PREDICTION OF RIB FRACTURE INJURY OUTCOME BY AN ARTIFICIAL NEURAL-NETWORK

Outcome-based therapy is becoming the standard for assessing patient c are efficacy, This study examines the ability of an artificial neural network to predict rib fracture injury outcome based on 20 intake vari ables determined within 1 hour of admission, The data base contained 5 80 patient records with four outcome variables: Length of hospital sta y (LOS), ICU days, Lived, and Died, A 522-patient training set and a 5 8-patient test set were randomly selected, Nine networks were set up i n a feed-forward, back-propagating design with each trained under diff erent initial conditions, These networks predicted the test set outcom e variables with an accuracy as high as 98% at the 80% testing level, Internal weight matrix examination indicated that age, ventilatory sup port, and high trauma scores were strongly associated with both ICU da ys and mortality, Being female, injury severity, and injury type were associated with increased LOS. Smoking and rib fracture number were lo w-level predictors of the four outcome variables.