COMPARATIVE-EVALUATION OF THE USE OF ARTIFICIAL NEURAL NETWORKS FOR MODELING THE EPIDEMIOLOGY OF SCHISTOSOMIASIS-MANSONI

There has been a marked increase in the application of approaches base d on artificial intelligence (AI) in the field of computer science and medical diagnosis, but AI is still relatively unused in epidemiologic al settings. In this study we report results of the application of neu ral networks (NN; a special category of AI) to schistosomiasis. It was possible to design an NN structure which can process and fit epidemio logical data collected from 251 schoolchildren in Egypt using the firs t year's data to predict second and third years' infection rates. Data collected over 3 years included age, gender, exposure to canal water and agricultural activities, medical history and examination, and stoo l and urine parasitology. Schistosoma mansoni infection rates were 50% , 78% and 66% at the baseline and the 2 follow-up periods, respectivel y. NN modelling was based on the standard back-propagation algorithm, in which we built a suitable configuration of the network, using the f irst year's data, that: optimized performance. It was implemented on a n IBM compatible computer using commercially available software. The p erformance of the NN model in the first year compared favourably with logistic regression (NN sensitivity=83% (95% confidence interval [CI] 78-88%) and positive predictive value (PPV)=63% (95% CI 57-69%); logis tic regression sensitivity=66% (95% CI 60%-72%) and PPV=59% (95% CI 53 %-65%). The NN model generalized the criteria for predicting infection over time better than logistic regression and showed more stability o ver time, as it retained its sensitivity and specificity and had bette r false positive and negative profiles than logistic regression. The p otential of NN-based models to analyse and predict wide-scale control programme data, which are inevitably based on unstable egg excretion r ates and insensitive laboratory techniques, is promising but still unt apped.