The purpose of this study was to assess the feasibility of machine learning (ML) in predicting the risk of end-stage kidney disease (ESKD) from patients with chronic kidney disease (CKD). Data were obtained from a longitudinal CKD cohort. Predictor variables included patients’ baseline characteristics and routine blood test results. The outcome of interest was the presence or absence of ESKD by the end of 5 years. Missing data were imputed using multiple imputation. Five ML algorithms, including logistic regression, naïve Bayes, random forest, decision tree, and K-nearest neighbors were trained and tested using fivefold cross-validation. The performance of each model was compared to that of the Kidney Failure Risk Equation (KFRE). The dataset contained 748 CKD patients recruited between April 2006 and March 2008, with the follow-up time of 6.3 ± 2.3 years. ESKD was observed in 70 patients (9.4%). Three ML models, including the logistic regression, naïve Bayes and random forest, showed equivalent predictability and greater sensitivity compared to the KFRE. The KFRE had the highest accuracy, specificity, and precision. This study showed the feasibility of ML in evaluating the prognosis of CKD based on easily accessible features. Three ML models with adequate performance and sensitivity scores suggest a potential use for patient screenings. Future studies include external validation and improving the models with additional predictor variables.

Background/Aims: Urotensin II (UII) and its receptor are highly expressed in the kidney tissue of patients with diabetic nephropathy (DN). The aim of this study is to examine the roles of UII in the induction of endoplasmic reticulum stress (ER stress) and Epithelial-mesenchymal transition (EMT) in DN in vivo and in vitro. Methods: Kidney tissues were collected from patients with DN. C57BL/6 mice and mice with UII receptor knock out were injected with two consecutive doses of streptozotocin to induce diabetes and were sacrificed at 3^th week for in vivo study. HK-2 cells in vitro were cultured and treated with UII. Markers of ER stress and EMT, fibronectin and type IV collagen were detected by immunohistochemistry, real time PCR and western blot. Results: We found that the expressions of protein of UII, GRP78, CHOP, ALPHA-SMA, fibronectin and type IV collagen were upregulated while E-cadherin protein was downregulated as shown by immunohistochemistry or western blot analysis in kidney of diabetic mice in comparison to normal control; moreover expressions of GRP78, CHOP, ALPHA-SMA, fibronectin and type IV collagen were inhibited while E-caherin expression was enhanced in kidney in diabetic mice with UII receptor knock out in comparison to C57BL/6 diabetic mice. In HK-2 cells, UII induced upregulation of GRP78, CHOP, ALPHA-SMA, fibroblast-specifc protein 1(FSP-1), fibronectin and type collagen and downregulation of E-cadherin. UII receptor antagonist can block UII-induced ER stress and EMT; moreover, 4-PBA can inhibit the mRNA expression of ALPHA-SMA and FSP1 induced by UII in HK-2 cells. Conclusions: We are the first to verify UII induces ER stress and EMT and increase extracellular matrix production in renal tubular epithelial cell in early diabetic mice. Moreover, UII may induce renal tubular epithelial EMT via triggering ER stress pathway in vitro, which might be the new pathogenic pathway for the development of renal fibrosis in DN.

Our work first demonstrated that urinary phospholipids might be biomarkers for the chronic kidney disease patients. Increased urinary phospholipids in chronic kidney disease patients might result from proteinuria, damaged kidney function or proteinuria induced hypoalbuminemia or lipotoxicity.

Background/Aims: To investigate the change of intrarenal renin-agiotensin system (RAS) and its role in high-salt induced hypertension. Methods: Wistar rats were divided into normal-salt (NS), high-salt diet (HS) and high-salt diet with Losartan group (HS+L), for 6 weeks. Systolic blood pressure (SBP) was monitored. Blood and urine samples were collected every 2 weeks. Angiotensinogen (AGT) was measured by ELISA. AGT mRNA and protein were measured by real-time PCR and immunohistochemistry. Renin activity and angiotensin II (Ang II) were measured by radioimmunoassay. Results: HS versus NS group, SBP increased from 2^nd week (P<0.05), urinary protein increased at 6^th week (P<0.05). Although plasma renin, AGT and Ang II had no significant changes (P>0.05), renal cortex renin, AGT, and Ang II increased significantly in HS (P<0.05). In HS+L, Losartan failed to reduce SBP (P>0.05) but abolished the increase of proteinuria (P<0.01), renal cortex renin, AGT, Ang II and urinary AGT reduced (P<0.05) while plasma renin, AGT and Ang II enhanced (P<0.05) when compared with HS. Urinary AGT was positively correlated with renal AGT (r=0.592, P <0.01) and Ang II (r=0.726, P <0.01). Conclusion: Inappropriate response of the renal RAS to a high salt diet may contribute to hypertension and renal damage, and urinary AGT could reflect intrarenal RAS activity.

Background/Aims: Skeletal muscle atrophy is one of the main manifestations of protein energy wasting. We hypothesized that urotensin II (UII) can lead to skeletal muscle atrophy through upregulating autophagy and affecting Irisin precursor fibronectin type III domain containing 5 (FNDC5) expressions. Methods: Three animal models (the sham operation, wild-type C57BL/6 mice with 5/6 nephrectomy, UII receptor (UT) gene knockout (UTKO) mice with 5/6 nephrectomy) were designed. Skeletal muscle weight, cross-sectional area (CSA) along with UII, FNDC5, LC3, and p62 expression were investigated. C2C12 cells were differentiated for up to 4 days into myotubes. These cells were then exposed to different UII concentrations (10–5 to 10–7 M) for 6–12 h and analyzed for the expressions of autophagic markers. These cells were also exposed to the same predetermined UII concentrations for 48–72 h and analyzed for the FNDC5 expression. Myotube diameter was measured. Results: Upregulation of UII expression in skeletal muscle tissue was accompanied by reduced muscle weight and skeletal muscle CSA in the 2 posterior limbs, upregulated autophagy markers expression, and downregulated FNDC5 expression in 5/6 nephrectomy mice. The decrease of skeletal muscle weight, skeletal muscle CSA, downregulation of FNDC5 expression, and the upregulation of autophagy markers were inhibited in UTKO with 5/6 nephrectomy mice. Our in vitrostudy showed that UII could directly decrease myotube diameter, induce autophagy markers upregulation, and inhibit expression of FNDC5. When UII receptor gene was interfered by UT-specific siRNA, UII induced autophagy markers upregulation and FNDC5 downregulation were inhibited. Conclusion: We are the first to verify UII induces mice skeletal muscle atrophy associated with enhanced skeletal muscle autophagy and inhibited FNDC5 expression in chronic renal failure.