Skip to main content
eScholarship
Open Access Publications from the University of California

Scholarly Works (2 results)

  • Article
  • Peer Reviewed
UC Davis Previously Published Works (2020)

Objective

To develop a simplified clinical prediction tool for identifying children with clinically important traumatic brain injuries (ciTBIs) after minor blunt head trauma by applying machine learning to the previously reported Pediatric Emergency Care Applied Research Network dataset.

Study design

The deidentified dataset consisted of 43 399 patients <18 years old who presented with blunt head trauma to 1 of 25 pediatric emergency departments between June 2004 and September 2006. We divided the dataset into derivation (training) and validation (testing) subsets; 4 machine learning algorithms were optimized using the training set. Fitted models used the test set to predict ciTBI and these predictions were compared statistically with the a priori (no information) rate.

Results

None of the 4 machine learning models was superior to the no information rate. Children without clinical evidence of a skull fracture and with Glasgow Coma Scale scores of 15 were at the lowest risk for ciTBIs (0.48%; 95% CI 0.42%-0.55%).

Conclusions

Machine learning algorithms were unable to produce a more accurate prediction tool for ciTBI among children with minor blunt head trauma beyond the absence of clinical evidence of skull fractures and having Glasgow Coma Scale scores of 15.
    Cover page: Derivation and Validation of a Simplified Clinical Prediction&nbsp;Rule&nbsp;for&nbsp;Identifying Children at Increased Risk&nbsp;for&nbsp;Clinically&nbsp;Important&nbsp;Traumatic&nbsp;Brain Injuries Following Minor&nbsp;Blunt&nbsp;Head Trauma
    • Article
    Emergency Medicine (2020)

    • The Pediatric Emergency Care Applied Research Network (PECARN) conducted a study of ~42,000 children with minor blunt head trauma and developed and validated a clinical prediction rule to identify those at low risk of clinically-important traumatic brain injuries (ciTBIs) .1

    • Prior studies have relied on traditional multivariable statistical methods,1-2 but more recent research regarding prediction rules has used machine learning (ML). 3-6

    • In a previous study, investigators created a ML algorithm analyzing the PECARN dataset using a single decision tree that fits all nodes simultaneously, a complicated model at risk of over fitting. 6

    • In this study, we created multiple algorithms (see Table 2) using ML for classification of children at risk for ciTBIs via the PECARN head trauma public use dataset. The model predictions were statistically compared to no information rates, the error rate when the input and output are independent.

      Cover page: Predictors of Clinically Important Traumatic Brain Injuries Following Minor Blunt Head Trauma in Children: A Failure of the Machine Learning Approach
      Top