Objective To develop and validate a nomogram based on Doppler ultrasound hemodynamics at 2 weeks post-surgery for predicting autogenous arteriovenous fistula (AVF) maturation failure. Methods Patients with end-stage renal disease who underwent first-time AVF surgery between March 2023 and September 2025 were selected. Patients were classified into the maturation group and maturation failure group according to AVF status at 6 weeks post-surgery. Predictive variables were screened using LASSO regression, and a nomogram was constructed via multivariable logistic regression. Model performance was evaluated using area under the curve (AUC), calibration curves, and decision curve analysis. Results A total of 260 patients were included. Among 260 patients, 94 (36.2%) experienced AVF maturation failure. Seven variables were selected by LASSO regression: female gender, diabetes, draining vein diameter, vascular access blood flow, pulsatility index, vein depth, and anastomotic stenosis. Multivariable logistic regression demonstrated that female gender, diabetes, smaller draining vein diameter, lower vascular access blood flow, and higher pulsatility index were independent predictors (P<0.05). The nomogram yielded an AUC of 0.924 [95%CI (0.893, 0.956)], with a bootstrap-corrected AUC of 0.912. The model showed good calibration (χ2=3.703, P=0.883) and clinical net benefit. Conclusion The established nomogram exhibits robust performance and can be integrated into the routine 2-week post-operative follow-up to facilitate early identification and individualized management of AVF maturation failure.
