A case study of using artificial neural networks for classifying cause of death from verbal autopsy

Background Artificial neural networks (ANN) are gaining prominence as a met hod of classification in a wide range of disciplines. In this study ANN is applied to data from a verbal autopsy study as a means of classifying cause of death. Method A simulated ANN was trained on a subset of verbal autopsy data, and the performance was tested on the remaining data. The performance of the AN N models were compared to two other classification methods (physician revie w and logistic regression) which have been tested on the same verbal autops y data. Results Artificial neural network models were as accurate as or better than the other techniques in estimating the cause-specific mortality fraction ( CSMF). They estimated the CSMF within 10% of true value in 8 out of 16 caus es of death. Their sensitivity and specificity compared favourably with tha t of data-derived algorithms based on logistic regression models. Conclusions Cross-validation is crucial in preventing the over-fitting of t he ANN models to the training data. Artificial neural network models are a potentially useful technique for classifying causes of death from verbal au topsies. Large training data sets are needed to improve the performance of data-derived algorithms, in particular ANN models.