Abstract: Objective To construct a nomogram that integraties imaging features and biomarkers to predict pathologic complete response (pCR) in patients with hepatocellular carcinoma (HCC) undergoing conversion therapy.  Methods The study cohort comprised HCC patients who received the transcatheter arterial chemoembolization (TACE) and/or hepatic arterial infusion chemotherapy (HAIC) in conjunction with targeted therapy and immunotherapy at Guangxi Medical University Cancer Hospital from November 2019 to October 2024. Independent predictors of pCR were identified through univariable and multivariable logistic regression analyses, and these predictors were utilized to develop the nomogram. The performance of the nomogram was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA).  Results Among the 135 patients with HCC, 27.4% (37/135) achieved pCR following treatment. The systemic inflammatory response index (SIRI), tumor biomarker response, tumor number, and tumor complete response as assessed by the modified Response Evaluation Criteria in Solid Tumors (mRECIST) were identified as independent predictors of pCR (all P<0.05). A nomogram model was developed with AUC of  0.925 (95%CI: 0.882-0.967), demonstrating significantly superior predictive performance compared to the alpha⁃fetoprotein  (AFP) response (AUC=0.655) or mRECIST complete response (AUC=0.785)  (both  P<0.001). Internal validation using 1,000 times bootstrap resamples resulted in an AUC of 0.918 (95%CI: 0.873-0.963) for the nomogram model. The calibration curve confirmed excellent model calibration， and DCA demonstrated significant clinical utility. Conclusions The nomogram model,  incorporating SIRI, tumor biomarker response, tumor number, and mRECIST complete response,  provides an accurate pCR prediction following HCC conversion therapy in HCC patients and may serve as a foundation for individualized surgical decision⁃making.

Key words: Hepatocellular carcinoma, Conversion therapy, Nomogram, Pathologic complete response, Biomarker, Imaging features