Prehospital Factors Predict Outcomes in Pediatric Trauma: A Principal Component Analysis

Use of artificial intelligence to support prehospital traumatic injury care: A scoping review

Background

Artificial intelligence (AI) has transformative potential to support prehospital clinicians, emergency physicians, and trauma surgeons in acute traumatic injury care. This scoping review examines the literature evaluating AI models using prehospital features to support early traumatic injury care.

Methods

We conducted a systematic search in August 2023 of PubMed, Embase, and Web of Science. Two independent reviewers screened titles/abstracts, with a third reviewer for adjudication, followed by a full-text analysis. We included original research and conference presentations evaluating AI models-machine learning (ML), deep learning (DL), and natural language processing (NLP)-that used prehospital features or features available immediately upon emergency department arrival. Review articles were excluded. The same investigators extracted data and systematically categorized outcomes to ensure consistency and transparency. We calculated kappa for interrater reliability and descriptive statistics.

Results

We identified 1050 unique publications, with 49 meeting inclusion criteria after title and abstract review (kappa 0.58) and full-text review. Publications increased annually from 2 in 2007 to 10 in 2022. Geographic analysis revealed a 61% focus on data from the United States. Studies were predominantly retrospective (88%), used local (45%) or national level (41%) data, focused on adults only (59%) or did not specify adults or pediatrics (27%), and 57% encompassed both blunt and penetrating injury mechanisms. The majority used machine learning (88%) alone or in conjunction with DL or NLP, and the top three algorithms used were support vector machine, logistic regression, and random forest. The most common study objectives were to predict the need for critical care and life-saving interventions (29%), assist in triage (22%), and predict survival (20%).

Conclusions

A small but growing body of literature described AI models based on prehospital features that may support decisions made by dispatchers, Emergency Medical Services clinicians, and trauma teams in early traumatic injury care.

Epidemiology and factors associated with mortality among pediatric major trauma patients in Nova Scotia: A 17-year retrospective analysis

BACKGROUND

Major traumatic injury in the pediatric population requires further evaluation to improve patient outcomes. Relatively few Canadian studies have investigated pediatric trauma using population-based data. Our objectives were to describe the epidemiology of pediatric major trauma in Nova Scotia and identify factors associated with in-hospital mortality.

METHODS

Retrospective cohort study of pediatric major trauma patients (age <18 years) injured in Nova Scotia over a 17-year period (April 2001-March 2018). Data were collected from the Nova Scotia Trauma Registry. Characteristics were compared between patient subgroups using t-tests, chi-square analyses and Fisher's exact test. Temporal trends were evaluated using the Mann-Kendall test. Incidence and mortality rates were mapped using ArcGIS Pro. A multivariate logistic regression model was created to assess for factors associated with in-hospital mortality.

RESULTS

A total of 1258 injuries were observed over the 17-year study period. The incidence of pediatric major trauma was 41.7 per 100,000 person-years. Most patients were male (819/1258; 65.1 %) and resided in urban areas (764/1258; 60.7 %). Blunt trauma accounted for 86.2 % (1084/1258) of injuries, and motor vehicle collisions were the most common cause (448/1258; 35.6 %). Incidence and mortality rates were highest in the 15-17 year age group, with a trend towards increasing incidence among females (p = 0.011). Mortality was 17.2 % (217/1258) of patients; 10.9 % (137/1258) died pre-hospital. No trends were detected in mortality rates. The regression model showed increased odds of in-hospital mortality for every point increase in the ISS (OR 1.05; 95 % CI 1.02 to 1.09) and for every unit decrease in scene GCS (OR 0.63; 95 % CI 0.56-0.71). Rural patients were 2 times more likely to die in-hospital versus urban patients (OR 2.40; 95 % CI 1.01-5.69), and patients injured at home were 6 times more likely to die compared to those injured in other locations (OR 6.19; 95 % CI 1.01-38.11).

CONCLUSION

Pediatric trauma remains a major public health issue in Canada and beyond. Greater efforts are required to expand our understanding of trauma epidemiology and develop targeted injury prevention strategies, especially for rural inhabitants.

The associations of "weekend warrior" and regularly active physical activity with abdominal and general adiposity in US adults

OBJECTIVE

This study examined the association between physical activity patterns and abdominal and general adiposity.

METHODS

Data were extracted among 20- to 59-year-old participants in the National Health and Nutrition Examination Survey (NHANES) from 2011 to 2018. Abdominal and general adiposity was assessed by dual-energy x-ray absorptiometry (DXA) and anthropometric measures. DXA-measured indicators were further normalized into z scores. Physical activity levels were collected by questionnaire and classified as inactive, "weekend warrior" (WW), and regularly active (RA). Survey linear regression models were used to assess associations between physical activity patterns and adiposity indicators.

RESULTS

Among 9629 participants, 772 (8.2%) reported the WW pattern and 3277 (36.9%) reported the RA pattern. Compared with inactive, both WW and RA had lower DXA-measured abdominal adiposity (WW: β: -0.24, 95% CI: -0.38 to -0.10; RA: -0.18, 95% CI: -0.29 to -0.07), waist circumference (WW: β: -1.94, 95% CI: -3.16 to -0.73; RA: -1.31, 95% CI: -2.32 to -0.29), whole-body fat mass (WW: β: -0.16, 95% CI: -0.25 to -0.08; RA: -0.11, 95% CI: -0.18 to -0.04), and BMI (WW: β: -0.78, 95% CI: -1.27 to -0.28; RA: -0.47, 95% CI: -0.89 to -0.04).

CONCLUSIONS

The WW pattern was associated with similarly lower abdominal and general adiposity to the RA pattern versus the inactive pattern.

Pre-hospital mortality among pediatric trauma patients in Nova Scotia

OBJECTIVES

Limited data exist on pre-hospital pediatric trauma mortality in Canada. The Nova Scotia Trauma Registry is a provincial population-based registry that captures data from the Medical Examiner Service. This study examined the characteristics of pediatric trauma patient mortality in the pre-hospital and in-hospital settings.

METHODS

We conducted a cohort study of major pediatric traumas recorded in our provincial database from April 1, 2001 to March 31, 2018. Characteristics of pre-hospital and in-hospital deaths were compared with t tests and Chi-square analyses. Multivariate regression modeling was used to identify predictors of pre-hospital mortality. The geographic distribution of pre-hospital trauma was assessed using choropleth maps.

RESULTS

We identified 1,258 pediatric traumas, resulting in 217 deaths (137 pre-hospital, 80 in-hospital). Males accounted for 62.7% of fatalities. The 15-17 age group accounted for most deaths in both groups (pre-hospital 61.3%; in-hospital 41.3%). Injuries sustained in rural areas resulted in 74.7% of all deaths. For both groups, blunt trauma was the predominant injury type and motor vehicle collisions, the most prevalent injury mechanism. Patients who died pre-hospital had a higher mean age (13.3 vs. 10.7, p = 0.002) and a greater proportion were intentional injuries (23.4% vs. 15%; p = 0.02). Urban residency was more frequently observed in in-hospital deaths (57.5% vs. 36.5%, p < 0.001). Pre-hospital mortality was associated with increasing age (OR 1.1), higher injury severity score (OR 1.1), and intentional injury (OR 15.6).

CONCLUSION

Over 10% of major pediatric traumas resulted in pre-hospital death, primarily from motor vehicle collisions in rural areas. Compared to in-hospital mortality, patients who died pre-hospital were older with more severe injuries and more likely to have intentionally injured themselves. These results underscore the importance for emergency physicians and EMS systems to consider geographic factors and injury patterns, advocate for improved injury prevention programs, mental health supports, and delivery of on-scene critical care services.