Explore the vast range of titles available.

Abstract Rationale The around-the-clock presence of an in-house attending critical care physician (24/7 coverage) is purported to be associated with improved outcomes among high-risk children with critical illness. Objectives To evaluate the association of 24/7 in-house coverage with outcomes in children with critical illness. Methods Patients younger than 18 years of age in the Virtual Pediatric Systems Database (2009–2014) were included. The main analysis was performed using generalized linear mixed effects multivariable regression models. In addition, multiple sensitivity analyses were performed to test the robustness of our findings. Measurements and Main Results A total of 455,607 patients from 125 hospitals were included (24/7 group: 266,319 patients; no 24/7 group: 189,288 patients). After adjusting for patient and center characteristics, the 24/7 group was associated with lower mortality in the intensive care unit (ICU) (24/7 vs. no 24/7; odds ratio [OR], 0.52; 95% confidence interval [CI], 0.33–0.80; P = 0.002), a lower incidence of cardiac arrest (OR, 0.73; 95% CI, 0.54–0.99; P = 0.04), lower mortality after cardiac arrest (OR, 0.56; 95% CI, 0.340–0.93; P = 0.02), a shorter ICU stay (mean difference, −0.51 d; 95% CI, −0.93 to −0.09), and shorter duration of mechanical ventilation (mean difference, −0.68 d; 95% CI, −1.23 to −0.14). Conclusions In this large observational study, we demonstrated that pediatric critical care provided in the ICUs staffed with a 24/7 intensivist presence is associated with improved overall patient survival and survival after cardiac arrest compared with patients treated in ICUs staffed with discretionary attending coverage. However, results from a few sensitivity analyses leave some ambiguity in these results.

Delaying intubation for patients failing Bi-Level Positive Airway Pressure (BIPAP) may be associated with harm. The objective of this study was to develop a deep learning model capable of aiding clinical decision making by predicting Bi-Level Positive Airway Pressure (BIPAP) failure. This was a retrospective cohort study in a tertiary pediatric intensive care unit (PICU) between 2010 and 2020. Three machine learning models were developed to predict BIPAP failure: two logistic regression models and one deep learning model, a recurrent neural network with a Long Short-Term Memory (LSTM-RNN) architecture. Model performance was evaluated in a holdout test set. 175 (27.7%) of 630 total BIPAP sessions were BIPAP failures. Patients in the BIPAP failure group were on BIPAP for a median of 32.8 (9.2–91.3) hours prior to intubation. Late BIPAP failure (intubation after using BIPAP > 24 h) patients had fewer 28-day Ventilator Free Days (13.40 [0.68–20.96]), longer ICU length of stay and more post-extubation BIPAP days compared to those who were intubated ≤ 24 h from BIPAP initiation. An AUROC above 0.5 indicates that a model has extracted new information, potentially valuable to the clinical team, about BIPAP failure. Within 6 h of BIPAP initiation, the LSTM-RNN model predicted which patients were likely to fail BIPAP with an AUROC of 0.81 (0.80, 0.82), superior to all other models. Within 6 h of BIPAP initiation, the LSTM-RNN model would identify nearly 80% of BIPAP failures with a 50% false alarm rate, equal to an NNA of 2. In conclusion, a deep learning method using readily available data from the electronic health record can identify which patients on BIPAP are likely to fail with good discrimination, oftentimes days before they are intubated in usual practice.

To compare the pressure-rate products and phase angles of children during minimal support ventilation and after extubation. Prospective, randomized single-center trial in a pediatric intensive care unit in a tertiary children's hospital. Seventeen endotracheally intubated, mechanically ventilated children were placed on T-piece, T-piece with heliox, continuous positive airway pressure, and pressure support in random order. Esophageal pressure swings, phase angles, respiratory mechanics, and physiological parameters were measured on these modes and after extubation. Pressure-rate product postextubation was significantly higher than on support modes. For each mode and after extubation they were: pressure support 198+/-31, continuous positive airway pressure 237+/-30, T-piece 323+/-47, T-piece/heliox 308+/-61, and extubation 378+/-43 cmH2O/min. Phase angles were significantly higher during T-piece ventilation than pressure support but not did not differ significantly from postextubation. Assessment of effort of breathing during even minimal mechanical ventilation may underestimate postextubation effort in children. Postextubation pressure-rate product and hence \"effort of breathing\" in children is best approximated by T-piece ventilation.

Children with peripheral airways obstruction suffer the negative effects of intrinsic positive end-expiratory pressure: increased work of breathing and difficulty triggering assisted ventilatory support. We examined whether external positive end-expiratory pressure to offset intrinsic positive end-expiratory pressure decreases work of breathing in children with peripheral airways obstruction. The change in work of breathing with incremental pressure support was also tested. Prospective clinical trial in a pediatric intensive care unit. Eleven mechanically ventilated, spontaneously breathing children with peripheral airways obstruction. Work of breathing (using pressure-rate product as a surrogate) was measured in three tiers: (a) Increasing pressure support over zero end-expiratory pressure. (b) Increasing applied positive end-expiratory pressure and fixed pressure support. The level of applied positive end-expiratory pressure at which pressure-rate product was least determined the compensatory positive end-expiratory pressure. (c) Increasing pressure support over compensatory (fixed) positive end-expiratory pressure. Increases in pressure support alone decreased pressure-rate product from mean 724+/-311 to 403+/-192 cmH2O/min. Applied positive end-expiratory pressure alone decreased pressure-rate product from mean 608+/-301 to 250+/-169 cmH2O/min. The lowest pressure-rate product (136+/-128 cmH2O/min) was achieved using compensatory positive end-expiratory pressure (12+/-4 cmH2O) with pressure support 16 cmH2O. For children with peripheral airways obstruction who require assisted ventilation, work of breathing during spontaneous breaths is decreased by the application of either compensatory positive end-expiratory pressure or pressure support.

The development of databases to track the outcomes of children with cardiovascular disease has been ongoing for much of the last two decades, paralleled by the rise of databases in the intensive care unit. While the breadth of data available in national, regional and local databases has grown exponentially, the ability to identify meaningful measurements of outcomes for patients with cardiovascular disease is still in its early stages. In the United States of America, the Virtual Pediatric Intensive Care Unit Performance System (VPS) is a clinically based database system for the paediatric intensive care unit that provides standardized high quality, comparative data to its participants [https://portal.myvps.org/]. All participants collect information on multiple parameters: (1) patients and their stay in the hospital, (2) diagnoses, (3) interventions, (4) discharge, (5) various measures of outcome, (6) organ donation, and (7) paediatric severity of illness scores. Because of the standards of quality within the database, through customizable interfaces, the database can also be used for several applications: (1) administrative purposes, such as assessing the utilization of resources and strategic planning, (2) multi-institutional research studies, and (3) additional internal projects of quality improvement or research. In the United Kingdom, The Paediatric Intensive Care Audit Network is a database established in 2002 to record details of the treatment of all critically ill children in paediatric intensive care units of the National Health Service in England, Wales and Scotland. The Paediatric Intensive Care Audit Network was designed to develop and maintain a secure and confidential high quality clinical database of pediatric intensive care activity in order to meet the following objectives: (1) identify best clinical practice, (2) monitor supply and demand, (3) monitor and review outcomes of treatment episodes, (4) facilitate strategic healthcare planning, (5) quantify resource requirements, and (6) study the epidemiology of critical illness in children. Two distinct physiologic risk adjustment methodologies are the Pediatric Risk of Mortality Scoring System (PRISM), and the Paediatric Index of Mortality Scoring System 2 (PIM 2). Both Pediatric Risk of Mortality (PRISM 2) and Pediatric Risk of Mortality (PRISM 3) are comprised of clinical variables that include physiological and laboratory measurements that are weighted on a logistic scale. The raw Pediatric Risk of Mortality (PRISM) score provides quantitative measures of severity of illness. The Pediatric Risk of Mortality (PRISM) score when used in a logistic regression model provides a probability of the predicted risk of mortality. This predicted risk of mortality can then be used along with the rates of observed mortality to provide a quantitative measurement of the Standardized Mortality Ratio (SMR). Similar to the Pediatric Risk of Mortality (PRISM) scoring system, the Paediatric Index of Mortality (PIM) score is comprised of physiological and laboratory values and provides a quantitative measurement to estimate the probability of death using a logistic regression model. The primary use of national and international databases of patients with congenital cardiac disease should be to improve the quality of care for these patients. The utilization of common nomenclature and datasets by the various regional subspecialty databases will facilitate the eventual linking of these databases and the creation of a comprehensive database that spans conventional geographic and subspecialty boundaries.

High Flow Nasal Cannula (HFNC) provides non-invasive respiratory support for critically ill children who may tolerate it more readily than other Non-Invasive (NIV) techniques. Timely prediction of HFNC failure can provide an indication for increasing respiratory support. This work developed and compared machine learning models to predict HFNC failure. A retrospective study was conducted using EMR of patients admitted to a tertiary pediatric ICU from January 2010 to February 2020. A Long Short-Term Memory (LSTM) model was trained to generate a continuous prediction of HFNC failure. Performance was assessed using the area under the receiver operating curve (AUROC) at various times following HFNC initiation. The sensitivity, specificity, positive and negative predictive values (PPV, NPV) of predictions at two hours after HFNC initiation were also evaluated. These metrics were also computed in a cohort with primarily respiratory diagnoses. 834 HFNC trials [455 training, 173 validation, 206 test] met the inclusion criteria, of which 175 [103, 30, 42] (21.0%) escalated to NIV or intubation. The LSTM models trained with transfer learning generally performed better than the LR models, with the best LSTM model achieving an AUROC of 0.78, vs 0.66 for the LR, two hours after initiation. Machine learning models trained using EMR data were able to identify children at risk for failing HFNC within 24 hours of initiation. LSTM models that incorporated transfer learning, input data perseveration and ensembling showed improved performance than the LR and standard LSTM models.

We present a novel application of LSTM recurrent neural networks to multilabel classification of diagnoses given variable-length time series of clinical measurements. Our method outperforms a strong baseline on a variety of metrics.