Evaluating Outcomes of Nonaccidental Trauma in Military Children

BACKGROUND

Nonaccidental trauma (NAT), or child abuse, is a leading cause of childhood injury and death in the US. Studies demonstrate that military-affiliated individuals are at greater risk of mental health complication and family violence, including child maltreatment. There is limited information about the outcomes of military children who experience NAT. This study compares the outcomes between military-dependent and civilian children diagnosed with NAT.

STUDY DESIGN

A single-institution, retrospective review of children admitted with confirmed NAT at a Level I trauma center was performed. Data were collected from the institutional trauma registry and the Child Abuse Team's database. Military affiliation was identified using insurance status and parental or caregiver self-reported active-duty status. Demographic and clinical data including hospital length of stay (LOS), morbidity, specialty consult, and mortality were compared.

RESULTS

Among 535 patients, 11.8% (n = 63) were military-affiliated. The median age of military-associated patients, 3 months (interquartile range [IQR] 1 to 7), was significantly younger than civilian patients, 7 months (IQR 3 to 18, p < 0.001). Military-affilif:ated patients had a longer LOS of 4 days (IQR 2 to 11) vs 2 days (IQR 1 to 7, p = 0.041), increased morbidity or complication (3 vs 2 counts, p = 0.002), and a higher mortality rate (10% vs 4%, p = 0.048). No significant difference was observed in the number of consults or injuries, trauma activation, or need for surgery.

CONCLUSIONS

Military-affiliated children diagnosed with NAT experience more adverse outcomes than civilian patients. Increased LOS, morbidity or complication, and mortality suggest military-affiliated patients experience more life-threatening NAT at a younger age. Larger studies are required to further examine this population and better support at-risk families.

Application of a Machine Learning Algorithm in Prediction of Abusive Head Trauma in Children

PURPOSE

We explored the application of a machine learning algorithm for the timely detection of potential abusive head trauma (AHT) using the first free-text note of an encounter and demographic information.

METHODS

First free-text physician notes and demographic information were collected for children under 5 years of age at a Level 1 Trauma Center. The control group, which included patients with head/neck injury, was compared to those with AHT diagnosed by the Child Protective Team. Differential scores accounted for words overrepresented in AHT patient vs. control notes. Sentiment scores were reflective of note positivity/negativity and subjectivity scores accounted for note subjectivity/objectivity. The composite scores reflected the patient's differential score modified by the subjectivity score. Composite, sentiment, and subjectivity scores combined with demographic information trained a Random Forest (RF) machine learning algorithm to predict AHT.

RESULTS

Final composite scores with demographic information were highly associated with AHT in a test dataset. The control group included 587 patients and the test group included 193 patients. Combining composite scores with demographic information into the RF model improved AHT classification area under the curve (AUC) from 0.68 to 0.78, with an overall accuracy of 84%. Feature importance analysis of our RF model revealed that composite score, sentiment, age, and subjectivity were the most impactful predictors of AHT. The sentiment was not significantly different between control and AHT notes (p = 0.87), while subjectivity trended higher for AHT notes (p = 0.081).

CONCLUSION

We conclude that a machine learning algorithm can recognize patterns within free-text notes and demographic information that aid in AHT detection in children.

LEVEL OF EVIDENCE

III.