Predictive modeling in pediatric traumatic brain injury using machine learning

Abstract

BackgroundPediatric traumatic brain injury (TBI) constitutes a significant burden and diagnostic challenge in the emergency department (ED). While large North American research networks have derived clinical prediction rules for the head injured child, these may not be generalizable to practices in countries with traditionally low rates of computed tomography (CT). We aim to study predictors for moderate to severe TBI in our ED population aged < 16 years.MethodsThis was a retrospective case–control study based on data from a prospective surveillance head injury database. Cases were included if patients presented from 2006 to 2014, with moderate to severe TBI. Controls were age-matched head injured children from the registry, obtained in a 4 control: 1 case ratio. These children remained well on diagnosis and follow up. Demographics, history, and physical examination findings were analyzed and patients followed up for the clinical course and outcome measures of death and neurosurgical intervention. To predict moderate to severe TBI, we built a machine learning (ML) model and a multivariable logistic regression model and compared their performances by means of Receiver Operating Characteristic (ROC) analysis.ResultsThere were 39 cases and 156 age-matched controls. The following 4 predictors remained statistically significant after multivariable analysis: Involvement in road traffic accident, a history of loss of consciousness, vomiting and signs of base of skull fracture. The logistic regression model was created with these 4 variables while the ML model was built with 3 extra variables, namely the presence of seizure, confusion and clinical signs of skull fracture. At the optimal cutoff scores, the ML method improved upon the logistic regression method with respect to the area under the ROC curve (0.98 vs 0.93), sensitivity (94.9% vs 82.1%), specificity (97.4% vs 92.3%), PPV (90.2% vs 72.7%), and NPV (98.7% vs 95.4%).ConclusionsIn this study, we demonstrated the feasibility of using machine learning as a tool to predict moderate to severe TBI. If validated on a large scale, the ML method has the potential not only to guide discretionary use of CT, but also a more careful selection of head injured children who warrant closer monitoring in the hospital.

Using an artificial neural network to predict traumatic brain injury

“…More recently, ANNs have been shown to robustly predict complications, outcomes, and prognosis among numerous fields, 5,13,31,[34][35][36] including TBI. 8,18,26,32,37,38 Thus, an ANN tool yielding predictive information concerning CRTBI would be helpful and provide an evidence-based mechanism for treating these patients. ANNs are computational constructs used to interpret the maximum number of combinations of data in complex systems, such as making medical diagnoses in neurosurgery, 36,37 where many competing factors influence outcome.…”

Comparison of Artificial Neural Network and Logistic Regression Models for Prediction of Psychological Symptom Six Months after Mild Traumatic Brain Injury

“…Studies which have been conducted on statistical modeling of post-traumatic psychological symptom (15,(17)(18)(19)(20) mostly aimed to examine the effective factors on psychological symptoms by using the LR model. However, in the present study, we aimed to investigate the prediction of accuracy and precision of LR and neural network models for the first time.…”

Artificial intelligence and pediatrics: A synthetic mini review

“…AI use in developmental disorders where examples include quantifying risk for anxiety disorders in preschool children [25], developing socially intelligent robots as possible educational or therapeutic toys for children with autism [26], identifying children with autism based on face abnormality [27] etc; AI in paediatric emergency care was used for automated appendicitis risk stratification [28], supporting diagnostic decisions [29], traumatic brain injury [30] and detection of low-volume blood loss [31];…”