Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
This study aims to prospectively validate a retrospective cohort-derived AI-based multimodal model and explore tumor heterogeneity and the immune microenvironment to guide TACE combined with immunotherapy and targeted therapy in HCC.
This study will integrate a retrospective cohort with a prospective observational cohort. Multimodal data will be collected in the prospective cohort to validate the AI-based imaging model developed from the retrospective cohort. In addition, advanced multi-omics technologies will be incorporated to characterize tumor heterogeneity and the immune microenvironment, thereby supporting early and precise guidance for TACE combined with immunotherapy and targeted therapy in HCC.
Not provided
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Retrospective cohort | Patients with hepatocellular carcinoma who received TACE combined with immunotherapy and targeted therapy, as well as other treatment modalities, will be retrospectively included. Multimodal data from this cohort will be used to develop and train the AI-based model. |
| |
| Prospective cohort | Patients with hepatocellular carcinoma who receive TACE combined with immunotherapy and targeted therapy will be prospectively enrolled. Multimodal data, including clinical, imaging, and biospecimen-related data when available, will be collected to validate the AI-based multimodal model. |
|
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| Artificial Intelligence | Other | Investigators utilize a AI-based supportive system to predict clinical outcomes for patients with hepatocellular carcinoma who received TACE combined with immunotherapy and targeted therapy |
| Measure | Description | Time Frame |
|---|---|---|
| Prediction Performance of the AI Model | The area under curve (AUC) of Receiver Operating Characteristic (ROC) curves o f the AI model in predicting the clinical outcomes in patients receiving TACE combined with immunotherapy and targeted therapy. | From enrollment to approximately 2 years |
| Measure | Description | Time Frame |
|---|---|---|
| Objective response rate(ORR) | The ORR is defined as the proportion of patients with a documented complete response(CR) or partial response(PR) per RECIST 1.1 or per mRECIST. | up to approximately 2 years |
| Overall Survival(OS) |
Not provided
Retrospective Study Cohort 1.1 Inclusion Criteria Age ≥18 years; Patients with hepatocellular carcinoma confirmed by histopathology or clinical diagnosis; At least one intrahepatic lesion that is repeatedly measurable according to RECIST v1.1.
1.2 Exclusion Criteria Known sarcomatoid hepatocellular carcinoma or fibrolamellar hepatocellular carcinoma; Presence of other active malignancies within the past 5 years or concurrent active malignancies other than hepatocellular carcinoma; Missing preoperative imaging examinations, including CT or MRI, or poor image quality; Missing key baseline clinical data; Loss to follow-up after treatment.
Prospective Study Cohort 2.1 Inclusion Criteria Age ≥18 years; Patients with hepatocellular carcinoma confirmed by histopathology or clinical diagnosis; Scheduled to receive first-line TACE combined with immunotherapy and targeted therapy; At least one intrahepatic lesion that is repeatedly measurable according to RECIST v1.1; Expected survival of more than 3 months. 2.2 Exclusion Criteria Known sarcomatoid hepatocellular carcinoma or fibrolamellar hepatocellular carcinoma; Presence of other active malignancies within the past 5 years or concurrent active malignancies other than hepatocellular carcinoma; Other factors that, in the investigator's judgment, make the patient unsuitable for participation in this study; Severe allergy to iodinated contrast agents that preclude imaging examinations or TACE treatment.
Not provided
Not provided
Not provided
In the retrospective cohort, patients with HCC who received TACE combined with immunotherapy and targeted therapy, as well as other treatment modalities, will be retrospectively included. Multimodal data from this cohort will be used to develop and train the AI-based model. In the prospective cohort, patients with HCC who receive TACE combined with immunotherapy and targeted therapy will be prospectively enrolled. Multimodal data, including clinical, imaging, and biospecimen-related data when available, will be collected to validate the AI-based multimodal model.
| Name | Role | Phone | Extension | |
|---|---|---|---|---|
| Zhicheng Jin, MD | Contact | +86-025-83272121 | jinzhic@foxmail.com |
Not provided
Not provided
| PubMed Identifier | Type | Citation | Retractions |
|---|---|---|---|
| 39993404 | Background | Zhong BY, Fan W, Guan JJ, Peng Z, Jia Z, Jin H, Jin ZC, Chen JJ, Zhu HD, Teng GJ. Combination locoregional and systemic therapies in hepatocellular carcinoma. Lancet Gastroenterol Hepatol. 2025 Apr;10(4):369-386. doi: 10.1016/S2468-1253(24)00247-4. Epub 2025 Feb 21. | |
| 41213031 | Background | Jin ZC, Wei J, Xiao YD, Si A, Chen JJ, Zhu XL, Li JZ, Nie F, Ding R, Zhou HF, Ding W, Zhong BY, Xie Y, Hu HT, Yin GW, Ji JS, Zhang WH, Shi HB, Wu JB, Xu GH, Yuan CW, Yang WZ, Liu RB, Wu YM, Zheng CS, Xu AB, Huang MS, Li JP, Chen L, Wen SW, Wang YQ, Gu SZ, Li D, Wang D, Zhou GH, Wang WD, Peng Z, Wang X, Zhu HD, Tian J, Teng GJ. Decoding tumor heterogeneity with imaging biomarkers predicts response to TACE plus immunotherapy and targeted therapy in HCC (CHANCE2204). Hepatology. 2025 Nov 10. doi: 10.1097/HEP.0000000000001593. Online ahead of print. |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
The OS is defined as the time from the initiation of any combination treatment to death due to any cause.
| up to approximately 2 years |
| Progression free survival(PFS) | The PFS is defined as the time from the initiation of any combination treatment to the first documented progressive disease (according to RECIST 1.1 or mRECIST) or death due to any cause, whichever occurs first. | up to approximately 2 years |
| Other prediction performance of the model | Evaluation of the accuracy, sensitivity, and specificity of the prediction model in clinical application | From enrollment to approximately 2 years |
| 40246150 | Background | Vithayathil M, Koku D, Campani C, Nault JC, Sutter O, Ganne-Carrie N, Aboagye EO, Sharma R. Machine learning based radiomic models outperform clinical biomarkers in predicting outcomes after immunotherapy for hepatocellular carcinoma. J Hepatol. 2025 Oct;83(4):959-970. doi: 10.1016/j.jhep.2025.04.017. Epub 2025 Apr 17. |
| ID | Term |
|---|---|
| D006528 | Carcinoma, Hepatocellular |
| ID | Term |
|---|---|
| D000230 | Adenocarcinoma |
| D002277 | Carcinoma |
| D009375 | Neoplasms, Glandular and Epithelial |
| D009370 | Neoplasms by Histologic Type |
| D009369 | Neoplasms |
| D008113 | Liver Neoplasms |
| D004067 | Digestive System Neoplasms |
| D009371 | Neoplasms by Site |
| D004066 | Digestive System Diseases |
| D008107 | Liver Diseases |
Not provided
Not provided
| ID | Term |
|---|---|
| D001185 | Artificial Intelligence |
| ID | Term |
|---|---|
| D000465 | Algorithms |
| D055641 | Mathematical Concepts |
Not provided
Not provided