Constraint Satisfaction Neural Network for medical diagnosis
This objective of this study was to explore how a Constraint Satisfaction Neural Network (CSNN) can be used for medical diagnostic tasks. The study is based on a database of 500 patients who underwent breast biopsy at Duke University Medical Center due to suspicious mammographic findings. A CSNN was developed and evaluated to predict the biopsy result from the patient's mammographic findings. The diagnostic performance of the CSNN network was compared to a traditional backpropagation (BP) neural network and a case-based-reasoning (CBR) algorithm by means of Receiver Operating characteristics (ROC) analysis. This study demonstrates (i) how CSNNs can be applied for medical diagnostic tasks and, (ii) how they can be utilized to extract meaningful clinical information regarding underlying relationships among medical findings and associated diagnoses.