Pattern Based Classification of Chronic Kidney Disease Patients

Abstract

We apply a pattern-based classification method to identify clinical and genomic features associated with the progression of Chronic Kidney Disease (CKD). We analyze the African-American Study of Chronic Kidney Disease with Hypertension (AASK) dataset and construct a decision-tree classification model, consisting15 combinatorial patterns of clinical features and single nucleotide polymorphisms (SNPs), seven of which are associated with slow progression and eight with rapid progression of renal disease among AASK patients. We identify four clinical features and two SNPs that can accurately predict CKD progression. These features are validated with using sophisticated machine learning techniques including Random Forest, Nearest Neighbor, Support Vector Machines, Neural Networks, Logistic Regression, and Naive Bayes supervised learning methods. Clinical and genomic features identified in our experiments may be used in a future study to develop new therapeutic interventions for CKD patients.