easy to use these databases and we must use and develop advanced methods to extract useful information from them. Among all clinical database, using clinical laboratory data is important because it is inexpensive and accessible, and can also easily represent the general condition of the patient. Therefore, using machine learning tools for analyzing laboratory data can provide a good basis for research and knowledge discovery. During last decades, many researchers investigate different type of laboratory data, specially blood test. They use various machine learning methods aiming reducing the laboratory costs, increasing the accuracy of prognosis and diagnosis, and finding correlations among variables. In this thesis, we consider blood tests data from a clinical laboratory in Isfahan to find correlations among variables. One of main challenge for analyzing such a real data is large amount of missing data. In this regard, we use existing imputation methods and propose a new imputation method based on Bayesian network which fill each of variables with a specific Bayesian network defined for that variable. Finally, we will consider several کلید واژه های انگلیسی : 1-Machine learning 2-Data mining 3- Laboratory data 4- Test result prediction
