“Bayesian algorithm implementation in a real time calculating risk assessment model on benzene”

The objective of the current study was the composition of a reliable modeling platform in order to calculate in real time the estimated health risk for filling station employees evaluating the current environmental parameters (traffic, meteorological and amount of fuel traded) determined by the proper sensors. A set of Artificial Neural Networks (ANNs) was developed to predict benzene exposure pattern for the filling station employees. Furthermore, a Physiology Based Pharmaco-Kinetic (PBPK) risk assessment model was developed in order to calculate the lifetime probability distribution of leukemia to the employees, fed by data obtained by the ANN model. Bayesian algorithm was involved in crucial points of both model sub compartments. The application was evaluated in two filling stations (one urban and one rural). Among several algorithms implied for the development of the ANN exposure model, the Bayesian regularization provided the best results and in conclusion seemed to be a promising technique in the prediction of the exposure pattern of that occupational population group. On assessing the estimated leukemia risk under the scope of providing a distribution curve based on the exposure levels and the different susceptibility of the population, Bayesian algorithm was a completely necessary part of the Monte Carlo approach which is integrated in the PBPK model. Conclusively, the overall above modeling systems seems capable in exploiting the information gathered by the environmental sensors in order to calculate in real time the estimated risk of leukemia for the employees of the filling station.