Artificial neural networks in medical diagnosis

Abstract
An extensive amount of information is currently available to clinical specialists, ranging from details ofclinical symptoms to various types of biochemical data and outputs of imaging devices. Each type of dataprovides information that must be evaluated and assigned to a particular pathology during the diagnosticprocess. To streamline the diagnostic process in daily routine and avoid misdiagnosis, artificial intelligencemethods (especially computer aided diagnosis and artificial neural networks) can be employed. Theseadaptive learning algorithms can handle diverse types of medical data and integrate them into categorizedoutputs. In this paper, we briefly review and discuss the philosophy, capabilities, and limitations of artificialneural networks in medical diagnosis through selected examples