Related Experiment Video
Updated: Jul 24, 2025
Design and Analysis for Fall Detection System Simplification
Published on: April 6, 2020
Understanding the circumstances of paediatric fall injuries: a machine learning analysis of NEISS narratives
Elise Omaki1, Wendy Shields2, Masoud Rouhizadeh3
1Center for Injury Research and Policy, Johns Hopkins University Bloomberg School of Public Health, Baltimore, Maryland, USA eperry@jhu.edu.
Insights
Falls from beds are common injuries in young children. Falling from another person significantly increases hospitalization risk, emphasizing caregiver education for fall prevention.
Area of Science:
- Pediatric injury prevention
- Public health surveillance
- Child safety research
Background:
- Falls represent the primary cause of non-fatal injuries in young children.
- Understanding fall circumstances is crucial for developing effective prevention strategies.
Purpose of the Study:
- To identify and quantify the specific circumstances leading to medically attended pediatric fall injuries in children aged 0-4 years.
Main Methods:
- Utilized cross-sectional data from the National Electronic Injury Surveillance System (2012-2016).
- Manually coded a sample of fall narratives and applied natural language processing to a larger dataset (91,325 cases).
- Coded variables included fall source, landing surface, preceding activities, and fall mechanism.
Main Results:
- Falls from beds were the most frequent cause of injury (33% in infants, 13% in toddlers, 12% in preschoolers).
- Children falling from another person had a higher hospitalization rate (7.4% vs. 2.6%) and 2.1 times greater odds of hospitalization compared to other fall sources.
- Data were analyzed and tabulated by age and disposition.
Conclusions:
- The high incidence of bed falls and increased hospitalization risk from falling off another person necessitate improved caregiver communication on fall prevention.
- Targeted educational interventions are needed to address common fall scenarios and reduce serious injuries in young children.
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.
