Objective <p>To develop and validate a nomogram prediction model for postoperative recurrence in elderly patients with hepatocellular carcinoma (HCC) based on multimodal ultrasound parameters.</p> Methods <p>Clinical data of 299 elderly HCC patients who underwent laparoscopic hepatectomy in our hospital from January 2021 to June 2024 were retrospectively collected. Patients were randomly divided into a training cohort (<i>n</i> = 209) and a validation cohort (<i>n</i> = 90) at a ratio of 7:3. According to tumor recurrence within 1 year after surgery, patients were classified into recurrence and non-recurrence groups. Preoperative multimodal ultrasound parameters and other clinical characteristics were recorded. Multivariate logistic regression analysis was performed to identify independent risk factors for postoperative recurrence. A nomogram prediction model was constructed based on multimodal ultrasound parameters using R software. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA).</p> Results <p>No significant differences were observed in baseline characteristics between the training and validation cohorts (<i>P</i> &gt; 0.05). In the training cohort, the recurrence group had a lower proportion of intact tumor capsules, lower hepatic artery pulsatility index (HA-PI) and resistive index (HA-RI), higher tumor stiffness and strain ratio (SR), shorter washout time (WT), and a higher prevalence of chronic viral hepatitis compared with the non-recurrence group (all <i>P</i> &lt; 0.05). Multivariate logistic regression revealed that non-intact tumor capsule, lower HA-RI, higher SR, shorter WT, and concomitant chronic viral hepatitis were independent risk factors for postoperative recurrence (<i>P</i> &lt; 0.05). Based on these predictors, a nomogram prediction model was developed. ROC analysis showed areas under the curve (AUC) of 0.906 (95% CI: 0.866–0.947) in the training cohort and 0.926 (95% CI: 0.868–0.983) in the validation cohort, indicating excellent discrimination. Calibration curves demonstrated good agreement between predicted and observed outcomes in both cohorts (<i>P</i> &gt; 0.05). DCA demonstrated substantial clinical net benefit across a wide range of threshold probabilities (0.01–0.92 in the training cohort; 0.01–0.96 in the validation cohort).</p> Conclusion <p>The nomogram prediction model based on multimodal ultrasound parameters demonstrates favorable predictive performance for postoperative recurrence in elderly HCC patients.</p>