Using an artificial neural network to predict traumatic brain injury

Abstract

<jats:sec><jats:title>OBJECTIVE</jats:title><jats:p>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.</jats:p></jats:sec><jats:sec><jats:title>METHODS</jats:title><jats:p>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 &gt; 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.</jats:p></jats:sec><jats:sec><jats:title>RESULTS</jats:title><jats:p>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.</jats:p></jats:sec><jats:sec><jats:title>CONCLUSIONS</jats:title><jats:p>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.</jats:p></jats:sec>

<p>Forecasting the seasonality and trend of pulmonary tuberculosis in Jiangsu Province of China using advanced statistical time-series analyses</p>

“…Second, we determine a three-layer BPNN model with one input layer, one hidden layer and one output layer (Figure 1). We construct the BPNN model by dividing the data into a training set, testing set and validation set, according to the ratio of 7:1.5:1.5 14. Third, we preliminarily determine the number of neurons in the hidden layer using the empirical formula: , where M is the number of neurons in the hidden layer, n is the number of neurons in the input layer, m is the number of neurons in the output layer and a is a constant in the range of 1 to 10 18.…”

“…Since the 1980s, the artificial neural network (ANN) model has been developed and rapidly applied as an effective tool in time series analysis and disease prediction. The ANN model can adjust its structure to adapt to the characteristics of samples, overcome the shortcomings of traditional parametric models that have high requirements on samples, and automatically recognize and learn the relationship between variables without any restrictions 12–14. Therefore, this model has attracted more and more attention in the field of medicine and biology 15–17.…”

ACR Appropriateness Criteria® Head Trauma: 2021 Update

“…Comparison studies from Australia and New Zealand determined clinical decision rules to be less specific than usual care by clinicians, contrasting with studies from the United States and reflecting differences in baseline scan rates [22,23]. Ongoing efforts to improve the specificity and positive predictive value of clinical decision rules include the application of machine learning techniques (eg, artificial neural networks and optimal classification trees), which come at the cost of complexity [24,25].…”

Artificial intelligence in paediatric radiology: Future opportunities

“…A more advanced feature in future applications would use machine learning to integrate information from imaging reports, patient demographics, biochemical and blood markers for risk stratification: to suggest probabilities of certain diagnoses or to predict patient outcomes. 11 In one example of this, Hale et al 12 used a deep-learning neural network to predict the possibility of clinically relevant paediatric traumatic brain injuries, through combining clinical information and radiologist-interpreted CT head reports. The creation of this tool allowed for an evidencebased automated risk stratification tool, encouraging early safe discharge for low-risk patients from the emergency department and reducing unnecessary hospital occupancy.…”