An approach based on probabilistic neural network for diagnosis of Mesothelioma’s disease

Malignant mesothelioma (MM) is an aggressive progress tumor that results from mesotel cells and pleura usually incurs. The two important causes, in MM etiologies are known as asbestos and erionite, both mineral fibers. Environmental asbestos exposure and MM are one of the major public health problems of Turkey. In this study, two different probabilistic neural network (PNN) structures were used for MM’s disease diagnosis. The PNN results were compared with the results of the multilayer and learning vector quantization neural networks focusing on MM’s disease diagnosis and using same database. It was observed the PNN is the best classification with 96.30% accuracy obtained via 3-fold cross-validation. The MM disease dataset were prepared from a faculty of medicine’s database using new patient’s hospital reports from south east region of Turkey.

► The study presents a comparative study for the realization of the Mesothelioma diseases diagnosis.
► The best results were obtained using the probabilistic neural network (PNN).
► The PNN system classification accuracy is highly reliable for the Mesothelioma diseases diagnosis.
► This system is useful to help the expert while deciding the healthy and patient subjects.