Dataset Information

Machine Learning Predicts Prolonged Acute Hypoxemic Respiratory Failure in Pediatric Severe Influenza.

ABSTRACT: Influenza virus is a major cause of acute hypoxemic respiratory failure. Early identification of patients who will suffer severe complications can help stratify patients for clinical trials and plan for resource use in case of pandemic. Objective:We aimed to identify which clinical variables best predict prolonged acute hypoxemic respiratory failure in influenza-infected critically ill children. Acute hypoxemic respiratory failure was defined using hypoxemia cutoffs from international consensus definitions of acute respiratory distress syndrome in patients with ventilatory support. Prolonged acute hypoxemic respiratory failure was defined by acute hypoxemic respiratory failure criteria still present at PICU day 7. Derivation Cohort:In this prospective multicenter study across 34 PICUs from November 2009 to April 2018, we included children (< 18 yr) without comorbid risk factors for severe disease. Validation Cohort:We used a Monte Carlo cross validation method with N 2 random train-test splits at a 70-30% proportion per model. Prediction Model:Using clinical data at admission (day 1) and closest to 8 am on PICU day 2, we calculated the area under the receiver operating characteristic curve using random forests machine learning algorithms and logistic regression. Results:We included 258 children (median age = 6.5 yr) and 11 (4.2%) died. By day 2, 65% (n = 165) had acute hypoxemic respiratory failure dropping to 26% (n = 67) with prolonged acute hypoxemic respiratory failure by day 7. Those with prolonged acute hypoxemic respiratory failure had a longer ICU stay (16.5 vs 4.0 d; p < 0.001) and higher mortality (13.4% vs 1.0%). A multivariable model using random forests with 10 admission and eight day 2 variables performed best (0.93 area under the receiver operating characteristic curve; 95 CI%: 0.90-0.95) where respiratory rate, Fio2, and pH on day 2 were the most important factors. Conclusions:In this prospective multicentric study, most children with influenza virus-related respiratory failure with prolonged acute hypoxemic respiratory failure can be identified early in their hospital course applying machine learning onto routine clinical data. Further validation is needed prior to bedside implementation.

SUBMITTER: Sauthier MS

PROVIDER: S-EPMC7417145 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning Predicts Prolonged Acute Hypoxemic Respiratory Failure in Pediatric Severe Influenza.

Sauthier Michaël S MS Jouvet Philippe A PA Newhams Margaret M MM Randolph Adrienne G AG

Critical care explorations 20200806 8

Influenza virus is a major cause of acute hypoxemic respiratory failure. Early identification of patients who will suffer severe complications can help stratify patients for clinical trials and plan for resource use in case of pandemic.<h4>Objective</h4>We aimed to identify which clinical variables best predict prolonged acute hypoxemic respiratory failure in influenza-infected critically ill children. Acute hypoxemic respiratory failure was defined using hypoxemia cutoffs from international con ...[more]

PMID: 32832912

Similar Datasets

Project description:ObjectivesTo characterize contemporary use of inhaled nitric oxide in pediatric acute respiratory failure and to assess relationships between clinical variables and outcomes. We sought to study the relationship of inhaled nitric oxide response to patient characteristics including right ventricular dysfunction and clinician responsiveness to improved oxygenation. We hypothesize that prompt clinician responsiveness to minimize hyperoxia would be associated with improved outcomes.DesignAn observational cohort study.SettingEight sites of the Collaborative Pediatric Critical Care Research Network.PatientsOne hundred fifty-one patients who received inhaled nitric oxide for a primary respiratory indication.Measurements and main resultsClinical data were abstracted from the medical record beginning at inhaled nitric oxide initiation and continuing until the earliest of 28 days, ICU discharge, or death. Ventilator-free days, oxygenation index, and Functional Status Scale were calculated. Echocardiographic reports were abstracted assessing for pulmonary hypertension, right ventricular dysfunction, and other cardiovascular parameters. Clinician responsiveness to improved oxygenation was determined. One hundred thirty patients (86%) who received inhaled nitric oxide had improved oxygenation by 24 hours. PICU mortality was 29.8%, while a new morbidity was identified in 19.8% of survivors. Among patients who had echocardiograms, 27.9% had evidence of pulmonary hypertension, 23.1% had right ventricular systolic dysfunction, and 22.1% had an atrial communication. Moderate or severe right ventricular dysfunction was associated with higher mortality. Clinicians responded to an improvement in oxygenation by decreasing FIO2 to less than 0.6 within 24 hours in 71% of patients. Timely clinician responsiveness to improved oxygenation with inhaled nitric oxide was associated with more ventilator-free days but not less cardiac arrests, mortality, or additional morbidity.ConclusionsClinician responsiveness to improved oxygenation was associated with less ventilator days. Algorithms to standardize ventilator management may improve signal to noise ratios in future trials enabling better assessment of the effect of inhaled nitric oxide on patient outcomes. Additionally, confining studies to more selective patient populations such as those with right ventricular dysfunction may be required.

Project description:BackgroundThere is no generalizable transcriptomics signature of pediatric acute respiratory distress syndrome. Our goal was to identify a whole blood differential gene expression signature for pediatric acute hypoxemic respiratory failure (AHRF) using transcriptomic microarrays within twenty-four hours of diagnosis. We used publicly available human whole-blood gene expression arrays of a Berlin-defined pediatric acute respiratory distress syndrome (GSE147902) cohort and a sepsis-triggered AHRF (GSE66099) cohort within twenty-four hours of diagnosis and compared those children with a PaO2/FiO2 < 200 to those with a PaO2/FiO2 ≥ 200.ResultsWe used stability selection, a bootstrapping method of 100 simulations using logistic regression as a classifier, to select differentially expressed genes associated with a PaO2/FiO2 < 200 vs. PaO2/FiO2 ≥ 200. The top-ranked genes that contributed to the AHRF signature were selected in each dataset. Genes common to both of the top 1,500 ranked gene lists were selected for pathway analysis. Pathway and network analysis was performed using the Pathway Network Analysis Visualizer (PANEV) and Reactome was used to perform an over-representation gene network analysis of the top-ranked genes common to both cohorts. Changes in metabolic pathways involved in energy balance, fundamental cellular processes such as protein translation, mitochondrial function, oxidative stress, immune signaling, and inflammation are differentially regulated early in pediatric ARDS and sepsis-induced AHRF compared to both healthy controls and to milder acute hypoxemia. Specifically, fundamental pathways related to the severity of hypoxemia emerged and included (1) ribosomal and eukaryotic initiation of factor 2 (eIF2) regulation of protein translation and (2) the nutrient, oxygen, and energy sensing pathway, mTOR, activated via PI3K/AKT signaling.ConclusionsCellular energetics and metabolic pathways are important mechanisms to consider to further our understanding of the heterogeneity and underlying pathobiology of moderate and severe pediatric acute respiratory distress syndrome. Our findings are hypothesis generating and support the study of metabolic pathways and cellular energetics to understand heterogeneity and underlying pathobiology of moderate and severe acute hypoxemic respiratory failure in children.

Dataset Information

Machine Learning Predicts Prolonged Acute Hypoxemic Respiratory Failure in Pediatric Severe Influenza.

Publications

Machine Learning Predicts Prolonged Acute Hypoxemic Respiratory Failure in Pediatric Severe Influenza.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets