A Survey on Data Mining Algorithms and Techniques in Medicine

Abstract

Medical Decision Support Systems (MDSS) industry collects a huge amount of data, which is not properly mined and not put to the optimum use. This data may contain valuable information that awaits extraction. The knowledge may be encapsulated in various patterns and regularities that may be hidden in the data. Such knowledge may prove to be priceless in future medical decision making. Available medical decision support systems are based on static data, which may be out of date. Thus, a medical decision support system that can learn the relationships between patient histories, diseases in the population, symptoms, pathology of a disease, family history, and test results, would be useful to physicians and hospitals. This paper provides an in-depth review of available data mining algorithms and techniques. In addition to that, data mining applications in medicine are discussed as well as techniques for evaluating them and available applications of performance metrics.

Keywords

• Data Mining
• Classification
• Decision Tree
• Neural Network
• Bayesian Network Classifier
• Evaluation Metrics