Extraction of Frequent Patterns from Diabetes Cluster

Abstract

Data mining is the process of discovering interesting knowledge, such as patterns, associations, changes, anomalies and significant structures, from large amounts of data stored in databases, data warehouses, or other information repositories. In this paper, we have proposed an efficient approach for the extraction of significant patterns from the patients database for diabetes prediction. The diagnosis of diseases is a significant and tedious task in medicine. To facilitate the diagnosis process, the effort to utilize knowledge and experience of numerous specialists and clinical screening data of patients collected in databases is considered a valuable option. The patients database is clustered using the KMIX clustering algorithm, which will extract the data relevant to diabetes from the database. Subsequently the frequent patterns are mined from the extracted data, relevant to diabetes, using the MAFIA algorithm. Then the significant patterns to diabetes diagnosis are chosen from these frequent patterns. These patterns can be used to apply in the healthcare system.