ANALYSING INTERACTIONS OF RISK FACTORS ACCORDING TO RISK LEVELS FOR HEMODIALYSIS PATIENTS IN TURKEY: A DATA MINING APPLICATION

Authors : Yunus ALTINTAS, Hadi GOKCEN, Mahir ULGU, Neslihan DEMİREL

Pages : 829-839

View : 22 | Download : 10

Publication Date : 2011-02-10

Article Type : Other Papers

Abstract :Normal 0 21 false false false TR X-NONE X-NONE MicrosoftInternetExplorer4 /* Style Definitions */ table.MsoNormalTable {mso-style-name:`Normal Tablo`; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-qformat:yes; mso-style-parent:``; mso-padding-alt:0cm 5.4pt 0cm 5.4pt; mso-para-margin-top:0cm; mso-para-margin-right:0cm; mso-para-margin-bottom:10.0pt; mso-para-margin-left:0cm; line-height:115%; mso-pagination:widow-orphan; font-size:11.0pt; font-family:`Calibri`,`sans-serif`; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-fareast-font-family:`Times New Roman`; mso-fareast-theme-font:minor-fareast; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin;} The End Stage Renal Disease insert ignore into journalissuearticles values(ESRD); as a chronical health problem requires an expensive and a lifetime treatment called hemodialysis. It is important to obtain new information in order to reduce the cost of the treatment and to improve the quality of patient’s life. Treatment period requires a lot of clinical tests related to the risk factors for monitoring patient’s health and effectiveness of the treatment. These factors vary depending on demographic parameters such as age, gender, race, clinical parameters such as hematocrit level, albumine level, and also dialysis treatment prescription. In this paper, a data mining application including data preprocessing, data transformation, data mining algorithms and interpretation is used to find out patterns of risk factors as decision rules according to risk levels for dialysis patients in Turkey. A data set is formed by collecting 76 parameters of 170 patients on dialysis for 12 or more months at a dialysis center. CMS HCC insert ignore into journalissuearticles values(the Centers for Medicare and Medicaid Services -- Hierarchical Coexisting Conditions); ESRD model which includes relative coefficients of age, gender and comorbid diseases as scoring parameters is employed on data set in order to calculate risk scores for each patient and these scores are added to data set as a parameter called “Risk Score”. ESTARD and WEKA softwares are used in order to achieve classification, clustering and decision tree algorithms. Decision rules as results of application are interpreted with domain expert for medical significance.   Keywords : Hemodialysis, Risk level, Risk score, Data Mining.  
Keywords : Hemodialysis, Risk level, Risk score, Data Mining