The prevalence of type 2 diabetes is increasing at an alarming rate. Various complications are associated with type 2 diabetes, with diabetic nephropathy being the leading cause of renal failure among diabetics. Often, when patients are diagnosed with diabetic nephropathy, their
renal functions have already been significantly damaged, speeding up the progression towards end stage renal disease. Therefore, a risk prediction tool may be beneficial for the implementation of early treatment and prevention. In the present study, we propose to develop a prediction model integrating clustering and classification approaches for the
identification of diabetic nephropathy among type 2 diabetes patients. Clinical and
genotyping data are obtained from 345 type 2 diabetic patients(160 with non-diabetic
nephropathy and 185 with diabetic nephropathy). The performance of using clinical features alone for cluster-based classification is compared with that of utilizing a combination of clinical and genetic attributes. We find that the inclusion of genetic features yield better
prediction results. Further refinement of the proposed approach has the potential to facilitate the accurate identification of diabetic nephropathy and the development of better treatment in a clinical setting.
The 3rd International Congress on Natural Sciences and Engineering (ICNSE'14), pp. 861-867.