Purpose: Integrating comprehensive information on hepatocellular carcinoma (HCC) is essential to improve its early detection. The investigators aimed to develop a model with multi-modal features (MMF) using artificial intelligence (AI) approaches to enhance the performance of HCC detection.

Experimental Design: A total of 1,092 participants were enrolled from 16 centers. These participants were allocated into the training, internal validation, and external validation cohorts. Peripheral blood specimens were collected prospectively and subjected to mass cytometry analysis. Clinical and radiological data were obtained from electrical medical records. Various AI methods were employed to identify pertinent features and construct single-modal models with optimal performance. The XGBoost algorithm was utilized to amalgamate these models, integrating multi-modal information and facilitating the development of a fusion model. Model evaluation and interpretability were demonstrated using the SHapley Additive exPlanations method.

Inclusion Criteria:

• Benign liver diseases, including but not limited to, hemangiomas, hepatic cysts, focal nodular hyperplasia, and cirrhosis

Exclusion Criteria:

• Participants who had undergone previous treatment for HCC or benign liver diseases,
• had taken medications affecting the hematological system within 2 weeks
• those who had received a blood transfusion within 6 months

Benign liver diseases, including but not limited to, hemangiomas, hepatic cysts, focal nodular hyperplasia, and cirrhosis were considered in this study. Participants who had undergone previous treatment for HCC or benign liver diseases, those who had taken medications affecting the hematological system within 2 weeks, or those who had received a blood transfusion within 6 months were excluded from the study.