Search

Pao 2 is the gold standard to assess acute hypoxic respiratory failure, but it is only routinely available by intermittent spot checks, precluding any automatic continuous analysis for bedside tools., Objective: To validate a continuous and noninvasive method to estimate hypoxemia severity for all Spo 2 values., Derivation Cohort: All patients who had an arterial blood gas and simultaneous continuous noninvasive monitoring from 2011 to 2019 at Boston Children's Hospital (Boston, MA) PICU., Validation Cohort: External cohort at Sainte-Justine Hospital PICU (Montreal, QC, Canada) from 2017 to 2020., Prediction Model: We estimated the Pao 2 using three kinds of neural networks and an empirically optimized mathematical model derived from known physiologic equations., Results: We included 52,879 Pao 2 (3,252 patients) in the derivation dataset and 12,047 Pao 2 (926 patients) in the validation dataset. The mean function on the last minute before the arterial blood gas had the lowest bias (bias -0.1% validation cohort). A difference greater than or equal to 3% between pulse rate and electrical heart rate decreased the intraclass correlation coefficients (0.75 vs 0.44; p < 0.001) implying measurement noise. Our estimated Pao 2 equation had the highest intraclass correlation coefficient (0.38; 95% CI, 0.36-0.39; validation cohort) and outperformed neural networks and existing equations. Using the estimated Pao 2 to estimate the oxygenation index showed a significantly better hypoxemia classification (kappa) than oxygenation saturation index for both Spo 2 less than or equal to 97% (0.79 vs 0.60; p < 0.001) and Spo 2 greater than 97% (0.58 vs 0.52; p < 0.001)., Conclusion: The estimated Pao 2 using pulse rate and electrical heart rate Spo 2 validation allows a continuous and noninvasive estimation of the oxygenation index that is valid for Spo 2 less than or equal to 97% and for Spo 2 greater than 97%. Display of continuous analysis of estimated Pao 2 and estimated oxygenation index may provide decision support to assist with hypoxemia diagnosis and oxygen titration in critically ill patients., Competing Interests: Dr. Sauthier received funding from “Fonds de recherche du Québec en Santé” and the Université de Montréal (Faculty of Medicine), National Institutes of Health (R01AI084011 to Dr. Randolph), and the Centers for Disease Control and Prevention (to Dr. Randolph). Dr. Jouvet received funding from “Institut de Valorisation des données” for the development and analysis of the database at Sainte-Justine Hospital. The remaining authors have disclosed that they do not have any potential conflicts of interest., (Copyright © 2021 The Authors. Published by Wolters Kluwer Health, Inc. on behalf of the Society of Critical Care Medicine.)

Introduction: Chest physiotherapy (CPT) and intrathoracic percussion ventilation have been recognised as to encourage dislodging the secretions; nonetheless, the tolerance to the procedure and its efficiency have not been proven to be sufficient., Method and Analyses: This study aims to examine the tolerance, feasibility and physiological effects in airway clearance by using a novel extrathoracic non-invasive oscillating transducer device (NIOD) in critically ill children. A two-stage cross-over randomised controlled study in a paediatric intensive care unit in a Canadian Academic Children's Hospital will be applied. Children under 24 months old, for whom CPT is prescribed for airway clearance, will be included. The study consists of two stages; (1) Stage 1 'Frequency Level': we will apply two different frequencies of the NIOD (40 Hz vs 60 Hz) for 12 min each, on each patient 3 hours apart, and (2) Stage 2 'NIOD versus CPT': we will implement NIOD and CPT alternatingly for 3 hours apart. The order of the procedures will be randomly allocated for each case. We will compare the average Δchanges of tidal lung volume measured by a 3D imaging system and regional lung functions using electrical impedance tomography, between the two different frequencies and between the NIOD periods and the CPT periods. We will also examine tolerance by seeing COMFORT Scales and related complications during the procedures. We estimate necessary sample size as 6 for each arm (Total 12 cases) for stage 1 and 48 cases for Stage 2, with power of 0.8 and alpha of 0.05., Ethics and Dissemination: This study has been approved by the Health Research Ethics Board of University of Montreal, Canada (REB number: 2020-2471). We will disseminate our findings through peer-reviewed publications and conference presentations in paediatric or/and critical care fields., Trial Registration Number: ClinicalTrials.gov Registry (NCT03821389)., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2020. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

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, Fio 2 , 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., Competing Interests: Dr. Sauthier received funding from “Fonds de recherche du Québec en Santé” and the Université de Montréal (Faculty of Medicine). The remaining authors have disclosed that they do not have any potential conflicts of interest., (Copyright © 2020 The Authors. Published by Wolters Kluwer Health, Inc. on behalf of the Society of Critical Care Medicine.)

Background: In an intensive care units, experts in mechanical ventilation are not continuously at patient's bedside to adjust ventilation settings and to analyze the impact of these adjustments on gas exchange. The development of clinical decision support systems analyzing patients' data in real time offers an opportunity to fill this gap., Objective: The objective of this study was to determine whether a machine learning predictive model could be trained on a set of clinical data and used to predict transcutaneous hemoglobin oxygen saturation 5 min (5min SpO2) after a ventilator setting change., Data Sources: Data of mechanically ventilated children admitted between May 2015 and April 2017 were included and extracted from a high-resolution research database. More than 776,727 data rows were obtained from 610 patients, discretized into 3 class labels (< 84%, 85% to 91% and c92% to 100%)., Performance Metrics of Predictive Models: Due to data imbalance, four different data balancing processes were applied. Then, two machine learning models (artificial neural network and Bootstrap aggregation of complex decision trees) were trained and tested on these four different balanced datasets. The best model predicted SpO2 with area under the curves < 0.75., Conclusion: This single center pilot study using machine learning predictive model resulted in an algorithm with poor accuracy. The comparison of machine learning models showed that bagged complex trees was a promising approach. However, there is a need to improve these models before incorporating them into a clinical decision support systems. One potentially solution for improving predictive model, would be to increase the amount of data available to limit over-fitting that is potentially one of the cause for poor classification performances for 2 of the three class labels., Competing Interests: The authors have declared that no competing interests exist.

Respiratory support is required in most children in the pediatric intensive care unit. Decision-support tools (paper or electronic) have been shown to improve the quality of medical care, reduce errors, and improve outcomes. Computers can assist clinicians by standardizing descriptors and procedures, consistently performing calculations, incorporating complex rules with patient data, and capturing relevant data. This article discusses computer decision-support tools to assist clinicians in making flexible but consistent, evidence-based decisions for equivalent patient states., (Copyright © 2017 Elsevier Inc. All rights reserved.)

Objective: To evaluate acute rehabilitation practices in pediatric critical care units across Canada., Design: Retrospective cohort study., Setting: Six Canadian, tertiary care pediatric critical care units., Patients/subjects: Six hundred children aged under 17 years admitted to pediatric critical care unit during a winter and summer month of 2011 with a greater than 24-hour length of stay., Interventions: None., Measurements and Main Results: The primary outcome of interest was the nature and timing of pediatric critical care unit rehabilitation practices.Rehabilitation was classified according to mobility and nonmobility interventions. Predictors of mobilization and the time to mobilization were evaluated through regression and time-dependent survival analyses, respectively. The most common form of rehabilitation provided in pediatric critical care unit was physical therapy (45.5% patients) followed by occupational therapy (4.5%) and speech and language therapy (1.5%). Interventions were primarily nonmobility in nature (69.7% of sessions), most frequently in the form of chest physiotherapy (42.7% of sessions). The median time to mobilization was 2 days (interquartile range, 1-6) as compared with 1 day for nonmobility interventions (interquartile range, 1-3). Only 57 patients (9.5%) received early mobilization. Regression analyses revealed that increasing age, admission during winter, neuromuscular blockade, and sedative infusions were associated with an increased likelihood of receiving mobility therapy. Increasing age was a predictor of early mobilization, while neuromuscular blockade was associated with delayed mobilization. No significant differences in adverse events were found between nonmobility and mobility interventions., Conclusions: Only half of the children receive rehabilitation while in the pediatric critical care unit, and when it occurs, therapy is primarily focused on respiratory function. Mobilization appears to be reserved for at-risk children who were muscle relaxed and sedated; however, its implementation in these patients is delayed. Future pediatric-specific research is essential to identify patients at risk and to understand treatment priorities and rehabilitation strategies to improve functional recovery in critically ill children.

Purpose: Duration of weaning from mechanical ventilation is decreased with the use of written protocols in adults. In children, the use of written protocols has not had such an impact., Methods and Measurements: We conducted a single-center trial to assess the feasibility of conducting a multicenter randomized clinical trial comparing the duration of weaning from mechanical ventilation in those managed by a computer-driven explicit protocol versus usual care. Mechanically ventilated children aged between 2 and 17 years on pressure support and not receiving inotropes were included. After randomization, children were weaned either by usual care (n = 15) that was characterized by no protocolized decisions by attending physicians, or by a computer-driven protocol (Smartcare/PS™, Drager Medical) (n = 15). Weaning duration until first extubation was the primary outcome. For comparison, a Mann-Whitney U test was employed (p < 0.05)., Results: Patients characteristics at inclusion were similar. The median duration of weaning was 21 h (range 3-142 h) in the SmartCare/PS™ group and 90 h (range 4-552 h) in the usual care group, p = 0.007. The rate of reintubation within 48 h after extubation and the rate of noninvasive ventilation after extubation in the SmartCare/PS™ and usual care groups were 2/15 versus 1/15 and 2/15 versus 2/15, respectively., Conclusions: A pediatric randomized trial on mechanical ventilation with a computerized protocol in North America is feasible. A computer-driven protocol that also manages children younger than 2 years old would help to decrease the number of PICU admissions screened in a multicentre trial on this topic.

Mechanical ventilation is a very effective therapy, but with many complications. Simulators are used in many fields, including medicine, to enhance safety issues. In the intensive care unit, they are used for teaching cardiorespiratory physiology and ventilation, for testing ventilator performance, for forecasting the effect of ventilatory support, and to determine optimal ventilatory management. They are also used in research and development of clinical decision support systems (CDSSs) and explicit computerized protocols in closed loop. For all those reasons, cardiorespiratory simulators are one of the tools that help to decrease mechanical ventilation duration and complications. This paper describes the different types of simulators described in the literature for physiologic simulation and modeling of the respiratory system, including a new simulator (SimulResp), and proposes a validation process for these simulators.