Prediction and Risk Stratification of Cardiovascular Disease in Diabetic Kidney Disease Patients

Abstract

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.

Association of systemic immune-inflammation index with diabetic kidney disease in patients with type 2 diabetes: a cross-sectional study in Chinese population

“…Recently, growing evidence suggests that SII may be associated with metabolic disorder and its components, such as central obesity, nonalcoholic fatty liver disease, metabolic syndrome, dyslipidemia, and hypertension ( 15 – 19 ), all of which have been reported to be involved in the development and progression of DKD ( 20 ). Furthermore, it has been demonstrated that elevated SII levels are associated with subclinical atherosclerosis, and can efficiently predict the development, prognosis and clinical outcomes of various atherosclerotic macrovascular diseases, such as acute coronary syndrome, myocardial infarction, coronary artery disease (CAD), heart failure (HF), stroke, peripheral arterial disease (PAD), and diabetic foot infections ( 4 , 8 – 10 , 13 , 15 , 16 , 18 , 21 – 27 ), all of which were closely related to DKD ( 28 , 29 ). Given that chronic inflammation and metabolic disorder are involved in the pathogenesis of DKD, and that atherosclerotic macro- and microvascular diseases share multiple common pathogenetic pathways and risk factors, it is reasonable to hypothesize that T2DM individuals with high SII would have a high risk for DKD.…”

Association Between Liver Fibrosis Score and Diabetic Kidney Disease: A Retrospective Cross-Sectional Study of Hospitalized Patients

“…Despite the updated prevention and treatment strategies for DKD, the current status remains unsatisfactory, indicating that the presence and risk for progression of DKD are associated with several unknown causes. Indeed, patients with DKD frequently present with a range of chronic comorbidities, including cardiovascular disease, hypertension, and dyslipidemia [1,2]. Clinically, patients with these chronic comorbidities are more likely to develop end-stage renal disease than those with DKD without these chronic comorbidities [3,4].…”