CRIS

Permanent URI for this communityhttps://investigadores.udd.cl/handle/123456789/1

Browse

Search Results

Now showing 1 - 7 of 7

Some of the metrics are blocked by your
consent settings
Machine learning-based identification of efficient and restrictive physiological subphenotypes in acute respiratory distress syndrome
(Springer Science and Business Media LLC, 2025-03-01)
Gabriela Meza-Fuentes
;
DELGADO BECERRA, OROZIMBA IRIS
;
Mario Barbé
;
Ignacio Sánchez
;
RETAMAL LUCERO, MAURICIO ANTONIO
Acute respiratory distress syndrome (ARDS) is a severe condition with high morbidity and mortality, characterized by significant clinical heterogeneity. This heterogeneity complicates treatment selection and patient inclusion in clinical trials. Therefore, the objective of this study is to identify physiological subphenotypes of ARDS using machine learning, and to determine ventilatory variables that can effectively discriminate between these subphenotypes in a bedside setting with high performance, highlighting potential utility for future clinical stratification approaches.</jats:p> Methodology A retrospective cohort study was conducted using data from our ICU, covering admissions from 2017 to 2021. The study included 224 patients over 18 years of age diagnosed with ARDS according to the Berlin criteria and undergoing invasive mechanical ventilation (IMV). Data on physiological and ventilatory variables were collected during the first 24 h IMV. We applied machine learning techniques to categorize subphenotypes in ARDS patients. Initially, we employed the unsupervised Gaussian Mixture Classification Model approach to group patients into subphenotypes. Subsequently, we applied supervised models such as XGBoost to perform root cause analysis, evaluate the classification of patients into these subgroups, and measure their performance.</jats:p> </jats:sec> <jats:sec> <jats:title>Results</jats:title> <jats:p>Our models identified two ARDS subphenotypes with significant clinical differences and significant outcomes. Subphenotype Efficient (<jats:italic>n</jats:italic> = 172) was characterized by lower mortality, lower clinical severity and presented a less restrictive pattern with better gas exchange compared to Subphenotype Restrictive (<jats:italic>n</jats:italic> = 52), which showed the opposite. The models demonstrated high performance with an area under the ROC curve of 0.94, sensitivity of 94.2% and specificity of 87.5%, in addition to an F1 score of 0.85. The most influential variables in the discrimination of subphenotypes were distension pressure, respiratory frequency and exhaled carbon dioxide volume.Conclusion This study presents an approach to improve subphenotype categorization in ARDS. The generation of clustering and prediction models by machine learning involving clinical, ventilatory mechanics, and gas exchange variables allowed for more accurate stratification of patients. These findings have the potential to optimize individualized treatment selection and improve clinical outcomes in patients with ARDS.</jats:p> Graphical Abstract
Scopus© Citations 2 5
Some of the metrics are blocked by your
consent settings
Neonatal Mesenchymal Stem Cell Treatment Improves Myelination Impaired by Global Perinatal Asphyxia in Rats
(2021)
Andrea Tapia-Bustos
;
Carolyne Lespay-Rebolledo
;
Valentina Vío
;
Ronald Pérez-Lobos
;
Emmanuel Casanova-Ortiz
<jats:p>The effect of perinatal asphyxia (PA) on oligodendrocyte (OL), neuroinflammation, and cell viability was evaluated in telencephalon of rats at postnatal day (P)1, 7, and 14, a period characterized by a spur of neuronal networking, evaluating the effect of mesenchymal stem cell (MSCs)-treatment. The issue was investigated with a rat model of global PA, mimicking a clinical risk occurring under labor. PA was induced by immersing fetus-containing uterine horns into a water bath for 21 min (AS), using sibling-caesarean-delivered fetuses (CS) as controls. Two hours after delivery, AS and CS neonates were injected with either 5 μL of vehicle (10% plasma) or 5 × 104 MSCs into the lateral ventricle. Samples were assayed for myelin-basic protein (MBP) levels; Olig-1/Olig-2 transcriptional factors; Gglial phenotype; neuroinflammation, and delayed cell death. The main effects were observed at P7, including: (i) A decrease of MBP-immunoreactivity in external capsule, corpus callosum, cingulum, but not in fimbriae of hippocampus; (ii) an increase of Olig-1-mRNA levels; (iii) an increase of IL-6-mRNA, but not in protein levels; (iv) an increase in cell death, including OLs; and (v) MSCs treatment prevented the effect of PA on myelination, OLs number, and cell death. The present findings show that PA induces regional- and developmental-dependent changes on myelination and OLs maturation. Neonatal MSCs treatment improves survival of mature OLs and myelination in telencephalic white matter.</jats:p>
Scopus© Citations 7 2
Some of the metrics are blocked by your
consent settings
Tumor-like presentation of herpetic cervicitis: A case report
(2023)
Pablo Boldrini L.
;
Gabriel Vallejos P.
;
Polentze Ballesteros P.
;
Gonzalo Valenzuela L.
;
Enrique Roncone D.
2Scopus© Citations 1
Some of the metrics are blocked by your
consent settings
Mechanical power in pediatric acute respiratory distress syndrome: a PARDIE study
(2022)
Anoopindar K. Bhalla
;
Margaret J. Klein
;
Vicent Modesto I Alapont
;
Guillaume Emeriaud
;
Martin C. J. Kneyber
<jats:title>Abstract</jats:title><jats:sec> <jats:title>Background</jats:title> <jats:p>Mechanical power is a composite variable for energy transmitted to the respiratory system over time that may better capture risk for ventilator-induced lung injury than individual ventilator management components. We sought to evaluate if mechanical ventilation management with a high mechanical power is associated with fewer ventilator-free days (VFD) in children with pediatric acute respiratory distress syndrome (PARDS).</jats:p> </jats:sec><jats:sec> <jats:title>Methods</jats:title> <jats:p>Retrospective analysis of a prospective observational international cohort study.</jats:p> </jats:sec><jats:sec> <jats:title>Results</jats:title> <jats:p>There were 306 children from 55 pediatric intensive care units included. High mechanical power was associated with younger age, higher oxygenation index, a comorbid condition of bronchopulmonary dysplasia, higher tidal volume, higher delta pressure (peak inspiratory pressure—positive end-expiratory pressure), and higher respiratory rate. Higher mechanical power was associated with fewer 28-day VFD after controlling for confounding variables (per 0.1 J·min<jats:sup>−1</jats:sup>·Kg<jats:sup>−1</jats:sup> Subdistribution Hazard Ratio (SHR) 0.93 (0.87, 0.98), <jats:italic>p</jats:italic> = 0.013). Higher mechanical power was not associated with higher intensive care unit mortality in multivariable analysis in the entire cohort (per 0.1 J·min<jats:sup>−1</jats:sup>·Kg<jats:sup>−1</jats:sup> OR 1.12 [0.94, 1.32], <jats:italic>p</jats:italic> = 0.20). But was associated with higher mortality when excluding children who died due to neurologic reasons (per 0.1 J·min<jats:sup>−1</jats:sup>·Kg<jats:sup>−1</jats:sup> OR 1.22 [1.01, 1.46], <jats:italic>p</jats:italic> = 0.036). In subgroup analyses by age, the association between higher mechanical power and fewer 28-day VFD remained only in children < 2-years-old (per 0.1 J·min<jats:sup>−1</jats:sup>·Kg<jats:sup>−1</jats:sup> SHR 0.89 (0.82, 0.96), <jats:italic>p</jats:italic> = 0.005). Younger children were managed with lower tidal volume, higher delta pressure, higher respiratory rate, lower positive end-expiratory pressure, and higher PCO<jats:sub>2</jats:sub> than older children. No individual ventilator management component mediated the effect of mechanical power on 28-day VFD.</jats:p> </jats:sec><jats:sec> <jats:title>Conclusions</jats:title> <jats:p>Higher mechanical power is associated with fewer 28-day VFDs in children with PARDS. This association is strongest in children < 2-years-old in whom there are notable differences in mechanical ventilation management. While further validation is needed, these data highlight that ventilator management is associated with outcome in children with PARDS, and there may be subgroups of children with higher potential benefit from strategies to improve lung-protective ventilation.</jats:p> <jats:p><jats:bold>Take Home Message</jats:bold>: Higher mechanical power is associated with fewer 28-day ventilator-free days in children with pediatric acute respiratory distress syndrome. This association is strongest in children <2-years-old in whom there are notable differences in mechanical ventilation management.</jats:p> </jats:sec>
7Scopus© Citations 23
Some of the metrics are blocked by your
consent settings
Targeted high volume hemofiltration could avoid extracorporeal membrane oxygenation in some patients with severe Hantavirus cardiopulmonary syndrome
(2021)
LOPEZ HERNANDEZ, RENE RAMON
;
Rodrigo Pérez‐Araos
;
Álvaro Salazar
;
Mauricio Espinoza
;
Analia Cuiza
Scopus© Citations 10 1
Some of the metrics are blocked by your
consent settings
High Flow Nasal Cannula as Support in Immunocompromised Patients with Acute Respiratory Failure: A Retrospective Study
(2021)
Claudia Giugliano-Jaramillo
;
Josefina León
;
Cristobal Enriquez
;
Juan E. Keymer
;
Rodrigo Pérez-Araos
<jats:sec> <jats:title>Introduction:</jats:title> <jats:p>High Flow Nasal Cannula (HFNC) is a novel technique for respiratory support that improves oxygenation. In some patients, it may reduce the work of breathing. In immunocompromised patients with Acute Respiratory Failure (ARF), Non-Invasive Ventilation (NIV) is the main support recommended strategy, since invasive mechanical ventilation could increase mortality rates. NIV used for more than 48 hours may be associated with increased in-hospital mortality and hospital length of stay. Therefore HFNC seems like a respiratory support alternative.</jats:p> </jats:sec> <jats:sec> <jats:title>Objective:</jats:title> <jats:p>To describe clinical outcomes of immunocompromised patients with ARF HFNC-supported.</jats:p> </jats:sec> <jats:sec> <jats:title>Methods:</jats:title> <jats:p>Retrospective study in patients admitted with ARF and HFNC-supported. 25 adult patients were included, 21 pharmacologically and 4 non- pharmacologically immunosuppressed. Median age of the patients was 64 [60-76] years, APACHE II 15 [11-19], and PaO2:FiO2 218 [165-248]. Demographic information, origin of immunosuppression, Respiratory Rate (RR), Heart Rate (HR), Mean Arterial Pressure (MAP), oxygen saturation (SpO<jats:sub>2</jats:sub>) and PaO<jats:sub>2</jats:sub>:FiO<jats:sub>2</jats:sub> ratio were extracted from clinical records of our HFNC local protocol. Data acquisition was performed before and after the first 24 hours of connection. In addition, the need for greater ventilatory support after HFNC, orotracheal intubation, in-hospital mortality and 90 days out-patients’ mortality was recorded.</jats:p> </jats:sec> <jats:sec> <jats:title>Results:</jats:title> <jats:p>Mean RR before the connection was 25±22 breaths/min and 22±4 breaths/min after the first 24 hours of HFNC use (95% CI; p=0.02). HR mean before connection to HFNC was 96±22 beats/min, and after, it was 86±15 beats/min (95%CI; p=0.008). Previous mean MAP was 86±15 mmHg, and after HFNC, it was 80±12 mmHg (95%CI; p=0.09); mean SpO<jats:sub>2</jats:sub> after was 93±5% and before it was 95±4% (95% CI; p=0.13); and previous PaO<jats:sub>2</jats:sub>:FiO<jats:sub>2</jats:sub> mean was 219±66, and after it was 324±110 (95%CI; p=0.52). In-hospital mortality was 28% and 90 days out-patients’ mortality was 32%.</jats:p> </jats:sec> <jats:sec> <jats:title>Conclusion:</jats:title> <jats:p>HFNC in immunosuppressed ARF subjects significantly decreases HR and RR, being apparently an effective alternative to decrease work of breathing. In-hospital mortality in ARF immunosuppressed patients was high even though respiratory support was used. Better studies are needed to define the role of HFNC-support in ARF.</jats:p> </jats:sec>
11
Some of the metrics are blocked by your
consent settings
Near-Apneic Ventilation Decreases Lung Injury and Fibroproliferation in an ARDS Model with ECMO
(2019)
Joaquin Araos
;
Leyla Alegria
;
Patricio Garcia
;
Pablo Cruces
;
Dagoberto Soto
13Scopus© Citations 96

CRIS

Browse

Filters

Settings

Sort By

Results per page

Search Results