Development of a “ready to use” graphical tool based on artificial neural network classification: application for the prediction of late fecal incontinence after prostate cancer radiotherapy

Artificial Neural Networks (ANNs) are a valid tool to develop predictive models of radiotherapy outcomes, especially when complex nonlinear relationships between input and output variables are present. However, they are often considered as impenetrable "black boxes", with the original information being inscrutably elaborated throughout the network of neurons. In this study, we develop a readable ANN-based graphical tool for the prediction of late faecal incontinence after prostate cancer radiotherapy.

https://ift.tt/2ng0rZd