A machine-learning regional clustering approach to understand ventilator-induced lung injury: a proof-of-concept experimental study

Simple item page
dc.article.number60
dc.contributor.authorCruces, Pablo
dc.contributor.authorRetamal, Jaime
dc.contributor.authorDamián, Andrés
dc.contributor.authorLago, Graciela
dc.contributor.authorBlasina, Fernanda
dc.contributor.authorOviedo, Vanessa
dc.contributor.authorMedina, Tania
dc.contributor.authorPérez, Agustín
dc.contributor.authorVaamonde, Lucía
dc.contributor.authorDapueto, Rosina
dc.contributor.authorGonzález-Dambrauskas, Sebastian
dc.contributor.authorSerra, Alberto
dc.contributor.authorMonteverde-Fernandez, Nicolas
dc.contributor.authorNamías, Mauro
dc.contributor.authorMartínez, Javier
dc.contributor.authorHurtado, Daniel E.
dc.date.accessioned2024-07-22T21:10:34Z
dc.date.available2024-07-22T21:10:34Z
dc.date.issued2024
dc.date.updated2024-07-07T00:06:05Z
dc.description.abstractBackground The spatiotemporal progression and patterns of tissue deformation in ventilator-induced lung injury (VILI) remain understudied. Our aim was to identify lung clusters based on their regional mechanical behavior over space and time in lungs subjected to VILI using machine-learning techniques. Results Ten anesthetized pigs (27±2 kg) were studied. Eight subjects were analyzed. End-inspiratory and endexpiratory lung computed tomography scans were performed at the beginning and after 12 h of one-hit VILI model. Regional image-based biomechanical analysis was used to determine end-expiratory aeration, tidal recruitment, and volumetric strain for both early and late stages. Clustering analysis was performed using principal component analysis and K-Means algorithms. We identifed three diferent clusters of lung tissue: Stable, Recruitable Unstable, and Non-Recruitable Unstable. End-expiratory aeration, tidal recruitment, and volumetric strain were signifcantly diferent between clusters at early stage. At late stage, we found a step loss of end-expiratory aeration among clusters, lowest in Stable, followed by Unstable Recruitable, and highest in the Unstable Non-Recruitable cluster. Volumetric strain remaining unchanged in the Stable cluster, with slight increases in the Recruitable cluster, and strong reduction in the Unstable Non-Recruitable cluster. Conclusions VILI is a regional and dynamic phenomenon. Using unbiased machine-learning techniques we can identify the coexistence of three functional lung tissue compartments with diferent spatiotemporal regional biomechanical behavior.
dc.format.extent9 páginas
dc.fuente.origenBiomed Central
dc.identifier.citationIntensive Care Medicine Experimental. 2024 Jul 02;12(1):60
dc.identifier.doi10.1186/s40635-024-00641-8
dc.identifier.eissn2197-425X
dc.identifier.urihttps://doi.org/10.1186/s40635-024-00641-8
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/87206
dc.identifier.wosidWOS:001261417600002
dc.information.autorucEscuela de Medicina; Retamal, Jaime; 0000-0002-6817-3659; 175147
dc.information.autorucEscuela de Medicina; Oviedo, Vanessa; S/I; 1009275
dc.information.autorucEscuela de Ingeniería; Pérez, Agustín; S/I; 1073148
dc.information.autorucEscuela de Ingeniería; Hurtado, Daniel E.; 0000-0001-6261-9106; 3569
dc.language.isoen
dc.nota.accesocontenido completo
dc.revistaIntensive Care Medicine Experimental
dc.rightsacceso abierto
dc.rights.holderThe Author(s)
dc.rights.licenseCC BY 4.0 ATTRIBUTION 4.0 INTERNATIONAL
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectMechanical ventilation
dc.subjectVentilator-induced lung injury
dc.subjectLung strain
dc.subjectComputed tomography
dc.subjectDiagnostic imaging
dc.subject.ddc610
dc.subject.deweyMedicina y saludes_ES
dc.subject.ods03 Good health and well-being
dc.subject.odspa03 Salud y bienestar
dc.titleA machine-learning regional clustering approach to understand ventilator-induced lung injury: a proof-of-concept experimental study
dc.typeartículo
dc.volumen12
sipa.codpersvinculados175147
sipa.codpersvinculados1009275
sipa.codpersvinculados1073148
sipa.codpersvinculados3569
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
40635_2024_Article_641.pdf
Size:
1.73 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.98 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Artículos de revistas