotional auditory oddball task.
Approach. We consider the difference in event-related potential (ERP) parameters, namely the amplitude and latency of P300 subcomponents (P3a and P3b), between pairs of target words (standard, positive, negative and neutral). A model based on tensor factorization is then proposed to detect these components from the EEG using the CANDECOMP/PARAFAC (CP) decomposition technique. Finally, we employ the mutual information estimation method to select influential features for classification.
Main results. The highest classification accuracy, sensitivity, and specificity of 93.1%, 94.73%, and 90% are obtained via leave-one-out cross validation.
Significance. This is the first attempt to investigate the identification of individuals with psychometrically-defined HS from brain responses that are specifically associated with perceiving family stress and schizotypy. By measuring these brain responses to social stress, we achieve the goal of improving the accuracy in detection of early episodes of psychosis.
Item Type: | Journal article | ||||||
---|---|---|---|---|---|---|---|
Publication Title: | Journal of Neural Engineering | ||||||
Creators: | Zandbagleh, A., Mirzakuchaki, S., Daliri, M.R., Premkumar, P., Carretié, L. and Sanei, S. | ||||||
Publisher: | IOP Publishing | ||||||
Date: | 28 November 2022 | ||||||
ISSN: | 1741-2560 | ||||||
Identifiers: |
|
||||||
Divisions: | Schools > School of Science and Technology | ||||||
Record created by: | Jonathan Gallacher | ||||||
Date Added: | 30 Nov 2022 09:22 | ||||||
Last Modified: | 28 Nov 2023 03:00 | ||||||
URI: | https://irep.ntu.ac.uk/id/eprint/47549 |
Actions (login required)
Edit View |
Views
Views per month over past year
Downloads
Downloads per month over past year