Artificial Intelligence Based Evaluation of Prognostic Benefits from Immunotherapy Plus Targeted Therapy With or Without Radiotherapy or TACE in Advanced Hepatocellular Carcinoma

Yuehong Deng^1*Shiqin Song¹Huarong Zhao¹Yuqian Yang^2*Simin Lu^3*Dieting Li^4*

• ¹Hejiang County People's Hospital, Luzhou, Sichuan, China
• ²Chongqing Hygeia Hospital, Chongqing, China
• ³Luzhou People's Hospital, Luzhou, China
• ⁴No 363 Hospital, Chengdu, China

Background Hepatocellular carcinoma (HCC) remains a leading cause of cancer-related mortality worldwide, and the prognosis of advanced disease is still poor. Immunotherapy plus targeted therapy has reshaped systemic treatment, yet overall efficacy is limited. Increasing evidence suggests that combining systemic therapy with locoregional modalities such as TACE or radiotherapy (RT) may improve survival. Artificial intelligence (AI) offers the potential to refine prognostic prediction and optimize patient selection. Methods We retrospectively analyzed 351 patients with unresectable HCC, divided into three groups: immunotherapy plus targeted therapy (P+T, n=89), P+T combined with TACE (n=154), and P+T combined with RT (n=108). Univariable Cox regression identified prognostic factors, which were incorporated into five AI models. Model performance was evaluated by C-index, Brier score, time-dependent receiver operating characteristic (ROC), decision curve analysis (DCA), and calibration. Results Median overall survival (mOS) was 12.8 months in the P+T group, 19.7 months in the TACE group (P=0.011), and 22.3 months in the RT group (P=0.030). Among the five AI models, RSF showed the best performance (C-index=0.731) with favorable calibration. In time-dependent ROC analysis, the random survival forest (RSF) model achieved area under the curve (AUC) values of 0.844, 0.824, and 0.806 for predicting 6-, 12-, and 24-month survival, respectively. DCA indicated higher net clinical benefit with the RSF model, and calibration plots showed good agreement between predicted and observed survival. Conclusion Immunotherapy plus targeted therapy combined with TACE or RT significantly improved survival in advanced HCC compared with systemic therapy alone. RSF provided superior predictive performance and identified critical prognostic variables, supporting AI-assisted approaches as valuable tools for individualized risk stratification and treatment optimization in advanced HCC.