Problems with mining medical data

Since the early 1980´s, there has been a rapid growth of hospital information systems (HIS) for storing a large amount of laboratory examinations as databases. Thus, it is highly expected that data mining methods will find interesting patterns from these databases for reuse of stored data; this is important for medical research and practice because human beings cannot deal with such huge amounts of data. The article focuses on the characteristics of medical data and discusses how data miners deal with medical data