Respiratory tract viral infection continues to be among the most common reasons for emergency department visits and hospitalization of children, particularly infants younger than 1 year, in the United States. Throughout the years, clinicians have considered respiratory syncytial virus followed by influenza as the most common pathogens responsible. Over the past decade, new viruses have been discovered through both more specific testing and the finding of new agents causing infection. This includes human metapneumovirus, which leads to similar but often epidemiologically more severe clinical symptoms than respiratory syncytial virus. Other agents responsible for lower respiratory tract infection include Coronavirus (severe acute respiratory syndrome), Bocavirus, and others. This review serves to focus on some of the recent literature on these agents and the clinical impact they have on pediatric lung infection.

ObjectiveTo evaluate a proposed natural language processing (NLP) and machine-learning based automated method to risk stratify abdominal pain patients by analyzing the content of the electronic health record (EHR).MethodsWe analyzed the EHRs of a random sample of 2100 pediatric emergency department (ED) patients with abdominal pain, including all with a final diagnosis of appendicitis. We developed an automated system to extract relevant elements from ED physician notes and lab values and to automatically assign a risk category for acute appendicitis (high, equivocal, or low), based on the Pediatric Appendicitis Score. We evaluated the performance of the system against a manually created gold standard (chart reviews by ED physicians) for recall, specificity, and precision.ResultsThe system achieved an average F-measure of 0.867 (0.869 recall and 0.863 precision) for risk classification, which was comparable to physician experts. Recall/precision were 0.897/0.952 in the low-risk category, 0.855/0.886 in the high-risk category, and 0.854/0.766 in the equivocal-risk category. The information that the system required as input to achieve high F-measure was available within the first 4 h of the ED visit.ConclusionsAutomated appendicitis risk categorization based on EHR content, including information from clinical notes, shows comparable performance to physician chart reviewers as measured by their inter-annotator agreement and represents a promising new approach for computerized decision support to promote application of evidence-based medicine at the point of care.

In this pilot study, a significant percentage of children undergoing common emergency procedures exhibited an appreciable burden of negative behavior change at 1 week; these results demonstrate the need for further rigorous investigation of predictors of these changes and interventions, which can ameliorate these changes.

No abstract

No abstract