Rule-Mining for the Early Prediction of Chronic Kidney Disease Based on Metabolomics and Multi-Source Data

Abstract

1H Nuclear Magnetic Resonance (NMR)-based metabolic profiling is very promising for the diagnostic of the stages of chronic kidney disease (CKD). Because of the high dimension of NMR spectra datasets and the complex mixture of metabolites in biological samples, the identification of discriminant biomarkers of a disease is challenging. None of the widely used chemometric methods in NMR metabolomics performs a local exhaustive exploration of the data. We developed a descriptive and easily understandable approach that searches for discriminant local phenomena using an original exhaustive rule-mining algorithm in order to predict two groups of patients: 1) patients having low to mild CKD stages with no renal failure and 2) patients having moderate to established CKD stages with renal failure. Our predictive algorithm explores the m-dimensional variable space to capture the local overdensities of the two groups of patients under the form of easily interpretable rules. Afterwards, a L2-penalized logistic regression on the discriminant rules was used to build predictive models of the CKD stages. We explored a complex multi-source dataset that included the clinical, demographic, clinical chemistry, renal pathology and urine metabolomic data of a cohort of 110 patients. Given this multi-source dataset and the complex nature of metabolomic data, we analyzed 1- and 2-dimensional rules in order to integrate the information carried by the interactions between the variables. The results indicated that our local algorithm is a valuable analytical method for the precise characterization of multivariate CKD stage profiles and as efficient as the classical global model using chi2 variable section with an approximately 70% of good classification level. The resulting predictive models predominantly identify urinary metabolites (such as 3-hydroxyisovalerate, carnitine, citrate, dimethylsulfone, creatinine and N-methylnicotinamide) as relevant variables indicating that CKD significantly affects the urinary metabolome. In addition, the simple knowledge of the concentration of urinary metabolites classifies the CKD stage of the patients correctly.

Urinary metabolic profiling of asymptomatic acute intermittent porphyria using a rule-mining-based algorithm

“…For the supervised analysis, we used a rule-miming based approach that combines a supervised variable selection step and a classification step (Luck et al 2016 ). The rationale for the use of this approach is to avoid overfitting and provide more precise information compared to conventional methods.…”

“…The variable selection step is based on the combination of two univariate approaches: a global one, based on the χ 2 test (Scikit-learn project implementation (Pedregosa et al 2011 )), and a local one, based on a supervised rule mining algorithm (in-house implementation) (Luck et al 2015 , 2016 ). The global approach first selected variables with a chi2 test significant p value < 0.05 leading to a subset of variables.…”

“…However, these techniques do not perform an exhaustive exploration of the data. To overcome this limitation, we used a descriptive and easily understandable approach for metabolic profiling, which is based on a supervised rule-mining algorithm that locally and exhaustively explores the variable space of 1 H-NMR spectra datasets (Luck et al 2016 , 2015 ).…”

Association of Serum Soluble Urokinase Receptor Levels With Progression of Kidney Disease in Children

“…4,5 A growing body of preclinical and clinical research is evaluating novel approaches to pharmacological nephroprotection that may become available for children with CKD in the foreseeable future. 6,7 …”

Urinary NMR Profiling in Pediatric Acute Kidney Injury—A Pilot Study

“…This diversity may have helped in identifying a robust common denominator. Enhanced branched-chain amino acids and a reduction in citrate excretion has been reported previously, but for other nephropathies including chronic kidney disease, [39,40], diabetic nephropathy [41] and polycystic kidney disease [42]. They may be signs of early kidney damage, as a reduction of citrate can be a sign for mitochondrial dysfunction of the proximal tubular cell [24].…”