Abstract
Being involved in war experiences may have severe consequences in mental health. This exposure has been associated in Colombian ex-combatants with risk of proactive aggression modulating emotional processing. However, the extent of the cognitive processes underlying aggressive behavior is still an open issue. In this work, we propose a SVM-based processing pipeline to identify different cognitive phenotypes associated with atypical emotional processing, based on canonical correlation analysis of EEG network features, and cognitive and behavioral evaluations. Results show the existence of cognitive phenotypes associated with differences in the mean value of leaf fraction and diameter of EEG networks across groups. The ability of identifying phenotypes in these otherwise healthy subjects opens up the possibility to aid in the development of specific interventions aimed to reduce expression of proactive aggression in ex-combatants and assessing the efficacy of such interventions.
Original language | English |
---|---|
Pages (from-to) | 55090-55098 |
Number of pages | 9 |
Journal | IEEE Access |
Volume | 6 |
Early online date | 14 Sep 2018 |
DOIs | |
Publication status | E-pub ahead of print - 14 Sep 2018 |
Keywords
- EEG phenotypes
- ex-combatants
- functional connectivity
- graph theory
- machine learning
- scalp EEG
- electroencephalography