Using artificial neural networks to predict potential complications during trauma patients' hospitalization period.

Complications during treatment of seriously injured trauma patients cause an increase in mortality rates, and increased treatment costs, including bed occupancy. Current methods treat those at risk, and include numbers of false positives. By finding a method to predict those at risk of the three most common recorded Trauma Registry complications, considerable savings in mortality and treatment costs could arise. Artificial Neural Networks (ANN) work well with classification problems using feed-forward/back propagation methodology. Using the National Trauma Data Bank (V6.2) data files, Tiberius Software created the ANN models. Best models were identified by their Gini co-efficient, ability to predict the complication outcome selected, and their Root Mean Squared Error (RMSE) scores. The model ensemble for the three major complications recorded in the registry were determined, variables ranked and model accuracy recorded. The basic ANN is fairly accurate for those likely to contract Acute Respiratory Disease Syndrome (ARDS) though with a high rate of false positives. The ANN ability to predict Ventilator Associated Pneumonia (VAP) is less effective, though better at producing fewer false positives. Predicting Urinary Tract Infections (UTI) cases is not good enough using these input variables. Both VAP and UTI relate to those aged over 55 years, while ARDS related more to those under 16 years. The models need improving.