A NEW APPROACH TO PROBABILITY OF SURVIVAL SCORING FOR TRAUMA QUALITY ASSURANCE

This study examined the application of an artificial intelligence tech nique, the neural network (NET), in predicting probability of survival (Ps) for patients with penetrating trauma. A NET is a computer constr uct that can detect complex patterns within a data set. A NET must be ''trained'' by supplying a series of input patterns and the correspond ing expected output (e.g., survival). Once trained, the NET can recall the proper outputs for a specific set of inputs. It can also extrapol ate correct outputs for patterns never before encountered. A neural ne twork was trained on Revised Trauma Score, Injury Severity Score, age, and survival data contained in 3500 of 8300 state registry records of all patients with penetrating trauma reported in Pennsylvania from 19 87 through 1990. The remaining 4800 records were analyzed by TRISS, AS COT, and the trained NET. Sensitivity (accuracy of predicting death) a nd specificity (accuracy of predicting survival) were 0.840 and 0.985 for TRISS, 0.842 and 0.985 for ASCOT, and 0.904 and 0.972 for the neur al network. This represents a decrease in the number of improperly cla ssified (''unexpected'') deaths, from 73 for TRISS and 72 for ASCOT, t o 44 for the neural network. The increased sensitivity was statistical ly significant by Chi-square analysis. The NET for penetrating trauma provided a more sensitive but less specific technique for calculating Ps than did either TRISS or ASCOT. This translated into a 40% reductio n in the number of deaths requiring review, and the potential for more efficient use of quality assurance resources.