TY - JOUR AU1 - Bertsimas, Dimitris AU2 - Dunn, Jack AU3 - Steele, Dale W. AU4 - Trikalinos, Thomas A. AU5 - Wang, Yuchen AB - Key PointsQuestionCan machine learning improve the Pediatric Emergency Care Applied Research Network (PECARN) rules’ predictive accuracy to identify children at very low, intermediate, and high risk of clinically important traumatic brain injury? FindingsIn this cohort study of 42 412 children with head trauma, reanalysis of data from the PECARN group empirically suggests that novel machine-learning (optimal classification tree)–based rules perform as well as or better than the PECARN rules in identifying more children at very low risk of clinically important traumatic brain injury without missing more patients with clinically important traumatic brain injury. MeaningIf implemented in the electronic health record, the new rules may help reduce the number of unnecessary computed tomographic imaging scans, without missing more patients with clinically important traumatic brain injury than the PECARN rules. TI - Comparison of Machine Learning Optimal Classification Trees With the Pediatric Emergency Care Applied Research Network Head Trauma Decision Rules JF - JAMA Pediatrics DO - 10.1001/jamapediatrics.2019.1068 DA - 2019-07-13 UR - https://www.deepdyve.com/lp/american-medical-association/comparison-of-machine-learning-optimal-classification-trees-with-the-tYIcrZpP7G SP - 648 EP - 656 VL - 173 IS - 7 DP - DeepDyve ER -