The detection of mild traumatic brain injury in paediatrics using artificial neural networks

Head computed tomography (CT) is the gold standard in emergency departments (EDs) to evaluate mild traumatic brain injury (mTBI) patients, especially for paediatrics. Data-driven models for successfully classifying head CT scans that have mTBI will be valuable in terms of timeliness and cost-effectiveness for TBI diagnosis. This study applied two different machine learning (ML) models to diagnose mTBI in a paediatric population collected as part of the paediatric emergency care applied research network (PECARN) study between 2004 and 2006. The models were conducted using 15,271 patients under the age of 18 years with mTBI and had a head CT report. In the conventional model, random forest (RF) ranked the features to reduce data dimensionality and the top ranked features were used to train a shallow artificial neural network (ANN) model. In the second model, a deep ANN applied to classify positive and negative mTBI patients using the entirety of the features available. The dataset was divided into two subsets: 80% for training and 20% for testing using five-fold cross-validation. Accuracy, sensitivity, precision, and specificity were calculated by comparing the model's prediction outcome to the actual diagnosis for each patient. RF ranked ten clinical demographic features and twelve CT-findings; the hybrid RF-ANN model achieved an average specificity of 99.96%, sensitivity of 95.98%, precision of 99.25%, and accuracy of 99.74% in identifying positive mTBI from negative mTBI subjects. The deep ANN proved its ability to carry out the task efficiently with an average specificity of 99.9%, sensitivity of 99.2%, precision of 99.9%, and accuracy of 99.9%. The performance of the two proposed models demonstrated the feasibility of using ANN to diagnose mTBI in a paediatric population. This is the first study to investigate deep ANN in a paediatric cohort with mTBI using clinical and non-imaging data and diagnose mTBI with balanced sensitivity and specificity using shallow and deep ML models. This method, if validated, would have the potential to reduce the burden of TBI evaluation in EDs and aide clinicians in the decision-making process.

[1]  Mohamed Alfateh Badawy,et al.  Identification of children at very low risk of clinically-important brain injuries after head trauma: a prospective cohort study , 2009, The Lancet.

[2]  B. Ang,et al.  Hybrid outcome prediction model for severe traumatic brain injury. , 2007, Journal of Neurotrauma.

[3]  A Rogier T Donders,et al.  Imputation of missing values is superior to complete case analysis and the missing-indicator method in multivariable diagnostic research: a clinical example. , 2006, Journal of clinical epidemiology.

[4]  Josh Bongard,et al.  C L I N I C a L a R T I C L E , 2022 .

[5]  D. Rueckert,et al.  Prediction of stroke thrombolysis outcome using CT brain machine learning , 2014, NeuroImage: Clinical.

[6]  C. Rau,et al.  Mortality prediction in patients with isolated moderate and severe traumatic brain injury using machine learning models , 2018, PloS one.

[7]  Yanjun Qi.  Random Forest for Bioinformatics , 2012 .

[8]  J. Haukoos,et al.  Comparison of PECARN, CATCH, and CHALICE rules for children with minor head injury: a prospective cohort study. , 2014, Annals of emergency medicine.

[9]  Cláudio Rebelo de Sá,et al.  Variance-Based Feature Importance in Neural Networks , 2019, DS.

[10]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[11]  Haidi Ibrahim,et al.  Predicting Outcomes in Patients with Traumatic Brain Injury Using Machine Learning Models , 2019, Lecture Notes in Mechanical Engineering.

[12]  Yurong Liu,et al.  A survey of deep neural network architectures and their applications , 2017, Neurocomputing.

[13]  Arthur W. Toga,et al.  A Machine Learning Model to Predict Seizure Susceptibility from Resting-State fMRI Connectivity , 2019, 2019 Spring Simulation Conference (SpringSim).

[14]  Hon-Yi Shi,et al.  In-hospital mortality after traumatic brain injury surgery: a nationwide population-based comparison of mortality predictors used in artificial neural network and logistic regression models. , 2013, Journal of neurosurgery.

[15]  Daniel A. Hirsh,et al.  Trends in Computed Tomography Utilization in the Pediatric Emergency Department , 2012, Pediatrics.

[16]  Li Liu,et al.  Neural network modeling for surgical decisions on traumatic brain injury patients , 2000, Int. J. Medical Informatics.

[17]  Juan Lu,et al.  Predicting Outcome after Traumatic Brain Injury: Development and International Validation of Prognostic Scores Based on Admission Characteristics , 2008, PLoS medicine.

[18]  Tomaso A. Poggio,et al.  When and Why Are Deep Networks Better Than Shallow Ones? , 2017, AAAI.

[19]  S. Mohamad R. Soroushmehr,et al.  A machine learning based approach for identifying traumatic brain injury patients for whom a head CT scan can be avoided , 2016, EMBC.

[20]  Alireza Sadeghian,et al.  Using artificial neural networks to identify patients with concussion and postconcussion syndrome based on antisaccades. , 2019, Journal of neurosurgery.

[21]  M. W. McNerney,et al.  Objective Classification of mTBI Using Machine Learning on a Combination of Frontopolar Electroencephalography Measurements and Self-reported Symptoms , 2019, Sports Medicine - Open.

[22]  B. Erickson,et al.  Machine Learning for Medical Imaging. , 2017, Radiographics : a review publication of the Radiological Society of North America, Inc.

[23]  Nan Liu,et al.  Predictive modeling in pediatric traumatic brain injury using machine learning , 2015, BMC Medical Research Methodology.

[24]  Huan Liu,et al.  Feature Selection for Classification: A Review , 2014, Data Classification: Algorithms and Applications.

[25]  Tarun Kumar Gupta,et al.  Optimization of ANN Architecture: A Review on Nature-Inspired Techniques , 2019, Machine Learning in Bio-Signal Analysis and Diagnostic Imaging.

[26]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[27]  Kentaro Ishizu,et al.  Big Data Analytics, Machine Learning, and Artificial Intelligence in Next-Generation Wireless Networks , 2017, IEEE Access.

[28]  Sharmila Majumdar,et al.  Deep Learning Predicts Total Knee Replacement from Magnetic Resonance Images , 2020, Scientific Reports.

[29]  Eiji Kohmura,et al.  Machine Learning to Predict In-hospital Morbidity and Mortality after Traumatic Brain Injury. , 2020, Journal of neurotrauma.

[30]  Vince D. Calhoun,et al.  Dynamic functional network connectivity discriminates mild traumatic brain injury through machine learning , 2018, NeuroImage: Clinical.

[31]  M. Fararouei,et al.  Comparison of artificial neural network and logistic regression models for prediction of outcomes in trauma patients: A systematic review and meta-analysis. , 2019, Injury.

[32]  K. Borgwardt,et al.  Machine Learning in Medicine , 2015, Mach. Learn. under Resour. Constraints Vol. 3.

[33]  Mayur B. Patel,et al.  Using an artificial neural network to predict traumatic brain injury. , 2019, Journal of neurosurgery. Pediatrics.

[34]  Likang Xu,et al.  Surveillance report of traumatic brain injury-related emergency department visits, hospitalizations, and deaths, United States, 2014 , 2019 .

[35]  Tao Li,et al.  Cost-sensitive feature selection using random forest: Selecting low-cost subsets of informative features , 2016, Knowl. Based Syst..

[36]  Inan Güler,et al.  Evaluating of traumatic brain injuries using artificial neural networks , 2009, Expert Syst. Appl..

[37]  P. Dayan,et al.  Headache in Traumatic Brain Injuries From Blunt Head Trauma , 2015, Pediatrics.

[38]  P. Malik,et al.  Artificial intelligence as an emerging technology in the current care of neurological disorders , 2019, Journal of Neurology.

[39]  Vedat Verter,et al.  Predicting the Need for Ct Imaging in Children with Minor Head Injury Using an Ensemble of Naive Bayes Classifiers , 2022 .

[40]  Saeedeh Pourahmad,et al.  Identifying Important Attributes for Prognostic Prediction in Traumatic Brain Injury Patients , 2016, Methods of Information in Medicine.

[41]  Jui-Chang Tsai,et al.  Predicting Long-Term Outcome After Traumatic Brain Injury Using Repeated Measurements of Glasgow Coma Scale and Data Mining Methods , 2015, Journal of Medical Systems.

[42]  Sa'ed Abed,et al.  An efficient multiple sclerosis segmentation and detection system using neural networks , 2018, Comput. Electr. Eng..

[43]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[44]  E. Sribnick,et al.  U.S. Trends of ED Visits for Pediatric Traumatic Brain Injuries: Implications for Clinical Trials , 2017, International journal of environmental research and public health.

[45]  R. Diaz-Arrastia,et al.  Emergency Department Evaluation of Traumatic Brain Injury in the United States, 2009–2010 , 2016, The Journal of head trauma rehabilitation.

[46]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[47]  V. Fineschi,et al.  Diffuse Axonal Injury and Oxidative Stress: A Comprehensive Review , 2017, International journal of molecular sciences.