Understanding the circumstances of paediatric fall injuries: a machine learning analysis of NEISS narratives.

OBJECTIVES: Falls are the leading cause of non-fatal injury among young children. The aim of this study was to identify and quantify the circumstances contributing to medically attended paediatric fall injuries among 0-4 years old. METHODS: Cross-sectional data for falls among kids under 5 years recorded between 2012 and 2016 in the National Electronic Injury Surveillance System was obtained. A sample of 4546 narratives was manually coded for: (1) where the child fell from; (2) what the child fell onto; (3) the activities preceding the fall and (4) how the fall occurred. A natural language processing model was developed and subsequently applied to the remaining uncoded data to yield a set of 91 325 cases coded for what the child fell from, fell onto, the activities preceding the fall, and how the fall occurred. Data were descriptively tabulated by age and disposition. RESULTS: Children most often fell from the bed accounting for one-third (33%) of fall injuries in infants, 13% in toddlers and 12% in preschoolers. Children were more likely to be hospitalised if they fell from another person (7.4% vs 2.6% for all other sources; p<0.01). After adjusting for age, the odds of a child being hospitalised following a fall from another person were 2.1 times higher than falling from other surfaces (95% CI 1.6 to 2.7). CONCLUSIONS: The prevalence of injuries due to falling off the bed, and the elevated risk of serious injury from falling from another person highlights the need for more robust and effective communication to caregivers on fall injury prevention.

Number Needed to Screen for Tuberculosis Disease Among Children: A Systematic Review.

CONTEXT: Improving detection of pediatric tuberculosis (TB) is critical to reducing morbidity and mortality among children. OBJECTIVE: We conducted a systematic review to estimate the number of children needed to screen (NNS) to detect a single case of active TB using different active case finding (ACF) screening approaches and across different settings. DATA SOURCES: We searched 4 databases (PubMed, Embase, Scopus, and the Cochrane Library) for articles published from November 2010 to February 2020. STUDY SELECTION: We included studies of TB ACF in children using symptom-based screening, clinical indicators, chest x-ray, and Xpert. DATA EXTRACTION: We indirectly estimated the weighted mean NNS for a given modality, location, and population using the inverse of the weighted prevalence. We assessed risk of bias using a modified AXIS tool. RESULTS: We screened 27 221 titles and abstracts, of which we included 31 studies of ACF in children < 15 years old. Symptom-based screening was the most common screening modality (weighted mean NNS: 257 [range, 5-undefined], 19 studies). The weighted mean NNS was lower in both inpatient (216 [18-241]) and outpatient (67 [5-undefined]) settings (107 [5-undefined]) compared with community (1117 [28-5146]) and school settings (464 [118-665]). Risk of bias was low. LIMITATIONS: Heterogeneity in the screening modalities and populations make it difficult to draw conclusions. CONCLUSIONS: We identified a potential opportunity to increase TB detection by screening children presenting in health care settings. Pediatric TB case finding interventions should incorporate evidence-based interventions and local contextual information in an effort to detect as many children with TB as possible.