Determining Optimal Mean Arterial Blood Pressure Based on Cerebral Autoregulation in Children after Cardiac Surgery.

To evaluate the feasibility of continuous determination of the optimal mean arterial blood pressure (opt-MAP) according to cerebral autoregulation and to describe the opt-MAP, the autoregulation limits, and the time spent outside these limits in children within 48 h of cardiac surgery. Cerebral autoregulation was assessed using the correlation coefficient (COx) between cerebral oxygenation and MAP in children following cardiac surgery. Plots depicting the COx according to the MAP were used to determine the opt-MAP using weighted multiple time windows. For each patient, we estimated (1) the time spent with MAP outside the autoregulation limits and (2) the burden of deviation, defined as the area between the MAP curve and the autoregulation limits when the MAP was outside these limits. Fifty-one patients with a median age of 7.1 (IQR 0.7-52.0) months old were included. The opt-MAP was calculated for 94% (IQR 90-96) of the monitored time. The opt-MAP was significantly lower in neonates < 1 month old. The patients spent 24% (18-31) of the time outside of the autoregulation limits, with no significant differences between age groups. Continuous determination of the opt-MAP is feasible in children within the first 48 h following cardiac surgery.

Evaluating the Need for Intensive Care Admission After Supraglottoplasty for Severe Laryngomalacia.

OBJECTIVE: Postoperative airway concerns persist despite a low rate of post-supraglottoplasty complications for children with laryngomalacia. The objective of this study is to determine the factors associated with the need for intensive care unit (ICU) admission following supraglottoplasty. METHODS: A 7-year retrospective cohort analysis was conducted between 2014 and 2021. A patient requiring ICU level of care was defined as the use of respiratory support such as intubation, positive pressure ventilation, high-flow nasal cannula, or multiple doses of nebulized epinephrine. RESULTS: About 134 medical charts were reviewed; 12 patients were excluded because of concurrent surgery. Age at the time of surgery was 2.8 (4.3) months (median [interquartile range]). About 33 (27.0%) ultimately required ICU-level care. Prematurity (odds ratio [OR] 13.8), neurological condition (OR ∞), American Society of Anesthesiology class 3-4 (OR 6.5), and younger age (OR 1.8) were more likely to require ICU admission. No patient above 10 months of age needed ICU monitoring. The use of respiratory support justifying ICU was known within the first 4 h after surgery for almost all (32/33, 97%) of these patients. 4/33 (12.1%) were kept intubated and the remaining needed non-invasive ventilation. Only one patient (1/122, 0.8%) was reintubated 12 h after surgery for progressive respiratory distress. CONCLUSION: Approximately a quarter of patients required ICU-level care after supraglottoplasty. For nearly all patients without comorbidities requiring ICU, this can be safely predicted within the first 4 h after surgery. Our data suggest that selected patients undergoing supraglottoplasty may be safely monitored outside of an ICU setting after an observation period in the post-anesthesia care unit. LEVEL OF EVIDENCE: 4 Laryngoscope, 134:466-470, 2024.

CODA: an open-source platform for federated analysis and machine learning on distributed healthcare data.

OBJECTIVES: Distributed computations facilitate multi-institutional data analysis while avoiding the costs and complexity of data pooling. Existing approaches lack crucial features, such as built-in medical standards and terminologies, no-code data visualizations, explicit disclosure control mechanisms, and support for basic statistical computations, in addition to gradient-based optimization capabilities. MATERIALS AND METHODS: We describe the development of the Collaborative Data Analysis (CODA) platform, and the design choices undertaken to address the key needs identified during our survey of stakeholders. We use a public dataset (MIMIC-IV) to demonstrate end-to-end multi-modal FL using CODA. We assessed the technical feasibility of deploying the CODA platform at 9 hospitals in Canada, describe implementation challenges, and evaluate its scalability on large patient populations. RESULTS: The CODA platform was designed, developed, and deployed between January 2020 and January 2023. Software code, documentation, and technical documents were released under an open-source license. Multi-modal federated averaging is illustrated using the MIMIC-IV and MIMIC-CXR datasets. To date, 8 out of the 9 participating sites have successfully deployed the platform, with a total enrolment of >1M patients. Mapping data from legacy systems to FHIR was the biggest barrier to implementation. DISCUSSION AND CONCLUSION: The CODA platform was developed and successfully deployed in a public healthcare setting in Canada, with heterogeneous information technology systems and capabilities. Ongoing efforts will use the platform to develop and prospectively validate models for risk assessment, proactive monitoring, and resource usage. Further work will also make tools available to facilitate migration from legacy formats to FHIR and DICOM.

Clinical Decision Support System to Detect the Occurrence of Ventilator-Associated Pneumonia in Pediatric Intensive Care.

OBJECTIVES: Ventilator-associated pneumonia (VAP) is a severe care-related disease. The Centers for Disease Control defined the diagnosis criteria; however, the pediatric criteria are mainly subjective and retrospective. Clinical decision support systems have recently been developed in healthcare to help the physician to be more accurate for the early detection of severe pathology. We aimed at developing a predictive model to provide early diagnosis of VAP at the bedside in a pediatric intensive care unit (PICU). METHODS: We performed a retrospective single-center study at a tertiary-care pediatric teaching hospital. All patients treated by invasive mechanical ventilation between September 2013 and October 2019 were included. Data were collected in the PICU electronic medical record and high-resolution research database. Development of the clinical decision support was then performed using open-access R software (Version 3.6.1®). MEASUREMENTS AND MAIN RESULTS: In total, 2077 children were mechanically ventilated. We identified 827 episodes with almost 48 h of mechanical invasive ventilation and 77 patients who suffered from at least one VAP event. We split our database at the patient level in a training set of 461 patients free of VAP and 45 patients with VAP and in a testing set of 199 patients free of VAP and 20 patients with VAP. The Imbalanced Random Forest model was considered as the best fit with an area under the ROC curve from fitting the Imbalanced Random Forest model on the testing set being 0.82 (95% CI: (0.71, 0.93)). An optimal threshold of 0.41 gave a sensitivity of 79.7% and a specificity of 72.7%, with a positive predictive value (PPV) of 9% and a negative predictive value of 99%, and with an accuracy of 79.5% (95% CI: (0.77, 0.82)). CONCLUSIONS: Using machine learning, we developed a clinical predictive algorithm based on clinical data stored prospectively in a database. The next step will be to implement the algorithm in PICUs to provide early, automatic detection of ventilator-associated pneumonia.

Evaluation of the SIMULRESP: A simulation software of child and teenager cardiorespiratory physiology.

BACKGROUND: Mathematical models based on the physiology when programmed as a software can be used to teach cardiorespiratory physiology and to forecast the effect of various ventilatory support strategies. We developed a cardiorespiratory simulator for children called "SimulResp." The purpose of this study was to evaluate the quality of SimulResp. METHODS: SimulResp quality was evaluated on accuracy, robustness, repeatability, and reproducibility. Blood gas values (pH, PaCO2 , PaO2,  and SaO2 ) were simulated for several subjects with different characteristics and in different situations and compared to expected values available as reference. The correlation between reference and simulated data was evaluated by the coefficient of determination and Intraclass correlation coefficient. The agreement was evaluated with the Bland & Altman analysis. RESULTS: SimulResp produced healthy child physiological values within normal range (pH 7.40 ± 0.5; PaCO2 40 ± 5 mmHg; PaO2 90 ± 10 mmHg; SaO2 97 ± 3%) starting from a weight of 25-35 kg, regardless of ventilator support. SimulResp failed to simulate accurate values for subjects under 25 kg and/or affected with pulmonary disease and mechanically ventilated. Based on the repeatability was considered as excellent and the reproducibility as mild to good. SimulResp's prediction remains stable within time. CONCLUSIONS: The cardiorespiratory simulator SimulResp requires further development before future integration into a clinical decision support system.

Automated screening of potential organ donors using a temporal machine learning model.

Organ donation is not meeting demand, and yet 30-60% of potential donors are potentially not identified. Current systems rely on manual identification and referral to an Organ Donation Organization (ODO). We hypothesized that developing an automated screening system based on machine learning could reduce the proportion of missed potentially eligible organ donors. Using routine clinical data and laboratory time-series, we retrospectively developed and tested a neural network model to automatically identify potential organ donors. We first trained a convolutive autoencoder that learned from the longitudinal changes of over 100 types of laboratory results. We then added a deep neural network classifier. This model was compared to a simpler logistic regression model. We observed an AUROC of 0.966 (CI 0.949-0.981) for the neural network and 0.940 (0.908-0.969) for the logistic regression model. At a prespecified cutoff, sensitivity and specificity were similar between both models at 84% and 93%. Accuracy of the neural network model was robust across donor subgroups and remained stable in a prospective simulation, while the logistic regression model performance declined when applied to rarer subgroups and in the prospective simulation. Our findings support using machine learning models to help with the identification of potential organ donors using routinely collected clinical and laboratory data.

Designing a national pediatric critical care database: a Delphi consensus study.

PURPOSE: We sought to describe the processes undertaken for the systematic selection and consensus determination of the common data elements for inclusion in a national pediatric critical care database in Canada. METHODS: We conducted a multicentre Delphi consensus study of Canadian pediatric intensive care units (PICUs) participating in the creation of a national database. Participants were PICU health care professionals, allied health professionals, caregivers, and other stakeholders. A dedicated panel group created a baseline survey of data elements based on literature, current PICU databases, and expertise in the field. The survey was then used for a Delphi iterative consensus process over three rounds, conducted from March to June 2021. RESULTS: Of 86 invited participants, 68 (79%) engaged and agreed to participate as part of an expert panel. Panel participants were sent three rounds of the survey with response rates of 62 (91%), 61 (90%) and 55 (81%), respectively. After three rounds, 72 data elements were included from six domains, mostly reflecting clinical status and complex medical interventions received in the PICU. While race, gender, and home region were included by consensus, variables such as minority status, indigenous status, primary language, and ethnicity were not. CONCLUSION: We present the methodological framework used to select data elements by consensus for a national pediatric critical care database, with participation from a diverse stakeholder group of experts and caregivers from all PICUs in Canada. The selected core data elements will provide standardized and synthesized data for research, benchmarking, and quality improvement initiatives of critically ill children.

RéSUMé: OBJECTIF: Nous avons cherché à décrire les processus entrepris pour la sélection systématique et la détermination consensuelle des éléments de données communs à inclure dans une base de données nationale sur les soins intensifs pédiatriques au Canada. MéTHODE: Nous avons mené une étude multicentrique de consensus selon la méthode Delphi sur les unités de soins intensifs pédiatriques (USIP) canadiennes participant à la création d'une base de données nationale. Les personnes participant à l'étude étaient des professionnel·les de la santé de l'USIP, du personnel paramédical, des soignant·es et d'autres intervenant·es. Un groupe de travail spécialisé a créé une enquête de base des éléments de données sur la littérature, les bases de données actuelles portant sur les USIP et l'expertise dans le domaine. L'enquête a ensuite été utilisée pour créer un processus de consensus itératif Delphi sur trois cycles, mené de mars à juin 2021. RéSULTATS: Sur les 86 personnes invitées à participer, 68 (79 %) se sont engagées et ont accepté de participer à un groupe d'experts. Les membres du panel ont reçu trois rondes du sondage, avec des taux de réponse de 62 (91 %), 61 (90 %) et 55 (81 %), respectivement. Après trois cycles, 72 éléments de données provenant de six domaines ont été inclus, reflétant principalement l'état clinique et les interventions médicales complexes reçues à l'USIP. Alors que la race, le genre et la région d'origine ont été inclus par consensus, des variables telles que le statut de minorité, le statut d'autochtone, la langue principale parlée et l'origine ethnique ne l'ont pas été. CONCLUSION: Nous présentons le cadre méthodologique utilisé pour sélectionner des éléments de données consensuels destinés à une base de données nationale sur les soins intensifs pédiatriques, avec la participation d'un groupe diversifié d'expert·es et de soignant·es de toutes les USIP au Canada. Les éléments de données de base sélectionnés fourniront des données normalisées et synthétisées pour la recherche, l'analyse comparative et les initiatives d'amélioration de la qualité pour les enfants gravement malades.

Prevalence and determinants of anemia at discharge in pediatric intensive care survivors.

BACKGROUND: Restrictive transfusion practices are increasingly being followed in pediatric intensive care units (PICU); consequently, more patients are discharged anemic from PICU. Given the possible impact of anemia on long-term neurodevelopmental outcomes, we aim to describe the epidemiology of anemia at PICU discharge in a mixed (pediatric and cardiac) cohort of PICU survivors and to characterize risk factors for anemia. STUDY DESIGN AND METHODS: We performed a retrospective cohort study in the PICU of a multidisciplinary tertiary-care university-affiliated center. All consecutive PICU survivors for whom a hemoglobin level was available at PICU discharge were included. Baseline characteristics and hemoglobin levels were extracted from an electronic medical records database. RESULTS: From January 2013 to January 2018, 4750 patients were admitted to the PICU (97.1% survival); discharge hemoglobin levels were available for 4124 patients. Overall, 50.9% (n = 2100) were anemic at PICU discharge. Anemia at PICU discharge was also common in the cardiac surgery population (53.3%), mainly in acyanotic patients; only 24.6% of cyanotic patients were anemic according to standard definitions of anemia. Cardiac surgery patients were transfused more often and at higher hemoglobin levels than medical and non-cardiac surgery patients. Anemia at admission was the strongest predictor of anemia at discharge (odds ratios (OR): 6.51, 95% confidence interval (CI:5.40;7.85)). DISCUSSION: Half of PICU survivors are anemic at discharge. Further studies are required to determine the course of anemia after discharge and to ascertain whether anemia is associated with adverse long-term outcomes.

Elevated Diaphragmatic Tonic Activity in PICU Patients: Age-Specific Definitions, Prevalence, and Associations.

OBJECTIVES: Tonic diaphragmatic activity (tonic Edi, i.e., sustained diaphragm activation throughout expiration) reflects diaphragmatic effort to defend end-expiratory lung volumes. Detection of such elevated tonic Edi may be useful in identifying patients who need increased positive end-expiratory pressure. We aimed to: 1) identify age-specific definitions for elevated tonic Edi in ventilated PICU patients and 2) describe the prevalence and factors associated with sustained episodes of high tonic Edi. DESIGN: Retrospective study using a high-resolution database. SETTING: Single-center tertiary PICU. PATIENTS: Four hundred thirty-one children admitted between 2015 and 2020 with continuous Edi monitoring. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We characterized our definition of tonic Edi using data from the recovery phase of respiratory illness (i.e., final 3 hr of Edi monitoring, excluding patients with significant persistent disease or with diaphragm pathology). High tonic Edi was defined as population data exceeding the 97.5th percentile, which for infants younger than 1 year was greater than 3.2 µV and for older children as greater than 1.9 µV. These thresholds were then used to identify patients with episodes of sustained elevated tonic Edi in the first 48 hours of ventilation (acute phase). Overall, 62 of 200 (31%) of intubated patients and 138 of 222 (62%) of patients on noninvasive ventilation (NIV) had at least one episode of high tonic Edi. These episodes were independently associated with the diagnosis of bronchiolitis (intubated patients: adjusted odds [aOR], 2.79 [95% CI, 1.12-7.11]); NIV patients: aOR, 2.71 [1.24-6.0]). There was also an association with tachypnea and, in NIV patients, more severe hypoxemia. CONCLUSIONS: Our proposed definition of elevated tonic Edi quantifies abnormal diaphragmatic activity during expiration. Such a definition may help clinicians to identify those patients using abnormal effort to defend end-expiratory lung volume. In our experience, high tonic Edi episodes are frequent, especially during NIV and in patients with bronchiolitis.

Executive Summary of the Second International Guidelines for the Diagnosis and Management of Pediatric Acute Respiratory Distress Syndrome (PALICC-2).

OBJECTIVES: We sought to update our 2015 work in the Second Pediatric Acute Lung Injury Consensus Conference (PALICC-2) guidelines for the diagnosis and management of pediatric acute respiratory distress syndrome (PARDS), considering new evidence and topic areas that were not previously addressed. DESIGN: International consensus conference series involving 52 multidisciplinary international content experts in PARDS and four methodology experts from 15 countries, using consensus conference methodology, and implementation science. SETTING: Not applicable. PATIENTS: Patients with or at risk for PARDS. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Eleven subgroups conducted systematic or scoping reviews addressing 11 topic areas: 1) definition, incidence, and epidemiology; 2) pathobiology, severity, and risk stratification; 3) ventilatory support; 4) pulmonary-specific ancillary treatment; 5) nonpulmonary treatment; 6) monitoring; 7) noninvasive respiratory support; 8) extracorporeal support; 9) morbidity and long-term outcomes; 10) clinical informatics and data science; and 11) resource-limited settings. The search included MEDLINE, EMBASE, and CINAHL Complete (EBSCOhost) and was updated in March 2022. Grading of Recommendations, Assessment, Development, and Evaluation methodology was used to summarize evidence and develop the recommendations, which were discussed and voted on by all PALICC-2 experts. There were 146 recommendations and statements, including: 34 recommendations for clinical practice; 112 consensus-based statements with 18 on PARDS definition, 55 on good practice, seven on policy, and 32 on research. All recommendations and statements had agreement greater than 80%. CONCLUSIONS: PALICC-2 recommendations and consensus-based statements should facilitate the implementation and adherence to the best clinical practice in patients with PARDS. These results will also inform the development of future programs of research that are crucially needed to provide stronger evidence to guide the pediatric critical care teams managing these patients.

Leveraging Clinical Informatics and Data Science to Improve Care and Facilitate Research in Pediatric Acute Respiratory Distress Syndrome: From the Second Pediatric Acute Lung Injury Consensus Conference.

OBJECTIVES: The use of electronic algorithms, clinical decision support systems, and other clinical informatics interventions is increasing in critical care. Pediatric acute respiratory distress syndrome (PARDS) is a complex, dynamic condition associated with large amounts of clinical data and frequent decisions at the bedside. Novel data-driven technologies that can help screen, prompt, and support clinician decision-making could have a significant impact on patient outcomes. We sought to identify and summarize relevant evidence related to clinical informatics interventions in both PARDS and adult respiratory distress syndrome (ARDS), for the second Pediatric Acute Lung Injury Consensus Conference. DATA SOURCES: MEDLINE (Ovid), Embase (Elsevier), and CINAHL Complete (EBSCOhost). STUDY SELECTION: We included studies of pediatric or adult critically ill patients with or at risk of ARDS that examined automated screening tools, electronic algorithms, or clinical decision support systems. DATA EXTRACTION: Title/abstract review, full text review, and data extraction using a standardized data extraction form. DATA SYNTHESIS: The Grading of Recommendations Assessment, Development and Evaluation approach was used to identify and summarize evidence and develop recommendations. Twenty-six studies were identified for full text extraction to address the Patient/Intervention/Comparator/Outcome questions, and 14 were used for the recommendations/statements. Two clinical recommendations were generated, related to the use of electronic screening tools and automated monitoring of compliance with best practice guidelines. Two research statements were generated, related to the development of multicenter data collaborations and the design of generalizable algorithms and electronic tools. One policy statement was generated, related to the provision of material and human resources by healthcare organizations to empower clinicians to develop clinical informatics interventions to improve the care of patients with PARDS. CONCLUSIONS: We present two clinical recommendations and three statements (two research one policy) for the use of electronic algorithms and clinical informatics tools for patients with PARDS based on a systematic review of the literature and expert consensus.

Pediatric Interfacility Transport Curriculum: Its Impact on the Pediatric Intensive Care and Emergency Medicine Fellows' Performance and Confidence.

OBJECTIVE: Pediatric interfacility transports are frequent. Despite the absence of a formal pediatric transport curriculum in eastern Canada, directly managing patients during transport and medical direction of the referring center and transport team are part of the pediatric critical care medicine (PCCM) and pediatric emergency medicine (PEM) program requirements. The authors developed a pediatric interfacility transport curriculum and measured its impact on fellows' confidence and performance. METHODS: This was a pilot interventional prospective study in Montreal, Canada. Postcurriculum surveys were used to measure confidence, and high-fidelity simulations were used to measure performance. A target threshold for confidence was defined before implementation, and pre- and post values were compared. The simulation scenario and assessment checklist were locally developed. RESULTS: The participants were 11 PCCM and 3 PEM fellows. The content of the curriculum and educational methods were selected based on the literature and a needs assessment survey. All participants rated themselves as confident at the end of the curriculum. Eighty-three percent of the participants were deemed proficient with a perfect interrater agreement. CONCLUSION: The pediatric transport curriculum had a positive impact on PEM and PCCM fellows' confidence and performance in transport. Further studies should look at the impact of such a curriculum on participants' real-life performance and patient care.

Impact of Blood Sampling on Anemia in the PICU: A Prospective Cohort Study.

OBJECTIVES: Fifty percent of children are anemic after a critical illness. Iatrogenic blood testing may be a contributor to this problem. The objectives of this study were to describe blood sampling practice in a PICU, determine patient factors associated with increased sampling, and examine the association among blood sampling volume, anemia at PICU discharge, and change in hemoglobin from PICU entry to PICU discharge. DESIGN: Prospective observational cohort study. SETTING: PICU of Sainte-Justine University Hospital. PATIENTS: All children consecutively admitted during a 4-month period. MEASUREMENTS AND MAIN RESULTS: Four hundred twenty-three children were enrolled. Mean blood volume sampled was 3.9 (±19) mL/kg/stay, of which 26% was discarded volume. Children with central venous or arterial access were sampled more than those without access (p < 0.05). Children with sepsis, shock, or cardiac surgery were most sampled, those with a primary respiratory diagnosis; the least (p < 0.001). We detected a strong association between blood sample volume and mechanical ventilation (H, 81.35; p < 0.0001), but no association with severity of illness (Worst Pediatric Logistic Organ Dysfunction score) (R, -0.044; p = 0.43). Multivariate analysis (n = 314) showed a significant association between the volume of blood sampled (as continuous variable) and anemia at discharge (adjusted OR, 1.63; 95% CI, 1.18-2.45; p = 0.003). We lacked power to detect an association between blood sampling and change in hemoglobin from PICU admission to PICU discharge. CONCLUSIONS: Diagnostic blood sampling in PICU is associated with anemia at discharge. Twenty-five percent of blood losses from sampling is wasted. Volumes are highest for patients with sepsis, shock, or cardiac surgery, and in patients with vascular access or ventilatory support.

Oxygenation Defects, Ventilatory Ratio, and Mechanical Power During Severe Pediatric Acute Respiratory Distress Syndrome: Longitudinal Time Sequence Analyses in a Single-Center Retrospective Cohort.

OBJECTIVES: Our understanding of pediatric acute respiratory distress syndrome is based on information from studies reporting intermittent, serial respiratory data. We have analyzed a high-resolution, longitudinal dataset that incorporates measures of hypoxemia severity, metrics of lung mechanics, ventilatory ratio, and mechanical power and examined associations with survival after the onset of pediatric acute respiratory distress syndrome. DESIGN: Single-center retrospective cohort, 2013-2018. SETTING: Tertiary surgical/medical PICU. PATIENTS: Seventy-six cases of severe pediatric acute respiratory distress syndrome, determined according to the Pediatric Acute Lung Injury Consensus Conference criteria. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The high-resolution database included continuous monitoring of ventilatory data (0.03 Hz) for up to 14 days after the diagnosis of pediatric acute respiratory distress syndrome or until extubation or death (n = 26). In the 12,128 hours of data during conventional mechanical ventilation, we used generalized estimating equations to compare groups, accounting for any effect of time. We identified an association between survival and faster rate of improvement in delta pressure (peak inspiratory pressure minus positive end-expiratory pressure; p = 0.028). Nonsurvival was associated with higher daily Pediatric Logistic Organ Dysfunction-2 scores (p = 0.005) and more severe hypoxemia metrics (p = 0.005). Mortality was also associated with the following respiratory/pulmonary metrics (mean difference [95% CI]): positive end-expiratory pressure level (+2.0 cm H2O [0.8-3.2 cm H2O]; p = 0.001), peak inspiratory pressure level (+3.0 cm H2O [0.5-5.5 cm H2O]; p = 0.022), respiratory rate (z scores +2.2 [0.9-3.6]; p = 0.003], ventilatory ratio (+0.41 [0.28-0.55]; p = 0.0001], and mechanical power (+5 Joules/min [1-10 Joules/min]; p = 0.013). Based on generalized linear mixed modeling, mechanical power remained associated with mortality after adjustment for normal respiratory rate, age, and daily Pediatric Logistic Organ Dysfunction-2 score (+3 Joules/breath [1-6 Joules/breath]; p = 0.009). CONCLUSIONS: Mortality after severe pediatric acute respiratory distress syndrome is associated with the severity of organ dysfunction, oxygenation defects, and pulmonary metrics including dead space and theoretical mechanical energy load.

Estimated Pao2: A Continuous and Noninvasive Method to Estimate Pao2 and Oxygenation Index.

Pao2 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 Spo2 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 Pao2 using three kinds of neural networks and an empirically optimized mathematical model derived from known physiologic equations. RESULTS: We included 52,879 Pao2 (3,252 patients) in the derivation dataset and 12,047 Pao2 (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 Pao2 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 Pao2 to estimate the oxygenation index showed a significantly better hypoxemia classification (kappa) than oxygenation saturation index for both Spo2 less than or equal to 97% (0.79 vs 0.60; p < 0.001) and Spo2 greater than 97% (0.58 vs 0.52; p < 0.001). CONCLUSION: The estimated Pao2 using pulse rate and electrical heart rate Spo2 validation allows a continuous and noninvasive estimation of the oxygenation index that is valid for Spo2 less than or equal to 97% and for Spo2 greater than 97%. Display of continuous analysis of estimated Pao2 and estimated oxygenation index may provide decision support to assist with hypoxemia diagnosis and oxygen titration in critically ill patients.

Intravenous Immunoglobulin Use In Critically Ill Children.

Purpose: The use of intravenous immunoglobulins (IVIG) has increased significantly in the last decade causing challenges for blood suppliers to respond to the demand. Indications for which IVIG infusion should be given to critically ill children remain unclear. The objective of this study is to characterize the epidemiology of IVIG use in this population. Methods: We performed a single-center retrospective cohort study of all patients aged between 3 days and 18 years who received at least one IVIG infusion while hospitalized in the pediatric intensive care unit of the Centre hospitalier universitaire (CHU) Sainte-Justine, Montréal Quebec (Canada) between January 1, 2013 and December 31, 2018. Results: One hundred and seventy-two patients received a total of 342 IVIG infusions over the study period. Most common indications for IVIG infusions were staphylococcal or streptococcal toxic shock syndrome (n=53/342, 15.5%), immunoglobulin replacement in chylothorax (n=37/342, 10.9%), prophylaxis following bone marrow transplantation (n=31/342, 9.1%), myocarditis (n=25/342, 7.3%) and post-solid organ transplant complications (n=21/342, 6.1%). The median dose of IVIG per infusion was 0.95 g/kg (IQR 0.5-1.0) and median number of IVIG infusions per patient was one (IQR: 1-2). Seventy-nine percent of IVIG infusions given were administrated for off-label indications with regards to Health Canada recommendations. Conclusion: This study identified the most common indications for IVIG infusion in critically ill children in a tertiary care pediatric intensive care unit. Given the costs, the known adverse events associated with IVIG and the pressure that blood suppliers are facing to meet the demands, clinical trials are needed to evaluate the efficacy and safety of IVIG in conditions where use is significant.

Long-Term Mechanical Ventilation in Neonates: A 10-Year Overview and Predictive Model.

Objectives: Significant resources are devoted to neonatal prolonged mechanical ventilation (NPMV), but little is known about the outcomes in those children. Our primary objective was to describe the NPMV respiratory, digestive, and neurological outcomes at 18 months corrected age. Our second objective was on the early identification of which patients, among the NPMV cohort, will need to be ventilated for ≥125 days, which corresponded to the 75th percentile in the preliminary data, and to describe that subgroup. Methods: In this retrospective cohort study, we included all children born between 2004 and 2013 who had a NPMV (≥21 days of invasive or noninvasive respiratory support reached between 40 and 44 weeks of postconceptional age). We used random forests, logistic regression with penalization, naive Bayes, and XGBoost to predict which patients will need ≥125 days of ventilation. We used a Monte Carlo cross validation. Results: We included 164 patients. Of which, 40% (n = 66) were female, and the median gestational age was 29 weeks [interquartile range (IQR): 26-36 weeks] with a bimodal distribution. Median ventilation days were 104 (IQR: 66-139 days). The most frequently associated diagnoses were pulmonary hypertension (43%), early pulmonary dysplasia (41%), and lobar emphysema (37%). At 18 months corrected age, 29% (n = 47) had died, 59% (n = 97) were free of any respiratory support, and 45% (n = 74) were exclusively orally fed. A moderate area under the ROC curve of 0.65 (95% CI: 0.54-0.72) for identifying patients in need of ≥125 days of ventilation at inclusion was achieved by random forests classifiers. Among the 26 measured at inclusion, the most contributive ones were PCO2, inspired O2 concentration, and gestational age. At 18 months corrected age, patients ventilated for ≥125 days had a lower respiratory weaning success (76 vs. 87%, P = 0.05), lower exclusive oral feeding proportion (51 vs. 84%, P < 0.001), and a higher neurological impairment (median Pediatric Cerebral Performance Category score 3 vs. 2, P = 0.008) than patients ventilated for < 125 days. Conclusion: NPMV is a severe condition with a high risk of mortality, neurological impairment, and oral feed delay at 18 months. Most survivors are weaned of any respiratory support. We identified the risk factors that allow for the early identification of the most at-risk children of long-term ventilation with a moderate discrimination.

Arterial Partial Pressures of Carbon Dioxide Estimation Using Non-Invasive Parameters in Mechanically Ventilated Children.

OBJECTIVE: We aim to create a predictive model capable of giving a noninvasive, immediate and reliable estimate of the arterial partial pressure of carbon dioxide (PaCO2) in mechanically ventilated children with a better reliability than its estimation from end-tidal CO2 (PetCO2) and minute ventilation volume (Vmin) evolution. METHODS: We collected data from the Intensive Care Unit (ICU) database of Sainte-Justine University Hospital (Montreal, Canada) and used the multilayer perceptron (MLP) to estimate the PaCO2. Input data were (1) Arterial blood gas (ABG) at a previous time to calibrate the model, (2) mechanical ventilator parameters and (3) pulse oximetry. The data were divided into four groups depending on the time gap between previous ABG and its prediction: [0 h, 2 h], [2 h, 6 h], [6 h, 12 h] and [12 h, 24 h]. RESULTS: We included 17,329 ABGs collected from 527 patients between May 2015 and October 2018. Median age was 6.7 months (interquartile range 1-60) and female proportion was 45%. Patients had a median of 13 ABGs per patient (IQR 5-34). The accuracy of the models in the four groups was 18%, 18%, 19% and 25% higher than the minute volume models and the PetCO2 models (4% to 11%, respectively). CONCLUSION: Our model based on noninvasive parameters was able to better estimate the PaCO2 in mechanically ventilated children when compared to the traditional techniques. SIGNIFICANCE: ABG analysis is very important in ICU; it is the gold standard in respiratory and acid-base evaluation. ABG is invasive, painful and risky. Our approach, noninvasive and reliable, is an alternative for optimizing mechanical ventilator settings, thus providing better care for patients.

Validation process of a high-resolution database in a paediatric intensive care unit-Describing the perpetual patient's validation.

RATIONALE: High data quality is essential to ensure the validity of clinical and research inferences based on it. However, these data quality assessments are often missing even though these data are used in daily practice and research. AIMS AND OBJECTIVES: Our objective was to evaluate the data quality of our high-resolution electronic database (HRDB) implemented in our paediatric intensive care unit (PICU). METHODS: We conducted a prospective validation study of a HRDB in a 32-bed paediatric medical, surgical, and cardiac PICU in a tertiary care freestanding maternal-child health centre in Canada. All patients admitted to the PICU with at least one vital sign monitored using a cardiorespiratory monitor connected to the central monitoring station. RESULTS: Between June 2017 and August 2018, data from 295 patient days were recorded from medical devices and 4645 data points were video recorded and compared to the corresponding data collected in the HRDB. Statistical analysis showed an excellent overall correlation (R2 = 1), accuracy (100%), agreement (bias = 0, limits of agreement = 0), completeness (2% missing data), and reliability (ICC = 1) between recorded and collected data within clinically significant pre-defined limits of agreement. Divergent points could all be explained. CONCLUSIONS: This prospective validation of a representative sample showed an excellent overall data quality.

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

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.