Prediction of mortality

Real-time patient monitoring data collected over the course of trauma care are often large in quantities and require systematic representation that can combined temporal reasoning and validated algorithms to support clinical decision making. Available continuous vital signs, in many cases result in few state changes in the temporal range of interest; this work applies validated systematic algorithms to a small set of vital signs data to identify patients at risk for mortality. Vital signs signals are used to train J48, naïve bayes, decision stump and SMO models. The InfoGain features selection algorithm was used to extract the best features using full run time-series data and feature generation permitted the features to be trained/tested on sensor data of any size, which dramatically improved the prediction classification of the J48 algorithm. The evaluation of the models were done using leave-one-out cross validation. The quality of the classification was determined by the accuracy, precision and recall. Results show that the J48 algorithm coupled with feature selection is a simple method for the identification of patients at increased risk for mortality in trauma care.