Background/aim: There is a need for a scoring system for predicting ICU prognosis of patients with ANCA-associated vasculitis (AAV), but there are limited data on it in the literature. Therefore, we aimed to determine the scores that can estimate the prognosis of patients with AAV during intensive care follow up. Materials and methods: All adult patients admitted to the medical ICUs of 4 reference university hospitals in Turkey due to AAV activation and/or disease/treatment complications in the last 10 years were included in this study. Demographic data, treatments before ICU, the Birmingham Vasculitis Activity Score (BVAS) score at the time of vasculitis diagnosis, and BVAS, APACHE II, SOFA, and SAPS II scores at the ICU admission, treatments, procedures, and complications during ICU stay were recorded for all AAV patients. Results: Thirty-four patients were included in the study. The median age of the patients was 60 (42–70) years, and 64.7% were male. Twenty-five patients were diagnosed with Granulomatosis with polyangiitis, and 9 were diagnosed with Microscopic polyangiitis. The most common ICU admission causes were hemorrhage (85.3%) and sepsis/septic shock (67.6%). Twenty patients (58.8%) died in the ICU follow up. There were significant differences in APACHE II (P = 0.004) and SAPS II (P = 0.044) scores between survivors and nonsurvivors, while there were no significant differences in BVAS (during diagnosis P = 0.089 and ICU admission P = 0.539) and SOFA (P = 0.097) scores. APACHE II score was found to be an independent risk factor for ICU mortality (OR = 1.231, CI 95% = 1.011–1.498, P = 0.038) according to logistic regression analysis. An APACHE II score of greater than 20.5 predicted ICU mortality with 80% sensitivity and 70% specificity (AUC = 0.8, P = 0.004, Likelihood ratio = 2.6) according to the ROC curve analysis. Conclusion: APACHE II score can be used for the prediction of ICU mortality in AAV patients.