A comparison of ICU mortality prediction using the APACHE II scoring system and artificial neural networks

The aim of this study was to compare the ability of artificial neural netwo rks and the Acute Physiology and Chronic Health Evaluation II score to pred ict mortality in adult intensive care units. The same physiological variabl es were used in both predictive models to predict hospital mortality from a data set of 8796 patients collected from 26 adult intensive care units in the United Kingdom and Ireland as part of the Intensive Care Society study. The results from the two models were compared with the actual outcome. The overall prediction accuracy and the overall goodness-of-fit of all the mod els were assessed. Both predictive models showed similar goodness-of-fit an d prediction discrimination. The overall predictive and classification perf ormance of the artificial neural network developed matched and in some aspe cts was better than that of Acute Physiology and Chronic Health Evaluation II.