Classification of Chronic Kidney Disease Patients via k-important Neighbors in High Dimensional Metabolomics Dataset

Chronickidneydisease(CKD), characterizedbyprogressivelossofrenalfunction, is becoming a growing problem in the general population. New analytical technologies such as “omics”-based approaches, including metabolomics, provide a useful platform for biomarker discovery and improvement of CKD management. In metabolomics studies, not only prediction accuracy is attractive, but also variable importance is critical because the identified biomarkers reveal pathogenicmetabolicprocessesunderlyingthe progressionof chronickidney disease. We aimed to use k-important neighbors (KIN), for the analysis of a high dimensional metabolomics dataset to classify patients into mild or advanced progression of CKD. Urine samples were collected from CKD patients (n=73). The patientswere classified based on metabolite biomarkers into the two groups: mild CKD (glomerular filtration rate (GFR) 60 mL/min per 1·73 m^2) and advanced CKD (GFR 60 mL/min per 1·73 m^2). Accordingly, 48 and 25 patientswere inmild(class 1) andadvanced(class 2) groupsrespectively. Recently, KIN was proposed as a novel approach to high dimensional binary classification settings. Through employing a hybrid dissimilarity measure in KIN, it is possible to incorporate information of variables and distances simultaneously. TheproposedKINnotonlyselectedafewnumberofbiomarkers,italsoreachedahigher accuracy compared to traditional k-nearest neighbors (61.2% versus 60.4%) and random forest (61.2% versus 58.5%) which are currently known as the best classifieres. Real metabolomics dataset demonstrate the superiority of proposed KIN versus KNN in terms of both classification accuracy and variable importance.