Identification of Outliers in Medical Diagnostic System Using Data Mining Techniques

The outlier detection problem has important applications in the field of medical research. Clinical databases have accumulated large quantities of information about patients and their medical conditions. In this study, the data mining techniques are used to search for relationships in a large clinical database. Relationships and patterns within this data could provide new medical knowledge. The main objective of this paper is to detect the outliers and identify the influence factor in the diabetes symptoms of the patient using data mining techniques. Results are illustrated numerically and graphically. Outlier detection is a very important concept in the medical data analysis. The complex relationships that appear with regard to diabetic symptoms of the patient, diagnoses and behavior are the most promising areas of data mining. A data base may contain data objects that do not comply with the general behavior of the data. These data objects are outlier and the analysis of outlier data is referred to as outlier mining. Data mining is about finding new information from a large group of data. The problem of outlier detection for data mining is a rich area of research because the sequences are various types and outliers in sequences can be defined in multiple ways and hence there are different problem formulations. Most data mining methods discard outliers as noise or exceptions. The handling of outlier observations in a data set is one of the most important tasks in data pre-processing because of two reasons. First, outlier observations can have a considerable influence on the results of an analysis. Second, outliers are often measurement or recording errors, some of them can represent phenomena of interest, something significant from the viewpoint of the application domain. Some classical examples for inward procedures have given Hawkins (12) and Barnett and Lewis (2). Factor Analysis is useful for understanding the underlying reasons for the correlations among a group of variables. The main application of factor analytic technique is to reduce the number of variables and to detect structure in the relationships among variables that classify variables.