Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approach

Autores
Sanz García, Ancor; Pérez Romero, Miriam; Pastor, Jesús; Sola, Rafael G.; Vega Zelaya, Lorena; Vega, Gema; Monasterio, Fernando; Torrecilla, Carmen; Pulido, Paloma; Ortega, Guillermo José
Año de publicación
2019
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Objective. Sedation of neurocritically ill patients is one of the most challenging situation in ICUs. Quantitative knowledge on the sedation effect on brain activity in that complex scenario could help to uncover new markers for sedation assessment. Hence, we aim to evaluate the existence of changes of diverse EEG-derived measures in deeply-sedated (RASS-Richmond agitation-sedation scale -4 and -5) neurocritically ill patients, and also whether sedation doses are related with those eventual changes. Approach. We performed an observational prospective cohort study in the intensive care unit of the Hospital de la Princesa. Twenty-six adult patients suffered from traumatic brain injury and subarachnoid hemorrhage were included in the present study. Long-term continuous electroencephalographic (EEG) recordings (2141 h) and hourly annotated information were used to determine the relationship between intravenous sedation infusion doses and network and spectral EEG measures. To do that, two different strategies were followed: assessment of the statistical dependence between both variables using the Spearman correlation rank and by performing an automatic classification method based on a machine learning algorithm. Main results. More than 60% of patients presented a correlation greater than 0.5 in at least one of the calculated EEG measures with the sedation dose. The automatic classification method presented an accuracy of 84.3% in discriminating between different sedation doses. In both cases the nodes' degree was the most relevant measurement. Significance. The results presented here provide evidences of brain activity changes during deep sedation linked to sedation doses. Particularly, the capability of network EEG-derived measures in discriminating between different sedation doses could be the framework for the development of accurate methods for sedation levels assessment.
Fil: Sanz García, Ancor. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Pérez Romero, Miriam. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Pastor, Jesús. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Sola, Rafael G.. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa. Servicio de Neurocirugia. Grupo de Epilepsia; España
Fil: Vega Zelaya, Lorena. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Vega, Gema. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Monasterio, Fernando. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Torrecilla, Carmen. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Pulido, Paloma. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa. Servicio de Neurocirugia. Grupo de Epilepsia; España
Fil: Ortega, Guillermo José. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Materia
BRAIN NETWORKS
EEG
ICU
MACHINE LEARNING
SEDATION
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/122820
Acceder
id CONICETDig_4ea89ff333e2157416d0b90cb7e2a796
oai_identifier_str oai:ri.conicet.gov.ar:11336/122820
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approachSanz García, AncorPérez Romero, MiriamPastor, JesúsSola, Rafael G.Vega Zelaya, LorenaVega, GemaMonasterio, FernandoTorrecilla, CarmenPulido, PalomaOrtega, Guillermo JoséBRAIN NETWORKSEEGICUMACHINE LEARNINGSEDATIONhttps://purl.org/becyt/ford/2.6https://purl.org/becyt/ford/2Objective. Sedation of neurocritically ill patients is one of the most challenging situation in ICUs. Quantitative knowledge on the sedation effect on brain activity in that complex scenario could help to uncover new markers for sedation assessment. Hence, we aim to evaluate the existence of changes of diverse EEG-derived measures in deeply-sedated (RASS-Richmond agitation-sedation scale -4 and -5) neurocritically ill patients, and also whether sedation doses are related with those eventual changes. Approach. We performed an observational prospective cohort study in the intensive care unit of the Hospital de la Princesa. Twenty-six adult patients suffered from traumatic brain injury and subarachnoid hemorrhage were included in the present study. Long-term continuous electroencephalographic (EEG) recordings (2141 h) and hourly annotated information were used to determine the relationship between intravenous sedation infusion doses and network and spectral EEG measures. To do that, two different strategies were followed: assessment of the statistical dependence between both variables using the Spearman correlation rank and by performing an automatic classification method based on a machine learning algorithm. Main results. More than 60% of patients presented a correlation greater than 0.5 in at least one of the calculated EEG measures with the sedation dose. The automatic classification method presented an accuracy of 84.3% in discriminating between different sedation doses. In both cases the nodes' degree was the most relevant measurement. Significance. The results presented here provide evidences of brain activity changes during deep sedation linked to sedation doses. Particularly, the capability of network EEG-derived measures in discriminating between different sedation doses could be the framework for the development of accurate methods for sedation levels assessment.Fil: Sanz García, Ancor. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; EspañaFil: Pérez Romero, Miriam. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; EspañaFil: Pastor, Jesús. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; EspañaFil: Sola, Rafael G.. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa. Servicio de Neurocirugia. Grupo de Epilepsia; EspañaFil: Vega Zelaya, Lorena. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; EspañaFil: Vega, Gema. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; EspañaFil: Monasterio, Fernando. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; EspañaFil: Torrecilla, Carmen. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; EspañaFil: Pulido, Paloma. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa. Servicio de Neurocirugia. Grupo de Epilepsia; EspañaFil: Ortega, Guillermo José. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaIOP Publishing2019-04info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/122820Sanz García, Ancor; Pérez Romero, Miriam; Pastor, Jesús; Sola, Rafael G.; Vega Zelaya, Lorena; et al.; Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approach; IOP Publishing; Journal of Neural Engineering; 16; 2; 4-2019; 1-111741-2560CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://iopscience.iop.org/article/10.1088/1741-2552/ab039f/datainfo:eu-repo/semantics/altIdentifier/doi/10.1088/1741-2552/ab039finfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:42:45Zoai:ri.conicet.gov.ar:11336/122820instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:42:45.868CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approach
title Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approach
spellingShingle Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approach
Sanz García, Ancor
BRAIN NETWORKS
EEG
ICU
MACHINE LEARNING
SEDATION
title_short Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approach
title_full Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approach
title_fullStr Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approach
title_full_unstemmed Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approach
title_sort Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approach
dc.creator.none.fl_str_mv Sanz García, Ancor
Pérez Romero, Miriam
Pastor, Jesús
Sola, Rafael G.
Vega Zelaya, Lorena
Vega, Gema
Monasterio, Fernando
Torrecilla, Carmen
Pulido, Paloma
Ortega, Guillermo José
author Sanz García, Ancor
author_facet Sanz García, Ancor
Pérez Romero, Miriam
Pastor, Jesús
Sola, Rafael G.
Vega Zelaya, Lorena
Vega, Gema
Monasterio, Fernando
Torrecilla, Carmen
Pulido, Paloma
Ortega, Guillermo José
author_role author
author2 Pérez Romero, Miriam
Pastor, Jesús
Sola, Rafael G.
Vega Zelaya, Lorena
Vega, Gema
Monasterio, Fernando
Torrecilla, Carmen
Pulido, Paloma
Ortega, Guillermo José
author2_role author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv BRAIN NETWORKS
EEG
ICU
MACHINE LEARNING
SEDATION
topic BRAIN NETWORKS
EEG
ICU
MACHINE LEARNING
SEDATION
purl_subject.fl_str_mv https://purl.org/becyt/ford/2.6
https://purl.org/becyt/ford/2
dc.description.none.fl_txt_mv Objective. Sedation of neurocritically ill patients is one of the most challenging situation in ICUs. Quantitative knowledge on the sedation effect on brain activity in that complex scenario could help to uncover new markers for sedation assessment. Hence, we aim to evaluate the existence of changes of diverse EEG-derived measures in deeply-sedated (RASS-Richmond agitation-sedation scale -4 and -5) neurocritically ill patients, and also whether sedation doses are related with those eventual changes. Approach. We performed an observational prospective cohort study in the intensive care unit of the Hospital de la Princesa. Twenty-six adult patients suffered from traumatic brain injury and subarachnoid hemorrhage were included in the present study. Long-term continuous electroencephalographic (EEG) recordings (2141 h) and hourly annotated information were used to determine the relationship between intravenous sedation infusion doses and network and spectral EEG measures. To do that, two different strategies were followed: assessment of the statistical dependence between both variables using the Spearman correlation rank and by performing an automatic classification method based on a machine learning algorithm. Main results. More than 60% of patients presented a correlation greater than 0.5 in at least one of the calculated EEG measures with the sedation dose. The automatic classification method presented an accuracy of 84.3% in discriminating between different sedation doses. In both cases the nodes' degree was the most relevant measurement. Significance. The results presented here provide evidences of brain activity changes during deep sedation linked to sedation doses. Particularly, the capability of network EEG-derived measures in discriminating between different sedation doses could be the framework for the development of accurate methods for sedation levels assessment.
Fil: Sanz García, Ancor. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Pérez Romero, Miriam. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Pastor, Jesús. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Sola, Rafael G.. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa. Servicio de Neurocirugia. Grupo de Epilepsia; España
Fil: Vega Zelaya, Lorena. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Vega, Gema. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Monasterio, Fernando. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Torrecilla, Carmen. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España
Fil: Pulido, Paloma. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa. Servicio de Neurocirugia. Grupo de Epilepsia; España
Fil: Ortega, Guillermo José. Universidad Autonoma de Madrid. Hospital Universitario de la Princesa; España. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
description Objective. Sedation of neurocritically ill patients is one of the most challenging situation in ICUs. Quantitative knowledge on the sedation effect on brain activity in that complex scenario could help to uncover new markers for sedation assessment. Hence, we aim to evaluate the existence of changes of diverse EEG-derived measures in deeply-sedated (RASS-Richmond agitation-sedation scale -4 and -5) neurocritically ill patients, and also whether sedation doses are related with those eventual changes. Approach. We performed an observational prospective cohort study in the intensive care unit of the Hospital de la Princesa. Twenty-six adult patients suffered from traumatic brain injury and subarachnoid hemorrhage were included in the present study. Long-term continuous electroencephalographic (EEG) recordings (2141 h) and hourly annotated information were used to determine the relationship between intravenous sedation infusion doses and network and spectral EEG measures. To do that, two different strategies were followed: assessment of the statistical dependence between both variables using the Spearman correlation rank and by performing an automatic classification method based on a machine learning algorithm. Main results. More than 60% of patients presented a correlation greater than 0.5 in at least one of the calculated EEG measures with the sedation dose. The automatic classification method presented an accuracy of 84.3% in discriminating between different sedation doses. In both cases the nodes' degree was the most relevant measurement. Significance. The results presented here provide evidences of brain activity changes during deep sedation linked to sedation doses. Particularly, the capability of network EEG-derived measures in discriminating between different sedation doses could be the framework for the development of accurate methods for sedation levels assessment.
publishDate 2019
dc.date.none.fl_str_mv 2019-04
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/122820
Sanz García, Ancor; Pérez Romero, Miriam; Pastor, Jesús; Sola, Rafael G.; Vega Zelaya, Lorena; et al.; Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approach; IOP Publishing; Journal of Neural Engineering; 16; 2; 4-2019; 1-11
1741-2560
CONICET Digital
CONICET
url http://hdl.handle.net/11336/122820
identifier_str_mv Sanz García, Ancor; Pérez Romero, Miriam; Pastor, Jesús; Sola, Rafael G.; Vega Zelaya, Lorena; et al.; Potential EEG biomarkers of sedation doses in intensive care patients unveiled by using a machine learning approach; IOP Publishing; Journal of Neural Engineering; 16; 2; 4-2019; 1-11
1741-2560
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://iopscience.iop.org/article/10.1088/1741-2552/ab039f/data
info:eu-repo/semantics/altIdentifier/doi/10.1088/1741-2552/ab039f
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv IOP Publishing
publisher.none.fl_str_mv IOP Publishing
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844614461180084224
score 13.070432

Publicaciones similares