Objective The objective was to examine the 22 variables from the Sport Concussion Assessment Tool’s 5^th Edition (SCAT5) Symptom Evaluation using a decision tree analysis to identify those most likely to predict prolonged recovery following sport-related concussion.

Design Cross sectional.

Setting Single site – Primary care.

Participants 273 patients (52% male, mean age 21 ± 7.6 years) initially assessed by either an emergency medicine or sport medicine physician within 14 days of concussion (mean 6 ± 4 days).

Interventions (or Assessment of Risk Factors) 22 symptoms from the Sport Concussion Assessment Tool 5th Edition

Outcome Measures A decision tree analysis was performed using RStudio and the R package rpart. The decision tree was generated using a complexity parameter of 0.045, post-hoc pruning was conducted with rpart and the package carat was used to assess the final decision tree’s accuracy, sensitivity and specificity.

Main Results Of the 22 variables, only 2 contributed towards the predictive splits: Feeling like ‘in a fog’, and Sadness. The confusion matrix yielded a statistically significant accuracy of 0.7636 (p-Value [Acc > NIR]: 0.00009678), sensitivity of 0.6429, specificity of 0.8889, positive predictive value of 0.8571 and a negative predictive value of 0.7059.

Conclusions Decision tree analysis yielded a statistically significant decision tree model which can be used clinically to identify patients at initial presentation who are at a higher risk of having prolonged symptoms lasting 28 days or more post-concussion.