Predicting Mortality and Functional Status Scores of Traumatic Brain Injury Patients using Supervised Machine Learning

Traumatic brain injury (TBI) presents a significant public health challenge, often resulting in mortality or lasting disability. Predicting outcomes such as mortality and Functional Status Scale (FSS) scores can enhance treatment strategies and inform clinical decision-making. This study applies supervised machine learning (ML) methods to predict mortality and FSS scores using a real-world dataset of 300 pediatric TBI patients from the University of Colorado School of Medicine. The dataset captures clinical features, including demographics, injury mechanisms, and hospitalization outcomes. Eighteen ML models were evaluated for mortality prediction, and thirteen models were assessed for FSS score prediction. Performance was measured using accuracy, ROC AUC, F1-score, and mean squared error. Logistic regression and Extra Trees models achieved high precision in mortality prediction, while linear regression demonstrated the best FSS score prediction. Feature selection reduced 103 clinical variables to the most relevant, enhancing model efficiency and interpretability. This research highlights the role of ML models in identifying high-risk patients and supporting personalized interventions, demonstrating the potential of data-driven analytics to improve TBI care and integrate into clinical workflows.

Neural Network Verification through Replication

A system identification based approach to neural network model replication is presented and the application of model replication to verification of fundamental, single hidden layer, neural network systems is demonstrated. The presented approach serves as a means to partially address the problem of verifying that a neural network implementation meets a provided specification given only grey-box access to the implemented network. The procedure developed involves stimulating a neural network with a chosen signal, extracting a replicated model from the response, and systematically checking that the replicated model is output-equivalent to a specified model in order to verify that the grey-box system under test is implemented to specification without direct access to its hidden parameters. The replication step is introduced to provide an inherent guarantee that the stimulus signals employed yield sufficient test coverage. This method is investigated as a neural network focused nonlinear counterpart to the traditional verification of circuits through system identification. A strategy for choosing the stimulus is provided and an algorithm for verifying that the resulting response is indicative of a specification-compliant neural network system under test is derived. We find that the method can reliably detect defects in small neural networks or in small sub-circuits within larger neural networks.