“Poster” a prediction model of traumatic patients outcome by data mining technique

Trauma is one of the most common causes of death in the world, which often occurs as a result of road accidents. Prompt identification of patients with acute injury, leads to take the appropriate medical actions and thus save lives and also avoid enormous cost of treatment will be. The purpose of this study is prediction of patients´ outcome and then construction of a model for identifying severs trauma patients by data mining techniques. A number of data mining algorithms have been modified for the task and have been trained over wide range of features. Among the performed classification algorithms, decision tree was able to recognize death cases with higher precision, (91%). In order to find factors contributing in mortality on training a better Decision Tree classifier, the Best-First algorithm was used and then a predictive model for patients´ outcome is contrasted by C4.5 algorithms with accuracy of 87%.