Development and validation of a risk prediction model for diabetic kidney disease in patients with diabetic retinopathy

Abstract

Diabetic retinopathy (DR) and diabetic kidney disease (DKD) are the most common microvascular complications associated with type 2 diabetes mellitus (T2DM). However, the occurrence of DR and DKD is not parallel. The aim of our study is to identify the risk factors for combining DKD in T2DM patients with pre-existing DR and construct a nomogram predictive model to identify high-risk patients with DR combined with DKD. We retrospectively reviewed 683 T2DM patients with DR from March 2017 to March 2023. The patients were divided into the DR group and the DR combined with DKD group. The hold-out method was used to randomly divide all subjects into a training set (70%) and a validation set (30%). Using multivariate logistic regression, we identified eight independent risk factors: fibrinogen (FIB), albumin (ALB), atherogenic index of plasma (AIP), low-density lipoprotein cholesterol (LDL-C), body mass index (BMI), classification of DR, gender, and history of hypertension. These factors were used to construct the nomogram prediction model. The model's discriminative ability was assessed using receiver operating characteristic (ROC) curve analysis, yielding an area under the curve (AUC) of 0.780 (95% CI: 0.736-0.823) in the training set and 0.739 (95% CI: 0.668-0.809) in the validation set. Calibration curves and decision curve analysis (DCA) further demonstrated the model's clinical utility. Additionally, to explore potential genetic predisposition, single nucleotide polymorphism (SNP) genotyping analysis was conducted on a subset of 50 randomly selected patients (25 from each group). The results suggested that the rs6591190 and rs12146493 loci of the AP5B1 gene might be associated with an increased susceptibility to DKD in patients with DR, warranting further investigation. In summary, our nomogram represents a valuable tool for identifying T2DM patients with DR who are at high risk for developing DKD.

Keywords: diabetic kidney disease; diabetic retinopathy; nomogram; risk factors; type 2 diabetes mellitus.

Figure 1

Nomogram to predict the risk of DKD for patients with DR. FIB, fibrinogen; ALB, albumin; AIP, atherogenic index of plasma; LDL-C, low density lipoprotein cholesterol; BMI, body mass index; DR, diabetic retinopathy; PDR, proliferative diabetic retinopathy; NPDR, non-proliferative diabetic retinopathy.

Figure 2

The ROC curves for training set (A) and validation set (B). The part below the blue line is the AUC of the model. AUC, area under curve.

Figure 3

Calibration curves for training set (A) and validation set (B). The solid line represents the model after calibration. The closer the calibration curve of the model is to the ideal line, the better the model’s prediction accuracy.

Figure 4

Decision curve analysis for training set (A) and validation set (B). The red line indicates that all patients experienced DKD and the green line represents that no patients experience DKD. The blue line represents the nomogram model. The curves show that the model is clinically beneficial across a relatively wide range of threshold probabilities.