Analysis of risk factors for recurrence of Budd–Chiari syndrome based on zero–inflated model

Background: Patients diagnosed with Budd–Chiari syndrome (BCS) who have undergone standardized treatments face a relatively high risk of recurrence when persistent risk factors are present. However, there are limited studies that analyze the factors influencing the frequency of recurrence using count data.
Objective: To compare the goodness of fit for count models to identify the optimal model for assessing the recurrence frequency of BCS, and further analyze the factors contributing to BCS recurrence.
Methods: The study included a total of 754 patients who were admitted to the Affiliated Hospital of Xuzhou Medical University between January 2015 and July 2022 and met the inclusion criteria. Among them, 243 experienced recurrences during the follow-up period. Using the recurrence frequency of patients with BCS as the dependent variable in the training cohort, we constructed four different count outcome models in R: the Poisson model, the negative binomial (NB) model, the zero-inflated Poisson (ZIP) model, and the zero-inflated negative binomial (ZINB) model. We employed the O test to detect over-dispersion in the data. The models were compared using the Vuong test, log-likelihood ratio test (LR), Akaike information criteria (AIC), corrected AIC (AICc), −2LogLikelihood (−2LL), root mean squared error (RMSE), mean absolute error (MAE), accuracy, precision, and graphical methods to select the model with the best fitting performance for exploring factors associated with BCS recurrence.
Results: Of all 754 respondents, 511 patients reported no recurrences. The mean recurrence frequency was 0.64, with a variance of 2.46. The O statistic was 55.08 (p < 0.001), indicating over-dispersion in the data. The plot of predictions revealed that the predicted values of the ZINB model closely matched the actual values. The Vuong test revealed that the ZIP model outperformed the Poisson regression model (z = 34.29, p < 0.001), and the ZINB model was superior to the NB model (z = 3.40, p < 0.001). The LR tests indicated that the NB model performed better than the Poisson regression model (χ² = 124.91, p < 0.001), and the ZINB model outperformed the ZIP model (χ² = 34.29, p < 0.001). The ZINB model had the lowest −2LL (1100.26), AIC (1182.26), AICc (1188.40), MAE (0.94), and RMSE (2.02), whereas it achieved the highest accuracy (58.94%) and precision (28.07%) among the four models. In the ZINB model, the analysis of the counting process revealed that the variables significantly associated with recurrence frequency included age (odds ratio [OR] = 0.69; 95% confidence interval [CI]: 0.57–0.84), sex (female: OR = 1.77; 95% CI: 1.24–2.55), anticoagulant use (warfarin vs. new oral anticoagulants [NOACs]: OR = 2.11, 95% CI: 1.34–3.31; not using anticoagulants vs. NOACs: OR = 1.98, 95% CI: 1.20–3.28), absence of cirrhosis (OR = 0.57, 95% CI: 0.40–0.82), and neutrophil count (OR = 1.22, 95% CI: 1.04–1.42). The zero process analysis revealed that sex (female: OR = 22.43, 95% CI: 2.41–208.46), the type of operation (balloon dilatation combined with stent implantation vs. simple balloon dilatation: OR = 17.49, 95% CI: 1.32–231.99), anticoagulant use (warfarin vs. NOACs: OR = 7.10, 95% CI: 1.12–45.15; not using anticoagulants vs. NOACs: OR = 14.51, 95% CI: 2.33–90.24), absence of cirrhosis (OR = 0.15, 95% CI: 0.04–0.62), hospital duration (OR = 0.40, 95% CI: 0.20–0.81), and apolipoprotein A (OR = 0.37, 95% CI: 0.18–0.74) significantly impacted the likelihood of recurrence.
Conclusions: The zero-inflated model proves robust in identifying factors influencing BCS recurrence compared to other models, elucidating the influence of gender, surgery, anticoagulation, cirrhosis, hospital duration, APOA, and neutrophil count on recurrence risk and frequency of BCS patients.