Abstract
Objectives:
Falls are the leading cause of nonfatal injury among young children. The aim of this study was to identify and quantify the circumstances contributing to medically-attended pediatric fall injuries among 0–4 year olds.
Methods:
Cross-sectional data for falls among kids under 5 years recorded between 2012–2016 in the National Electronic Injury Surveillance System was obtained. A sample of 4,546 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 hospitalized 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 hospitalized following a fall from another person were 2.1 times higher than falling from other surfaces (95% CI 1.6–2.7).
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.
Background
Falls are the leading cause of nonfatal injury among children aged 0–14 years in the United States, leading to approximately 2 million emergency room visits and over 30,000 hospitalizations each year. These falls result in over $7 billion in medical costs and $16 billion in work loss. 1 Among children 0–14 in 2019, the rate of non-fatal pediatric fall injuries was highest among 1 to 2-year-olds (5,848 per 100,000) and 3 to 4 year-olds (4,124 per 100,000), followed by infants less than 1 year (3,670 per 100,000). 1 Falls are also the leading cause of traumatic brain injury (TBI) among children, accounting for 90% of TBIs in children aged 0–4 years and 42% of TBIs in children 5–14 years old. 2 Children under 5 years of age are most likely to experience fall injuries at home, while school age children and adolescents tend to experience fall injuries at school or during sporting activities. 3,4
Despite the prevalence of fall injuries among children, there is limited evidence on how to prevent them. A recent review established strong evidence for reducing the use of baby walkers, education about and distribution of stair gates, and mandates for window guards, but the authors did not find research on strategies to prevent falls from furniture. 5 The American Academy of Pediatrics recommends adult supervision, using playpens or cribs, and removing sharp-edged furniture and surfaces that offer potential for unintended climbing. 6 Recent analyses using data from national samples have described the demographic characteristics of children experiencing fall injuries as well as the consumer products associated with those falls, 3,4 but little is known about the circumstances leading up to and surrounding fall events, information essential to designing effective prevention strategies.
The aim of this study was to identify and quantify the circumstances contributing to medically-attended pediatric fall injuries among a nationally representative sample of 0–4 year olds to inform injury prevention recommendations. The analysis harnessed the power of machine learning techniques and the rich information contained in case narratives within the National Electronic Injury Surveillance System – All Injury Program (NEISS-AIP) to 1) describe the circumstances in which these injuries occurred, and 2) examine the relationship between the fall circumstances and injury severity.
Methods
The NEISS-AIP collects data on non-fatal injuries from a sample of 66 hospital emergency departments in the US. The data are collected by the Consumer Product Safety Commission (CPSC) in partnership with CDC’s National Center for Injury Prevention and Control and are weighted to be nationally representative. In addition to demographic characteristics, diagnosis & disposition, mechanism and intent of injury, a narrative field of up to 400 characters captures notes about the reason for the emergency room visit. 7–9 As no coded, quantiative variables on the circumstances for the emergency room visit are available in the NEISS data, the narrative was the primary source of information for this analysis.
Using the 2015 data (most recently available at the time of this study), a randomly selected sample of 4,546 case narratives was manually coded for four characteristics: 1) what the child fell from; 2) what the child fell onto; 3) the action leading to the fall (e.g., if the child slipped, was dropped, etc.); and 4) the precipitating event (e.g. what the child was doing immediately before the fall). These four characteristics were selected by the study team as circumstances that help describe the context of fall injuries and contributing factors that may inform prevention. The manually coded sample was randomly selected by year of age to ensure the distribution of ages in the coded sample would match that of the larger sample. A coding dictionary was established through a content analysis the first 250 case narratives. For the fell from and fell onto characteristics, the codes were guided by product codes from CPSC; additional codes for falls from or onto non-product related items (i.e., from another person, or from a standing position), and codes for fall action and precipitating event were developed and assigned based on a review of the narratives. The remaining selected narratives were then coded by a single coder according to the coding dictionary. A study co-author met regularly with the coder and reviewed a sample of the codings to verify consistency with the coding dictionary.
Using the sample of manually coded cases as the “gold standard”, a machine learning model was designed to predict the four characteristics of interest. Narratives were pre-processed to optimize the text for natural language processing (NLP) by the spaCy Python library. 10 Subsequently, NLP was used to identify the type of falls in the narratives. Because the narratives are centered around a fall event, we trained deep learning event classification pipelines using state-of-the-art transformer models, including BERT which achieve high accuracy on well-established shared tasks.11 In particular, we used the FLAIR text classification Python library,12 with pre-trained BERT base model from Huggingface.13 After fall events were labeled, they were translated and mapped to the coded variables via a post-processing pipeline in spaCy. After an optimal model was developed, it was applied to the remaining uncoded narratives to yield a final coded set of over 90,000 cases coded for the four characteristics of interest: what the child fell from, what the child fell onto, the fall action, and the precipitating event.
Descriptive statistics of child’s age (grouped as: infants < 1 year, toddlers 1–2 years, and preschoolers 3–4 years), sex, race, and disposition (classified as hospitalized or treated and released) were generated for the entire sample. Tabulations for the four circumstance characteristics were generated by age group. Subsequently, we tabulated the circumstance characteristics by disposition, and selected those fall circumstances with at least 4% hospitalized and greater than 5000 cases to examine the relationship between circumstances and injury severity. These two criteria were selected because they represent those circumstances at elevated risk for hospitalization with sufficient data for statistical comparisons. Relative risk was established with a Rao-Scott chi-square test, and odds of hospitalization was estimated using logistic regression adjusting for age. Statistical analyses were conducted in SAS 9.4 (Cary, SC).
Ethics Statement.
The Johns Hopkins School of Public Health IRB exempted this study from review and oversight for the use of anonymous, publicly available data.
Patient and public involvement.
No patients or members of the public were involved in the design, conduct, reporting or dissemination plans of our research.
Results
A total of 91,325 falls among children under 5 years were recorded in the NEISS-AIP data between 2012–2016, reflecting a weighted estimate of 3.87 million total (95%CI: 2.94 million – 4.80 million) and 773,674 annual (95%CI: 588,161 – 959,187) fall injuries treated in US emergency departments. The majority of these injuries were treated and released, however 2.7% resulted in hospitalization. See Table 1 for additional descriptive statistics on sex, age, and race.
Table 1.
National Estimates of Pediatric Falls in the U.S., NEISS-AIP, 2012–2016
| Sample Size | Total Estimated Injuries, 2012–2016 | Injuries per 100,000 (95%CI) | |
|---|---|---|---|
| Age | |||
| Infants (<12 months) | 15578 | 604,964 (15.6%) | 16,296 (11,817, 20,774) |
| Toddlers (1–2 years) | 44675 | 1,912,073 (49.4%) | 24,148 (18,478, 29,819) |
| Preschoolers (3–4 years) | 31072 | 1,351,334 (34.9%) | 16,278 (12,434, 20,122) |
| Sex | |||
| Male | 52452 | 2,227,609 (57.6%) | 21,866 (16,725, 27,006) |
| Female | 38871 | 1,640,672 (42.4%) | 16,837 (12,683, 20,991) |
| Race | |||
| Black/African American | 17430 | 394,779 (10.2%) | 13,984 (8,505, 19,463) |
| White | 40665 | 2,108,729 (54.5%) | 15,881 (11,583, 20,179) |
| Other | 15069 | 608,429 (15.7%) | 15,882 (6,223, 25,541) |
| Unknown | 18161 | 756,434 (19.6%) | |
| Body Part Injured | |||
| Face | 32980 | 1,440,189 (37.2%) | |
| Head | 39472 | 1,674,275 (43.3%) | |
| Trunk | 1628 | 74,540 (1.9%) | |
| Upper Extremity | 11962 | 480,341 (12.4%) | |
| Lower Extremity | 5283 | 199,026 (5.1%) | |
| Diagnosis | |||
| Concussion | 1973 | 81,796 (2.1%) | |
| Contusion abrasion, hematoma | 14128 | 723,443 (18.7%) | |
| Dislocation | 1243 | 55,791 (1.4%) | |
| Fracture, sprain or strain | 13446 | 482,804 (12.5%) | |
| Internal injury | 27399 | 1,102,449 (28.5%) | |
| Laceration | 28468 | 1,268,136 (32.8%) | |
| Other | 4666 | 153,905 (4%) | |
| Disposition | |||
| Treated & Released | 87653 | 3,763,902 (97.3%) | |
| Hospitalized | 3672 | 104,470 (2.7%) | |
The circumstances leading to fall injuries are described in Table 2. Infants (<12 months) most often fell from the bed (33%), primarily onto the floor (97%). Infants also commonly fell from baby equipment (16%), or from another person (11%). Toddlers (1–2 years) and preschoolers (3–4 years) fell from a standing or seated position in 17% and 18% of cases respectively, primarily during some type of independent movement (51% and 53% respectively). Falls from the bed were also common in these age groups (13% in toddlers and 12% in preschoolers), usually preceded by independent movement (29% and 43% respectively). The fall action could not be identified in the majority (79%) of cases; of those cases where the action was identified, trips (6.7%) and slips (3.8%) were the most frequent. The precipitating event was identified in 52% of cases, with children most commonly moving independently (25%) such as playing or running immediately before the fall.
Table 2:
Estimates of Pediatric Fall Circumstances by Age, 2012–2016
| Total (0–4 years) N (Column %) |
Infants (<12 mos) N (Column %) |
Toddlers (1–2 yrs) N (Column %) |
Preschoolers (3–4 yrs) N (Column %) |
|
|---|---|---|---|---|
| Fell From | ||||
| Baby Equipment | 186,240 (4.8%) | 95,100 (15.7%) | 80,670 (4.2%) | 10,470 (0.8%) |
| Beds | 604,766 (15.6%) | 201,430 (33.3%) | 241,522 (12.6%) | 161,815 (12.0%) |
| Chairs | 220,499 (5.7%) | 13,427 (2.2%) | 133,691 (7.0%) | 73,381 (5.4%) |
| Housing Elements | 63,429 (1.6%) | 9,247 (1.5%) | 30,045 (1.6%) | 24,137 (1.8%) |
| Play Equipment | 267,488 (6.9%) | 7,910 (1.3%) | 92,284 (4.8%) | 167,294 (12.4%) |
| Sofas & Couches | 265,005 (6.9%) | 53,219 (8.8%) | 131,190 (6.9%) | 80,595 (6.0%) |
| Stairs/Steps | 378,847 (9.8%) | 33,373 (5.5%) | 221,747 (11.6%) | 123,726 (9.2%) |
| Miscellaneous Furniture | 114,410 (3%) | 10,165 (1.7%) | 56,771 (3.0%) | 47,474 (3.5%) |
| Other Product | 257,888 (6.7%) | 21,459 (3.5%) | 134,371 (7.0%) | 102,058 (7.6%) |
| Standing/Seated Child | 608,049 (15.7%) | 35,982 (5.9%) | 330,398 (17.3%) | 241,668 (17.9%) |
| Other Person | 109,429 (2.8%) | 64,084 (10.6%) | 31,777 (1.7%) | 13,568 (1.0%) |
| Unspecified | 791,649 (20.5%) | 59,361 (9.8%) | 427,280 (22.4%) | 305,008 (22.6%) |
| Fell Onto | ||||
| Baby Equipment | 7,635 (0.2%) | 3,065 (0.5%) | 3,166 (0.2%) | 1,403 (0.1%) |
| Ground/Floor | 2,478,035 (64.1%) | 492,565 (81.4%) | 1,142,953 (59.8%) | 842,517 (62.4%) |
| Housing Elements | 314,049 (8.1%) | 18,015 (3.0%) | 175,526 (9.2%) | 120,508 (8.9%) |
| Play Equipment | 108,109 (2.8%) | 6,900 (1.1%) | 55,527 (2.9%) | 45,682 (3.4%) |
| Stairs/Steps | 386,751 (10%) | 47,668 (7.9%) | 216,052 (11.3%) | 123,031 (9.1%) |
| Miscellaneous Furniture | 558,082 (14.4%) | 35,892 (5.9%) | 310,713 (16.3%) | 211,476 (15.7%) |
| Other Product | 12,153 (0.3%) | 1419 (0.1%) | 6,494 (0.3%) | 5,239 (0.4%) |
| Other Person | 140 (0%) | 0 (0%) | 140 (0.0%) | 0 (0%) |
| Unspecified | 2,744 (0.1%) | 233 (0.0%) | 1,175 (0.1%) | 1,337 (0.1%) |
| Fall Action | ||||
| Dropped | 98,012 (2.5%) | 61,811 (10.7%) | 26,971 (1.5%) | 9,230 (0.7%) |
| Lost Balance | 529 (0%) | 0 (0%) | 154 (0.0%) | 375 (0.0%) |
| Rolled | 113,468 (2.9%) | 75,205 (13.1%) | 27,893 (1.5%) | 10,370 (0.8%) |
| Slipped | 145,875 (3.8%) | 9,877 (1.7%) | 69,940 (3.8%) | 66,058 (5.1%) |
| Tripped | 258,113 (6.7%) | 8,041 (1.4%) | 142,752 (7.8%) | 107,321 (8.3%) |
| Other | 21,927 (0.6%) | 10,779 (1.9%) | 6,519 (0.4%) | 4,629 (0.4%) |
| Unspecified | 3,050,171 (78.8%) | 409,333 (71.2%) | 1,551,210 (85.0%) | 1,089,628 (84.6%) |
| Precipitating Event | ||||
| Bathing | 89,845 (2.3%) | 5,566 (1.0%) | 47,615 (2.6%) | 36,664 (2.8%) |
| Dependent Movement | 272,748 (7.1%) | 75,488 (13.1%) | 110,441 (6.1%) | 86,819 (6.7%) |
| Independent Movement | 972,545 (25.1%) | 42,072 (7.3%) | 462,870 (25.4%) | 467,604 (36.3%) |
| Stationary | 507,829 (13.1%) | 173,299 (30.1%) | 232,910 (12.8%) | 101,619 (7.9%) |
| Unspecified | 1,845,127 (47.7%) | 278,622 (48.5%) | 971,601 (53.2%) | 594,904 (46.2%) |
Children were more likely to be hospitalized if they fell from another person (7.4% vs. 2.6% for all other sources; p<0.01) (see Table 3). These children were most likely dropped (75%) during dependent movement (i.e., being carried by an adult, 74%). After adjusting for age, the odds of a child being hospitalized following a fall from another person were 2.1 times higher than falling from other surfaces (95% CI 1.6–2.7). Relative to other sources of falls, children falling from baby equipment (4.5% vs. 2.6%; p<0.01) and miscellaneous furniture such as tables, desks and dressers (4.7% vs. 2.6%; p<0.01) had elevated rates of hospitalization, although only falls from furniture remained statistically significant after adjusting for age. The odds of being hospitalized due to a fall from a being dropped (vs. other fall action) and following dependent movement (vs. other precipitating events) were also elevated after adjusting for age (see Table 4).
Table 3.
Pediatric Fall Circumstances by Disposition
| Hospitalized N (Row %) |
Treated & Released N (Row %) |
|
|---|---|---|
| Fell From | ||
| Baby Equipment | 8,343 (4.5%) | 177,897 (95.5%) |
| Beds | 21,712 (3.6%) | 583,054 (96.4%) |
| Chairs | 4,181 (1.9%) | 216,317 (98.1%) |
| Housing Elements | 2,844 (4.5%) | 60,585 (95.5%) |
| Play Equipment | 9,410 (3.5%) | 258,078 (96.5%) |
| Sofas & Couches | 7,210 (2.7%) | 257,795 (97.3%) |
| Stairs/Steps | 8,207 (2.2%) | 370,640 (97.8%) |
| Miscellaneous Furniture | 5,324 (4.7%) | 109,086 (95.3%) |
| Other Product | 9,249 (3.6%) | 248,639 (96.4%) |
| Other Person | 8,066 (7.4%) | 101,363 (92.6%) |
| Standing/Seated Child | 9,279 (1.5%) | 598,770 (98.5%) |
| Unspecified | 10,644 (1.3%) | 781,005 (98.7%) |
| Fell Onto | ||
| Baby Equipment | 381 (5.0%) | 7,254 (95.0%) |
| Ground/Floor | 85,072 (3.4%) | 2,392,963 (96.6%) |
| Housing Elements | 2,743 (0.9%) | 311,307 (99.1%) |
| Play Equipment | 1,658 (1.5%) | 106,452 (98.5%) |
| Stairs/Steps | 9,786 (2.5%) | 376,965 (97.5%) |
| Miscellaneous Furniture | 4,633 (0.8%) | 553,448 (99.2%) |
| Other Product | 173 (1.4%) | 11,979 (98.6%) |
| Other Person | 0 (0%) | 140 (100.0%) |
| Unspecified | 24 (0.9%) | 2,860 (99.1%) |
| Fall Action | ||
| Dropped | 7,571 (7.7%) | 90,440 (92.3%) |
| Lost Balance | 0 (0%) | 529 (100.0%) |
| Rolled | 3,603 (3.2%) | 109,865 (96.8%) |
| Slipped | 3,625 (2.5%) | 142,250 (97.5%) |
| Tripped | 3,269 (1.3%) | 254,844 (98.7%) |
| Other | 1,108 (5.1%) | 20,818 (94.9%) |
| Unspecified | 80,902 (2.7%) | 2,969,268 (97.3%) |
| Precipitating Event | ||
| Bathing | 1,010 (1.1%) | 88,835 (98.9%) |
| Dependent Movement | 12,514 (4.6%) | 260,234 (95.4%) |
| Independent Movement | 27,025 (2.8%) | 945,520 (97.2%) |
| Stationary | 16,086 (3.2%) | 491,742 (96.8%) |
| Unspecified | 43,444 (2.4%) | 1,801,683 (97.6%) |
Table 4.
Risk of hospitalization for select circumstances of falls
| Risk of hospitalization relative to other fall circumstances | Odds of hospitalization, adjusted for age | |
|---|---|---|
| Fell from other person (vs. all other fall from sources) | 7.4% vs. 2.6% (p<0.01) | 2.09 (1.62–2.70) |
| Fell from misc. furniture | 4.7% vs. 2.6% (p<0.01) | 1.95 (1.47–2.60) |
| Fell from baby equipment | 4.5% vs. 2.6% (p<0.01) | 1.25 (0.84–1.86) |
| Dropped (vs. other fall actions) | 7.7% vs. 2.6% (p<0.01) | 2.13 (1.53–2.98) |
| Dependent Movement (vs. other precipitating events) | 4.6% vs. 2.6% (p<0.01) | 1.60 (1.23–2.09) |
Discussion
An estimated 773,000 fall injuries to children 4 and under were treated in US emergency departments annually between 2012–2016, resulting in over 20,000 hospitalizations per year. This study identified falls from beds as a leading contributor to medically attended fall injuries, particularly among infants. In addition, a large share of falls from beds in toddlers and preschoolers were preceded by independent movement such as playing or jumping. These cases likely represent avoidable injuries. Our results are consistent with other analyses of fall injuries. Another study using NEISS data estimated that beds were associated with over 26% of medically-attended infant falls and 10% of falls among 1–4-year-olds.3 And data from pediatric trauma registries have identified falls from the bed as a leading source of falls requiring hospitalization.14,15 While it may not be possible to eliminate children jumping and playing on beds, prevention messages should emphasize the associated risks, recommend close supervision, and educate caregivers about the potential for soft surfaces around beds to offer some modicum of protection.
This analysis also highlights the elevated risk of serious injury for a child falling from another person such as a caregiver. In our analysis, children who fell from another person were twice as likely to be hospitalized than children who fell from any other source. Analysis of data from a trauma registries also identified falls from a caregiver’s arms as a leading source of falls leading to hospitalization.14,15 These falls occur most often among infants; given the nature of child development, infants spend more time being held and carried by a caregiver. In our analysis, even after adjusting for the child’s age, falls from another person were more likely to result in serious injury. This underscores the need for messaging caution when holding young children. We do not have data as to where these fall injuries occurred, such as on stairs, although falls on stairs are known to be particularly hazardous for children as well as adults.16 Nevertheless, our data strongly suggest that prevention messages regarding the risks of falling while carrying a baby around the home are needed. To our knowledge, this information is not routinely shared with parents in the most commonly available fall prevention literature. Prevention strategies may include attention to footwear, keeping one hand free for holding onto handrails on stairs, and having soft surfacing where possible.
Our analysis shows an increase in the share of falls due to independent movement as children age. Increased independent movement is expected as children develop but there is a need for parents to understand their child’s limits, to establish safe spaces for the child to play, to install soft surfacing where possible, and to be vigilant with supervision behaviors. Current recommendations advise parents to stop using a crib between 18–36 months to prevent the child from climbing and falling out of the crib. This logic can also be applied to the use of playpens and stairgates, but more attention is needed to understand how to help families create a home environment that is safe for young children.
Large investments have been made into national data sources such as NEISS and National Emergency Department Sample (NEDS) to collect data on medically attended injuries, however the potential for these data to directly inform injury prevention relies on having sufficient context about the events leading up to the injury. Based on our experience in this study, we believe that a new emphasis on including prevention-related information in the database is urgently needed. An additional field dedicated to capturing the precipitating event would increase the utility of these systems for prevention. In our analysis, the precipitating event was extracted from the narrative using natural language processing, however, that information was unspecified in nearly half of the case narratives. Case narratives have been traditionally used as a catch-all to describe the injury event as well as a description of what was happening when the injury occurred. 8 A data field dedicated to capturing precipitating events separate from the injury diagnoses could yield information about the sequence of events leading up to the injury with the richness needed to identify opportunities for intervention and prevention.
This analysis relied on narratives contained within NEISS-AIP which are limited to injuries treated in the ED. These data do not reflect falls treated in other medical settings such as primary and urgent care. The utility of this analysis is also limited by the level of detail contained within the narrative field; over 20% of narratives made no mention of what the child fell from, and the fall action was unspecified in the majority of cases. Additionally, no information on the height of the fall were available. However, an important strength of this analysis is the use of natural language processing to code a large volume of data for these fall circumstances, allowing us to produce national estimates of substantive contextual information relevant to prevention. To our knowledge, analysis of narrative text from NEISS has been limited to manually coded fields, which are labor intensive, or simple text searches, which have limited utility. 17–19 This analysis demonstrates the power of machine learning to inform injury prevention and the potential for NEISS to be used in that capacity.
Current fall prevention recommendations advise parents to supervise small children closely in the home, discourage climbing on furniture, and to use safety features of baby equipment. 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.
What is already known on this topic
Falls are the leading cause of nonfatal injury and the leading cause of traumatic brain injury (TBI) among children aged 0–14 years. Young children under 5 years are mostly likely to experience fall injuries at home. Despite the prevalence of fall injuries among children, there is limited information on the circumstances contributing to falls, making it challenging to craft meaningful prevention messages.
What this study adds
This study identifies circumstances of pediatric fall injuries and those most likely to result in hospitalization. The findings highlight the prevalence of injuries due to falling off the bed, and the risk of serious injury from falling from another person.
How this study might affect research, practice or policy
This study identifies opportunities for improving communication to caregivers on fall injury prevention.
Funding:
This work was supported by a grant from the National Institute for Child Health and Development (grant number 1R21HD099513) and from the American Public Health Association’s Injury and Violence Prevention Data Science Demonstration Program.
Footnotes
Conflicts of Interest: There are no conflicts of interest to disclose.
References
- 1.Centers for Disease Control and Prevention. WISQARS. https://www.cdc.gov/injury/wisqars/
- 2.Taylor C, Bell J, Breiding M, Xu L. Traumatic Brain Injury–Related Emergency Department Visits, Hospitalizations, and Deaths — United States, 2007 and 2013. Morb Mortal Wkly Rep MMWR Surveill Summ. 2017;66. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 3.Ali B, Lawrence B, Miller T, Swedler D, Allison J. Consumer Products Contributing to Fall Injuries in Children Aged <1 to 19 Years Treated in US Emergency Departments, 2010 to 2013: An Observational Study. Glob Pediatr Health. 2019;6. doi: 10.1177/2333794X18821941 [DOI] [PMC free article] [PubMed] [Google Scholar]
- 4.Wang D, Zhao W, Wheeler K, Yang G, Xiang H. Unintentional fall injuries among US children: a study based on the National Emergency Department Sample. Int J Inj Contr Saf Promot. 2013;20(1):27–35. doi: 10.1080/17457300.2012.656316 [DOI] [PubMed] [Google Scholar]
- 5.Gielen AC, McDonald EM, Shields W. Unintentional Home Injuries Across the Life Span: Problems and Solutions. Annu Rev Public Health. 2015;36(1):231–253. doi: 10.1146/annurev-publhealth-031914-122722 [DOI] [PubMed] [Google Scholar]
- 6.Bull MJ, Agran P, Gardener HG, et al. Falls from heights: Windows, roofs, and balconies. Pediatrics. 2001;107(5):1188–1191. doi: 10.1542/peds.107.5.1188 [DOI] [PubMed] [Google Scholar]
- 7.Centers for Disease Control and Prevention (CDC). Data Sources for WISQARS Nonfatal - NCIPC. Accessed February 10, 2021. https://www.cdc.gov/ncipc/wisqars/nonfatal/datasources.htm
- 8.US Consumer Product Safety Commission. NEISS Coding Manual.; 2013. Accessed February 8, 2022. www.cpsc.gov
- 9.[dataset] Centers for Disease Control & Prevention, U.S. Consumer Product Safety Commission. National Electronic Injury Surveillance System All Injury Program. doi: 10.3886/ICPSR37274.v1 [DOI]
- 10.Honnibal M, Montani I, Van Landeghem S, Boyd A. spaCy: Industrial-strength Natural Language Processing in Python. Zenodo. Published online 2020. doi: 10.5281/zenodo.1212303 [DOI] [Google Scholar]
- 11.Devlin J, Chang MW, Lee K, Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.; 2019:4171–4186. [Google Scholar]
- 12.Akbik A, Bergmann T, Blythe D, Rasul K, Schweter S, Vollgraf R. FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics; 2019:54–59. doi: 10.18653/V1/N19-4010 [DOI] [Google Scholar]
- 13.Hugging Face – The AI community building the future. Accessed February 28, 2022. https://huggingface.co/
- 14.Chaudhary S, Figueroa J, Shaikh S, et al. Pediatric falls ages 0–4: understanding demographics, mechanisms, and injury severities. Inj Epidemiol. 2018;5(1):77–87. doi: 10.1186/S40621-018-0147-X/FIGURES/1 [DOI] [PMC free article] [PubMed] [Google Scholar]
- 15.Unni P, Locklair MR, Morrow SE, Estrada C. Age variability in pediatric injuries from falls. Am J Emerg Med. 2012;30(8):1457–1460. doi: 10.1016/J.AJEM.2011.12.001 [DOI] [PubMed] [Google Scholar]
- 16.Blazewick DH, Chounthirath T, Hodges NL, Collins CL, Smith GA. Stair-related injuries treated in United States emergency departments. Am J Emerg Med. 2018;36(4):608–614. doi: 10.1016/J.AJEM.2017.09.034 [DOI] [PubMed] [Google Scholar]
- 17.Graves JM, Whitehill JM, Hagel BE, Rivara FP. Making the most of injury surveillance data: Using narrative text to identify exposure information in case-control studies. Injury. 2015;46(5):891–897. doi: 10.1016/j.injury.2014.11.012 [DOI] [PMC free article] [PubMed] [Google Scholar]
- 18.Shields W, McDonald E, Frattaroli S, Bishai D, Ma X, Gielen A. Structural housing elements associated with home injuries in children. Inj Prev. 2016;22:105–109. [DOI] [PubMed] [Google Scholar]
- 19.Shields WC, McDonald EM, Pfisterer K, Gielen AC. Scald burns in children under 3 years: an analysis of NEISS narratives to inform a scald burn prevention program. Inj Prev J Int Soc Child Adolesc Inj Prev. 2015;21(5):296–300. doi: 10.1136/injuryprev-2015-041559 [DOI] [PubMed] [Google Scholar]