Medical data mining issues and experiments
Data analysis and data mining methods have been extensively applied for industrial and business applications; however, their utilization in medicine and healthcare is sparse. The data mining techniques such as Neural Network, Naive Bayes, and Association rules are at present not well explored on medical databases. The application of data mining techniques on medical databases is certainly a challenging process considering the high volume, complexity, and poor quality of the medical databases. In this thesis, we discuss the challenges facing the medical data mining. The focus is on the issues, difficulties and the discovered rules. Using commercially available data mining tools namely XLMiner, Knowledge Studio, different data mining techniques such as Neural Network, Naive Bayes, and Association rules, Classification Trees are applied on Thrombosis medical database. While some results confirm with experts, some are trivial and redundant rules.