Non-invasive ventilation usage and adherence in children and adults with Duchenne muscular dystrophy: A multicenter analysis.

INTRODUCTION/AIMS: Non-invasive ventilation (NIV) is routinely prescribed to support the respiratory system in Duchenne muscular dystrophy (DMD) patients; however, factors improving NIV usage are unclear. We aimed to identify predictors of NIV adherence in DMD patients. METHODS: This was a multicenter retrospective analysis of DMD patients prescribed NIV and followed at (1) The Hospital for Sick Children, Canada; (2) Rady Children's Hospital San Diego, USA; and (3) University of California San Diego Health, USA, between February 2016 and October 2020. The primary and secondary outcomes were 90-day period NIV adherence and clinical and socioeconomic predictors of NIV adherence. RESULTS: We identified 59 DMD patients prescribed NIV (mean ± SD age = 20.1 ± 6.7 y). Overall, percentage of nights used, and average nightly usage, were 79.9 ± 31.1% and 7.23 ± 4.12 h, respectively. Compared with children, adults had higher percentage of nights used (92.9 ± 16.9% vs. 70.4 ± 36.9%; P < .05), and average nightly usage (9.5 ± 4.7 h vs. 5.3 ± 3.7 h; P < .05). Non-English language (P = .01), and absence of deflazacort prescription (P = .02) were significantly associated with higher percentage of nights used while Hispanic ethnicity (P = .01), low household income (P = .02), and absence of deflazacort prescription (P = .02) were significantly associated with higher nightly usage. Based on univariable analysis, older age and declining forced vital capacity were associated with increased percentage of nights used and increased average nightly usage. DISCUSSION: Certain clinical and socioeconomic determinants had a significant impact on NIV adherence in DMD patients, providing insight into those at risk for high versus low compliance with respiratory therapy.

Using machine learning to improve our understanding of COVID-19 infection in children.

PURPOSE: Children are at elevated risk for COVID-19 (SARS-CoV-2) infection due to their social behaviors. The purpose of this study was to determine if usage of radiological chest X-rays impressions can help predict whether a young adult has COVID-19 infection or not. METHODS: A total of 2572 chest impressions from 721 individuals under the age of 18 years were considered for this study. An ensemble learning method, Random Forest Classifier (RFC), was used for classification of patients suffering from infection. RESULTS: Five RFC models were implemented with incremental features and the best model achieved an F1-score of 0.79 with Area Under the ROC curve as 0.85 using all input features. Hyper parameter tuning and cross validation was performed using grid search cross validation and SHAP model was used to determine feature importance. The radiological features such as pneumonia, small airways disease, and atelectasis (confounded with catheter) were found to be highly associated with predicting the status of COVID-19 infection. CONCLUSIONS: In this sample, radiological X-ray films can predict the status of COVID-19 infection with good accuracy. The multivariate model including symptoms presented around the time of COVID-19 test yielded good prediction score.

A data-driven model for early prediction of need for invasive mechanical ventilation in pediatric intensive care unit patients.

RATIONALE: Acute respiratory failure is a life-threatening clinical outcome in critically ill pediatric patients. In severe cases, patients can require mechanical ventilation (MV) for survival. Early recognition of these patients can potentially help clinicians alter the clinical course and lead to improved outcomes. OBJECTIVES: To build a data-driven model for early prediction of the need for mechanical ventilation in pediatric intensive care unit (PICU) patients. METHODS: The study consists of a single-center retrospective observational study on a cohort of 13,651 PICU patients admitted between 1/01/2010 and 5/15/2018 with a prevalence of 8.06% for MV due to respiratory failure. XGBoost (extreme gradient boosting) and a convolutional neural network (CNN) using medication history were used to develop a prediction model that could yield a time-varying "risk-score"-a continuous probability of whether a patient will receive MV-and an ideal global threshold was calculated from the receiver operating characteristics (ROC) curve. The early prediction point (EPP) was the first time the risk-score surpassed the optimal threshold, and the interval between the EPP and the start of the MV was the early warning period (EWT). Spectral clustering identified patient groups based on risk-score trajectories after EPP. RESULTS: A clinical and medication history-based model achieved a 0.89 area under the ROC curve (AUROC), 0.6 sensitivity, 0.95 specificity, 0.55 positive predictive value (PPV), and 0.95 negative predictive value (NPV). Early warning time (EWT) median [inter-quartile range] of this model was 9.9[4.2-69.2] hours. Clustering risk-score trajectories within a six-hour window after the early prediction point (EPP) established three patient groups, with the highest risk group's PPV being 0.92. CONCLUSIONS: This study uses a unique method to extract and apply medication history information, such as time-varying variables, to identify patients who may need mechanical ventilation for respiratory failure and provide an early warning period to avert it.

Leveraging Electronic Health Records for Guideline-Based Asthma Documentation.

BACKGROUND: Asthma is the most common pediatric chronic disease; thus, clinical guidelines have been developed for its assessment and management, which rely on systematic symptom documentation. Electronic health records (EHR) have the potential to record clinical data systematically; however, variability in documentation persists. OBJECTIVE: To identify if the use of a structured asthma template is associated with increased guideline-based asthma documentation and clinical outcomes when compared with the use of nonstructured ones. METHODS: We performed a retrospective case-control study comparing the use of nonstructured templates (NSTs) and asthma-structured templates (ASTs) in new patient and first follow-up encounters, evaluated by pediatric pulmonologists between March 2016 and December 2021. Asthma history items were selected following clinical guidelines, summarized in 29 items for new and 22 items for follow-up encounters. Associations with demographic, spirometry, and health care utilization were explored. RESULTS: A total of 546 initial encounters were included; 450 used structured templates. The use of an AST was associated with higher documentation of asthma items in initial and follow-up encounters. Linear regression analysis showed that the use of ASTs was associated with a 28.2% and 39.65% increase in asthma history completeness (in initial and follow-up encounters, respectively), compared with the use of NSTs. AST use was associated with higher rates of systemic steroid prescriptions within 12 months. No other differences were observed after adjusting for asthma severity. CONCLUSIONS: Using asthma-specific structured templates was associated with increased guideline-based asthma documentation. Leveraging the EHR as a clinical and research tool has the potential to improve clinical practice.