BackgroundDiabetic kidney disease (DKD) patients are facing an extremely high risk of cardiovascular disease (CVD), which is a major cause of death for DKD patients. We aimed to build a deep learning model to predict CVD risk among DKD patients and perform risk stratifying, which could help them perform early intervention and improve personal health management.MethodsA retrospective cohort study was conducted to assess the risk of the occurrence of composite cardiovascular disease, which includes coronary heart disease, cerebrovascular diseases, congestive heart failure, and peripheral artery disease, in DKD patients. A least absolute shrinkage and selection operator (LASSO) regression was used to perform the variable selection. A deep learning-based survival model called DeepSurv, based on a feed-forward neural network was developed to predict CVD risk among DKD patients. We compared the model performance with the conventional Cox proportional hazards (CPH) model and the Random survival forest (RSF) model using the concordance index (C-index), the area under the curve (AUC), and integrated Brier scores (IBS).ResultsWe recruited 890 patients diagnosed with DKD in this retrospective study. During a median follow-up of 10.4 months, there are 289 patients who sustained a subsequent CVD. Seven variables, including age, high density lipoprotein (HDL), hemoglobin (Hb), systolic blood pressure (SBP), smoking status, 24 h urinary protein excretion, and total cholesterol (TC), chosen by LASSO regression were used to develop the predictive model. The DeepSurv model showed the best performance, achieved a C-index of 0.767(95% confidence intervals [CI]: 0.717–0.817), AUC of 0.780(95%CI: 0.721–0.839), and IBS of 0.067 in the validation set. Then we used the cut-off value determined by ROC (receiver operating characteristic) curve to divide the patients into different risk groups. Moreover, the DeepSurv model was also applied to develop an online calculation tool for patients to conduct risk monitoring.ConclusionA deep-learning-based predictive model using seven clinical variables can effectively predict CVD risk among DKD patients and perform risk stratification. An online calculator allows its easy implementation.

Background RNA methylation is a widely known post-transcriptional regulation which exists in many cancer and immune system diseases. However, the potential role and crosstalk of five types RNA methylation regulators in diabetic nephropathy (DN) and immune microenvironment remain unclear. Methods The mRNA expression of 37 RNA modification regulators and RNA modification regulators related genes were identified in 112 samples from 5 Gene Expression Omnibus datasets. Nonnegative Matrix Factorization clustering method was performed to determine RNA modification patterns. The ssGSEA algorithms and the expression of human leukocyte antigen were employed to assess the immune microenvironment characteristics. Risk model based on differentially expression genes responsible for the modification regulators was constructed to evaluate its predictive capability in DN patients. Furthermore, the results were validated by using immunofluorescence co-localizations and protein experiments in vitro. Results We found 24 RNA methylation regulators were significant differently expressed in glomeruli in DN group compared with control group. Four methylation-related genes and six RNA regulators were introduced into riskScore model using univariate Logistic regression and integrated LASSO regression, which could precisely distinguish the DN and healthy individuals. Group with high-risk score was associated with high immune infiltration. Three distinct RNA modification patterns were identified, which has significant differences in immune microenvironment, biological pathway and eGFR. Validation analyses showed the METTL3, ADAR1, DNMT1 were upregulated whereas YTHDC1 was downregulated in DN podocyte cell lines comparing with cells cultured by the normal glucose. Conclusion Our study reveals that RNA methylation regulators and immune infiltration regulation play critical roles in the pathogenesis of DN. The bioinformatic analyses combine with verification in vitro could provide robust evidence for identification of predictive RNA methylation regulators in DN.