Analysis of risk factors associated with diffuse alveolar haemorrhage in patients with ANCA-associated vasculitis and construction of a risk prediction model using line graph

OBJECTIVES: This study aims to analyse the risk factors associated with diffuse alveolar haemorrhage (DAH) in patients with ANCA-associated vasculitis (AAV) and construct a risk prediction model using line graph. METHODS: A retrospective study was conducted from January 2012 to May 2023 at the First Clinical College of Three Gorges University, focusing on patients diagnosed with AAV. Clinical and laboratory data were collected from these patients. The potential predictors subsets of high-risk AAV combined with DAH were screened by LASSO regression and 10-fold cross-validation method, and determined by using multivariate Logistic regression analysis, then were used for developing a prediction nomogram for high-risk AAV combined with DAH using the R software. ROC curve analysis was used to validate the model's stability. Internal validation was performed using a bootstrap method. The discrimination of the nomogram was determined by calculating the average consistency index(C-index). The calibration curve was used to assess the calibration of the nomogram. RESULTS: A total of 234 patients with AAV were included, among whom 85 developed DAH, with an incidence rate of 36%, and the average age was 63±12. Multivariable logistic regression analysis showed that Age OR=1.037 (95%CI: 1.006, 1.071), p=0.019, platelet count (PLT) OR=0.996 (95%CI: 0.992, 0.999), p=0.029, ESR OR=1.028 (95%CI: 1.015, 1.042), p<0.01, HB OR=0.978 (95%CI: 0.959, 0.996), p=0.024, and haematuria OR=3.77 (95%CI: 1.677, 8.976), p=0.001 were found to be independent predictors of AAV combined with DAH and were used to construct a nomogram. The AUCROC values of the nomogram for DAH in AAV patients was 0.852 (95%CI: 0.801, 0.903), and the C-index could reach 0.824 after internal verification, showing good differentiation and consistency. CONCLUSIONS: The new nomogram, which included age, Hb, ESR, PLT and haematuria as variables, had the potential to predict the risk of AAV patients complicated with DAH.