AN ARTIFICIAL NEURAL NETWORK-BASED MODEL FOR PREDICTING ANNUAL DOSE IN HEALTHCARE WORKERS OCCUPATIONALLY EXPOSED TO DIFFERENT LEVELS OF IONIZING RADIATION.

Abstract

We presented an artificial intelligence-based model to predict annual effective dose (AED) value of health workers. Potential factors affecting AED and the results of annual blood tests were collected from 91 radiation workers. Filter-based feature selection strategy revealed that the eight factors plate, red cell distribution width (RDW), educational degree, nonacademic course in radiation protection (hour), working hours per month, department and the number of procedures done per year and work in radiology department or not (0,1) were the most important predictors for AED. The prediction model was developed using a multilayer perceptron neural network and these prediction parameters as inputs. The model provided favorable accuracy in predicting AED value while a regression model did not. There was a strong linear relationship between the predicted AED values and the measured doses (R-value =0.89 for training samples and 0.86 for testing samples). These results are promising and show that artificial neural networks can be used to improve/facilitate dose estimation process.