A4: Computational Bioengineering III

CLASSIFICATION OF URINARY DIELECTRIC PROPERTIES FOR DIABETES AND CHRONIC KIDNEY DISEASE USING SUPPORT VECTOR MACHINE

Hua Nong Ting1, Peck Shen Mun1, Seyed Mostafa Mirhassani2

1University of Malaya, Malaysia
2Shahrood University of Technology, Iran

Diabetes mellitus is among the most common cause of chronic kidney disease. Urinary glucose is an essential non-invasive approach for diabetes. Meanwhile, monitoring of urinary protein is required as standard care in the diagnosis and prognostication for chronic kidney disease. Recently, dielectric properties measurement offers the potential to determine variability of urinary glucose or protein as a simple and non-destructive manner. However, the accuracy of the determination should be investigated. This study classifies the urinary dielectric properties of subjects with diabetes mellitus (DM), chronic kidney disease (CKD), and normal subjects at microwave frequency from 1 GHz to 50 GHz using support vector machine (SVM). The urinary dielectric properties measurements were conducted using open-ended coaxial probe at room temperature (25°C), 30°C and human body temperature (37°C). The highest classification accuracy was achieved at 88.72% to distinguish between diabetic and normal subjects. The urinary dielectric behavior was found optimal at 30°C for classification. The highest accuracy was achieved at 64.50% for three-group classification.
 

Organised by

Endorsed by

 

        Supported by
 

 

                          
     

       

                             
           
 

        Supporting Media