Phenotyping Ex-Combatants From EEG Scalp Connectivity

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 paper, we propose a support vector machine-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.

• Autores: Quintero Zea, Andrés; López Hincapié, Jose David; Smith, Keith; Trujillo Orrego, Natalia; Parra Rodríguez, Mario Alfredo; Escudero Ordoñez, Javier Antonio
• Tipo de recurso: Article of investigation
• Fecha de publicación: 2018
• Institución: Universidad de Antioquia
• Repositorio: Repositorio UdeA
• Idioma: eng
• OAI Identifier: oai:bibliotecadigital.udea.edu.co:10495/37293
• Acceso en línea: https://hdl.handle.net/10495/37293
• Palabra clave: Electroencefalografía; Electroencephalography; Fenotipo; Phenotype; Aprendizaje Automático; Machine Learning; Teoría de grafos; Graph theory; Cuero cabelludo; Scalp; Ex-combatants; Excombatientes
• Rights: openAccess
• License: http://creativecommons.org/licenses/by-nc-nd/2.5/co/