Method for predicting risk of starting renal replacement therapy for patients with diabetic nephropathy within 3 years

Abstract

The invention relates to a method for predicting the risk of starting renal replacement therapy for patients with diabetic nephropathy within 3 years, comprising the following steps: collecting clinical data of a large number of patients with diabetic nephropathy and not starting renal replacement therapy yet, and tracking and following up whether the patients starts renal replacement therapy after 3 years; performing univariate logistic regression of the collected data according to whether the renal replacement therapy starts to screen out risk factors; including variables screened out by univariate analysis and variables considered clinically meaningful into an initial multivariate logistics model to obtain a prediction model containing relevant risk factors; verifying the accuracy of the prediction model, assigning values to each risk factor in the model, and drawing a corresponding nomogram; converting the nomogram into an application, and inputting risk factor data for different patients to obtain the predicted risk of renal replacement therapy. The invention is useful for screening high-risk groups of patients with diabetic nephropathy, and conveniently and effectively providing clinical guidance for patients with diabetic nephropathy.

Description

technical field [0001] The invention relates to the field of risk prediction of renal replacement therapy, in particular to a method for predicting the risk of diabetic nephropathy patients entering renal replacement therapy within 3 years. Background technique [0002] Diabetic nephropathy is one of the important causes of end-stage renal disease, which brings a heavy economic burden to society and families. The onset of diabetic nephropathy is insidious and progresses slowly, and there are not many symptoms related to early kidney disease. In the early stage of nephropathy, the kidneys are enlarged, the glomerular filtration function is hyperactive, and the trace amount of protein can last for many years, and it is not easy to be noticed. Most patients with diabetic nephropathy are noticed when they have obvious proteinuria or significant edema. Therefore, early prediction of diabetic nephropathy into end-stage renal disease has become a key issue. [0003] The currently...

AI Technical Summary

Problems solved by technology

However, this model is mainly aimed at all patients with chronic kidney disease stage 3-4, and patients with diabetic nephropathy have a higher risk of entering end-stage renal disease than other patients with chronic kidney disease. Is the current KFRE model more effective for patients with diabetic nephropathy? Good predictability is uncertain

Other risk models aimed at predicting diabetic nephropathy are mostly mentioned in the literature, and have not been further transformed into web calculators or APPs, which cannot provide further clinical guidance for patients with diabetic nephropathy

Images