Predicting Response to Systemic Therapies for Hepatocellular Carcinoma(HCC)

Effect of Drug, Hepatocellular Carcinoma Non-resectable

Hepatocellular Carcinoma, systemic therapy, immunotherapy, tyrosine kinase inhibitor, treatment response, radiomics, clinical characteristics, machine learning

As the most common type of primary liver cancer, hepatocellular carcinoma (HCC) has become a big challenge all over the world. Most patients are not available to curative resection when first diagnosed. There are a variety of treatment options for advanced HCC. However, due to the heterogeneity of HCC, the overall response rate (ORR) is not high for systemic therapies. Therefore, appropriate selection of patients who are suitable for individual systemic therapies is important for clinical decision-making.

Although major achievements have been acquired in diagnosis and treatment, the prognosis of hepatocellular carcinoma (HCC) is still unsatisfactory. Liver resection remains the main curative treatment for HCC, but most patients are at an advanced stage when first diagnosed, leading to be not available to curative therapies. There is a variety of treatment options for advanced HCC, such as transarterial chemoembolization (TACE), hepatic artery infusion chemotherapy (HAIC), targeted therapy (sorafenib and lenvatinib), immunotherapy, and the combination of different therapies. However, due to the heterogeneity of HCC, different patients respond differently to systemic therapies. The the overall response rate (ORR) is not satisfactory and most patients can not benefit from the systemic therapies. There is an urgent need to identify patients who are likely to have positive response to systemic therapies at the beginning before treatment. Therefore ,we want to collect the clinical information of patients with advanced HCC treated with systemic therapies, including demographic data , laboratory index, histological features, radiomics data. Patients are followed-up at a interval of 1 month after treatment, and the ORR, overall survival (OS), progression-free survival (PFS) are recorded. Then the treatment response are evaluated and the relationship between the clinical data and efficacy of systemic therapies are explored by machine learning methods. Then models based on clinical features or radiomics features are developed to predict response to different systemic therapies.

No related papers found yet.

China