A Computational Environment for Medical Diagnosis Support Systems

Abstract

As more health-care providers invest on computerised medical records, more clinical data is made accessible, and more of clinical insights will become reliable. As data collection technologies advance, a plethora of data is available in almost all domains of one.s lives, being of particular interest to this work that of Medicine. Indeed, Intelligent Diagnosis Systems (IDS) with built-in functions for knowledge discovery or data mining, concerning with extracting and abstracting useful rules from such huge repositories of data, are becoming increasingly important for purposes such as of offering better service or care, or obtaining a competitive advantage over different problem.s solving strategies or methodologies [1]. In particular, embedding Machine Learning technology into IDS’ systems seems to be well suited for medical diagnostics in specialized medical domains, namely due to the fact that automatically generated diagnosis rules slightly outperform the diagnostic accuracy of specialists when physicians have available the same information as the machine.