CONCEPT-FORMATION VS LOGISTIC-REGRESSION - PREDICTING DEATH IN TRAUMAPATIENTS

This study compares two classification models used to predict survival of injured patients entering the emergency department. Concept format ion is a machine learning technique that summarizes known examples/cas es in the form of a tree. After the tree is constructed, it can then b e used to predict the classification of new cases. Logistic regression , on the other hand, is a statistical model that allows for a quantita tive relationship for a dichotomous event with several independent var iables. The outcome (dependent) variable must have only two choices, e .g. does or does not occur, alive or dead, etc. The result of this mod el is an equation which is then used to predict the probability of cla ss membership of a new case. The two models were evaluated on a trauma registry database composed of information on all trauma patients admi tted in 1992 to a Level I trauma center. A total of 2155 records, repr esenting all trauma patients admitted for more than 24 h or who died i n the Emergency Department, were grouped into two databases as follows : (1) discharge status of 'died' (containing 151 records), and (2) any discharge status other than 'died' (containing 2004 records). Both da tabases contained the same variables.