Brain and heart physiological networks analysis employing neural networks granger causality

Anggie D. Jaimes-Albarracin, Alvaro D. Orjuela-Canon, Andres L. Jutinico, Maria A. Bazurto, Elida Duenas

Resultado de la investigación: Capítulo en Libro/Reporte/ConferenciaContribución a la conferencia

Resumen

This paper presents the study of brain-heart interactions in pediatric patients diagnosed with obstructive sleep apnea (OSA). A comparison between pre- and post- treatment stages was treated, searching to analyze the therapy effect. For this purpose, polysomnography signals were characterized, making use of electroencephalography and electrocardiography to compute the heart rate variability. Physiological networks analysis was driven through the computation of Granger causality to find interactions among brain and heart in both directions. Also, a proposal based on artificial neural networks was employed to include a nonlinear Granger causality sense. A preprocessing was implemented, according to five spectral subbands for the brain case, associate to five rhythms, and three for the heart case. Results showed that the treatment allowed recovery of connections mainly in subsystems involving the delta and gamma subbands. Finally, a notorious difference was evidenced between the results obtained with both methods where the nonlinear analysis obtained complementary results.

Idioma originalInglés estadounidense
Título de la publicación alojada2021 10th International IEEE/EMBS Conference on Neural Engineering, NER 2021
EditorialIEEE Computer Society
Páginas469-472
Número de páginas4
ISBN (versión digital)9781728143378
DOI
EstadoPublicada - may 4 2021
Evento10th International IEEE/EMBS Conference on Neural Engineering, NER 2021 - Virtual, Online, Italia
Duración: may 4 2021may 6 2021

Serie de la publicación

NombreInternational IEEE/EMBS Conference on Neural Engineering, NER
Volumen2021-May
ISSN (versión impresa)1948-3546
ISSN (versión digital)1948-3554

Conferencia

Conferencia10th International IEEE/EMBS Conference on Neural Engineering, NER 2021
País/TerritorioItalia
CiudadVirtual, Online
Período5/4/215/6/21

All Science Journal Classification (ASJC) codes

  • Inteligencia artificial
  • Ingeniería mecánica

Citar esto