Device for predicting development risk of kidney of ANCA related small vasculitis and model training method

Abstract

The present disclosure provides a device and a model training method for predicting the risk of kidney development against neutrophil cytoplasm antibody-associated small vasculitis (ANCA). The apparatus includes: an input unit configured to input, as input variables, values of three clinical pathological parameters of a target user having anti-neutrophil cytoplasm antibody-associated small vasculitis, the three clinical pathological parameters comprise a normal glomerular percentage as a first continuous variable, an estimated glomerular filtration rate as a second continuous variable and interstitial fibrosis / renal tubular atrophy as a third classification variable; a risk assessment unit configured to input the three input variables into a pre-trained risk assessment model based on a proportional risk regression model, the risk assessment model calculating, according to the three input variables, one or more percentage values indicating the likelihood of the target user progressing to end-stage nephropathy after a predetermined one or more time periods; and an output unit configured to output the one or more percentage values.

Description

technical field [0001] The present disclosure relates to the field of disease prognosis models. In particular, the present disclosure relates to a device for predicting the risk of renal development of antineutrophil cytoplasmic antibody (ANCA)-associated small vessel inflammation and training for predicting the risk of renal development of ANCA-associated small vessel inflammation Methods for risk assessment models. Background technique [0002] Antineutrophil cytoplasmic antibody (ANCA)-associated vasculitis (AAV) is a group of diseases characterized by necrotizing vasculitis, including microscopic polyangiitis (MPA) , granulomatous polyangiitis (GPA) and eosinophilic granulomatous polyangiitis (EGPA), usually accompanied by elevated serum autoantibodies (anti-proteinase 3 antibodies and anti-myeloperoxidase antibodies). Kidney is one of the most commonly affected organs of AAV, in which 80-100% of MPA patients and 38-70% of GPA patients will manifest as glomerulonephrit...

AI Technical Summary

Problems solved by technology

[0005] However, because the scoring model uses categorical variables, the information in the data cannot be fully and effectively mined, and the consistency of the model prediction value and the actual observation value of such a scoring model is not good after analysis.

In addition, such a scoring model can only give descriptive results such as "low risk" and "high risk", and patients cannot make more accurate and effective treatment decisions

Images