1 1Vanderbilt University School of Medicine, Medical Scientist Training Program;
2 2Vanderbilt University School of Medicine, Nashville, Tennessee;
3 3Johns Hopkins Medical Institute, Johns Hopkins University School of Medicine, Baltimore, Maryland;
4 6Department of Neurosurgery, Vanderbilt University Medical Center and Division of Pediatric Neurosurgery, Monroe Carell Jr. Children’s Hospital of Vanderbilt University; and
5 7Surgical Outcomes Center for Kids, Monroe Carell Jr. Children’s Hospital of Vanderbilt University, Nashville, Tennessee
6 4Division of Trauma, Emergency General Surgery, and Surgical Critical Care, Departments of Surgery and Hearing and Speech Sciences, Section of Surgical Sciences, Vanderbilt University Medical Center;
7 5Center for Health Services Research, Vanderbilt Brain Institute, Vanderbilt University Medical Center and Geriatric Research, Education and Clinical Center Service, Surgical Service, Department of Veterans Affairs Medical Center, Tennessee Valley Health Care System;
Pediatric traumatic brain injury (TBI) is common, but not all injuries require hospitalization. A computational tool for ruling in patients who will have a clinically relevant TBI (CRTBI) would be valuable, providing an evidence-based way to safely discharge children who are at low risk for a CRTBI. The authors hypothesized that an artificial neural network (ANN) trained on clinical and radiologist-interpreted imaging metrics could provide a tool for identifying patients likely to suffer from a CRTBI.
The authors used the prospectively collected, publicly available, multicenter Pediatric Emergency Care Applied Research Network (PECARN) TBI data set. All patients under the age of 18 years with TBI and admission head CT imaging data were included. The authors constructed an ANN using clinical and radiologist-interpreted imaging metrics in order to predict a CRTBI, as previously defined by PECARN: 1) neurosurgical procedure, 2) intubation > 24 hours as direct result of the head trauma, 3) hospitalization ≥ 48 hours and evidence of TBI on a CT scan, or 4) death due to TBI.
Among 12,902 patients included in this study, 480 were diagnosed with CRTBI. The authors’ ANN had a sensitivity of 99.73% with precision of 98.19%, accuracy of 97.98%, negative predictive value of 91.23%, false-negative rate of 0.0027%, and specificity for CRTBI of 60.47%. The area under the receiver operating characteristic curve was 0.9907.
The authors are the first to utilize artificial intelligence to predict a CRTBI in a clinically meaningful manner, using radiologist-interpreted CT information, in order to identify pediatric patients likely to suffer from a CRTBI. This proof-of-concept study lays the groundwork for future studies incorporating iterations of this algorithm directly into the electronic medical record for real-time, data-driven predictive assistance to physicians.
ABBREVIATIONSANN = artificial neural network; AUC = area under the curve; CRTBI = clinically relevant TBI; EMR = electronic medical record; NPV = negative predictive value; PECARN = Pediatric Emergency Care Applied Research Network; ROC = receiver operator characteristic; TBI = traumatic brain injury.