A Generative Model-based System for Predicting Survival and Guiding Treatment Decisions in Patients With Unresectable Hepatocellularcarcinoma Undergoing Transcatheter Arterial Chemoembolization in Combination With Immunotherapy and Targeted Therapy

NCT ID: NCT07065786

Last Updated: 2025-07-15

Basic Information

• Recruitment Status: ACTIVE_NOT_RECRUITING
• Total Enrollment: 550 participants
• Study Classification: OBSERVATIONAL
• Study Start Date: 2024-01-01
• Study Completion Date: 2026-02-01

Brief Summary

The entry point of this study is the proposition of "generative longitudinal prediction," which utilizes only pre-treatment imaging to create high-fidelity predictions of post-treatment imaging. This approach effectively overcomes the clinical challenge of acquiring genuine longitudinal follow-up data. This paradigm shift not only tackles the scarcity of longitudinal data but also introduces an innovative method for treatment simulation using digital twins. Clinicians can intuitively assess the potential efficacy of various treatment plans before intervention through virtually generated multi-timepoint imaging, providing a visual foundation for personalized treatment decisions. This research merges generative AI with dynamic risk models to achieve: 1) a transition from static assessment to dynamic simulation; 2) earlier survival predictions; and 3) personalized optimization of treatment plans. By eliminating dependence on longitudinal data, we aim to deliver more precise and individualized treatment decision support for advanced liver cancer patients, ultimately enhancing survival outcomes and quality of life.

Detailed Description

The entry point of this study is the proposition of "generative longitudinal prediction," which utilizes only pre-treatment imaging to create high-fidelity predictions of post-treatment imaging. This approach effectively overcomes the clinical challenge of acquiring genuine longitudinal follow-up data. This paradigm shift not only tackles the scarcity of longitudinal data but also introduces an innovative method for treatment simulation using digital twins. Clinicians can intuitively assess the potential efficacy of various treatment plans before intervention through virtually generated multi-timepoint imaging, providing a visual foundation for personalized treatment decisions. This research merges generative AI with dynamic risk models to achieve: 1) a transition from static assessment to dynamic simulation; 2) earlier survival predictions; and 3) personalized optimization of treatment plans. By eliminating dependence on longitudinal data, we aim to deliver more precise and individualized treatment decision support for advanced liver cancer patients, ultimately enhancing survival outcomes and quality of life. The model was developed in a retrospective cohort, with validation and testing conducted in multiple retrospective and prospective cohorts, respectively.

Conditions

Transcatheter Arterial Chemoembolization; Unresectable Hepatocellular Carcinoma

Study Design

• Observational Model Type: COHORT
• Study Time Perspective: OTHER

Study Groups

development cohort, validation cohort, test cohort

Generative model

Intervention Type: OTHER

Prospectively enroll pretreatment imaging data from patients with unresectable hepatocellular carcinoma undergoing TACE in combination with immunotherapy plus targeted therapy. Utilize a generative model to create virtual images that represent optimal treatment responses, and compare these virtual images with actual treatment response images collected during follow-up to evaluate the reliability of the generative model.

Interventions

Generative model

Prospectively enroll pretreatment imaging data from patients with unresectable hepatocellular carcinoma undergoing TACE in combination with immunotherapy plus targeted therapy. Utilize a generative model to create virtual images that represent optimal treatment responses, and compare these virtual images with actual treatment response images collected during follow-up to evaluate the reliability of the generative model.

Intervention Type: OTHER

Eligibility Criteria

Inclusion Criteria

• Diagnosed as unresectable hepatocellular carcinoma (HCC) by histopathology and/or clinical diagnosis (typical imaging features, clinical manifestations, laboratory tests, etc.) (Reference: Guidelines for Diagnosis and Treatment of Primary Liver Cancer (2024 Edition));
• Patients with unresectable HCC receiving TACE combined with targeted immunotherapy;
• Liver function classified as Child-Pugh A or B;
• Aged 18 or above, regardless of gender;
• Expected survival time ≥3 months;
• ECOG PS score ≤2;
• Meeting the following laboratory parameters: a) Hematologic function: Absolute neutrophil count ≥1.0×10⁹/L; Platelet count ≥50×10⁹/L; Hemoglobin ≥90 g/L; International normalized ratio (INR) <1.7 or prothrombin time prolongation ≤4 seconds; b) Liver function: ALT/AST ≤5× upper limit of normal (ULN); Total bilirubin ≤210 μmol/L [≤2.38 mg/dL]; Albumin ≥28 g/L; c) Renal function: Serum creatinine ≤1.5× ULN.

Exclusion Criteria

• Concurrent presence of other malignant tumors besides HCC;
• Moderate to severe ascites (ascites scoring 3 points on the Child-Pugh scale); - - Receipt of other first-line, second-line, or third-line systemic therapies (including any regimen of systemic treatment) or any local therapies (including transcatheter interventional therapy, ablation therapy, internal/external radiotherapy, etc.), as well as surgical resection or herbal medicine within 4 weeks prior to TACE combined with targeted immunotherapy;
• Incomplete data, such as missing baseline laboratory test results, unavailable or poor-quality imaging data, or lack of prognostic information;
• Severe liver dysfunction: e.g., decompensated cirrhosis or other liver diseases significantly affecting bilirubin levels;
• Severe comorbidities: e.g., refractory hypertension (blood pressure remaining above 150/100 mm Hg despite optimal medication), persistent arrhythmia (CTCAE grade 2 or higher), atrial fibrillation of any degree, prolonged QTc interval (>450 ms in males or >470 ms in females), renal insufficiency, etc.;
• Co-infection with human immunodeficiency virus (HIV) or acquired immunodeficiency syndrome (AIDS);
• Pregnant or breastfeeding women;
• Acute or chronic psychiatric disorders (including those affecting participant enrollment, treatment intervention, or follow-up).

• Minimum Eligible Age: 18 Years
• Eligible Sex: ALL
• Accepts Healthy Volunteers: No

Sponsors

Zhongda Hospital

OTHER

Sponsor Role: lead

Responsible Party

Gao-jun Teng

Professor of Radiology Zhongda Hospital, Southeast University

Responsibility Role: PRINCIPAL_INVESTIGATOR

Locations

Zhongda hospital

Changzhou, Jiangsu, China

Countries

China

Provided Documents

Document Type: Study Protocol

View Document

Other Identifiers

GenTI-uHCC

Identifier Type: -

Identifier Source: org_study_id