AI-Guided First-Line Immunotherapy Selection in Unresectable Hepatocellular Carcinoma

NCT07729618 | Not Yet Recruiting DMC

• 1 other identifier: HCC-AI-SELECT-01
• Study Type: interventional
• Target: 1,800
• Locations: 1 country
• Sites: 1

Brief Summary

This pragmatic, multicenter, cluster-randomized trial will evaluate whether a locked artificial intelligence (AI) clinical decision-support system can improve outcomes by helping multidisciplinary teams select first-line immune checkpoint inhibitor (ICI)-based systemic treatment for adults with unresectable hepatocellular carcinoma (HCC). Twenty-six hospitals or independent HCC multidisciplinary teams will be randomly assigned in a 1:1 ratio to AI-assisted treatment selection or usual-care treatment selection. Approximately 1,800 participants will be enrolled. Eligible participants must already be considered suitable for first-line ICI-based systemic therapy; the study does not compare immunotherapy with no immunotherapy. At AI-assisted sites, the system will use prespecified pretreatment information to estimate and compare expected outcomes across clinically appropriate, locally available, guideline-concordant ICI-based regimens. The AI output is advisory. Treating clinicians and patients retain responsibility for the final treatment decision, and reasons for not following an AI recommendation will be recorded. At usual-care sites, treatment will be selected through the standard multidisciplinary decision-making process without access to the AI output. Both groups will receive approved standard-of-care treatments. The AI model, input definitions, preprocessing pipeline, decision rules, thresholds, and software version will be locked before enrollment of the first participant and will not be retrained or modified using trial outcome data. Both groups will use the same eligibility criteria, patient-registration time point, imaging schedule, follow-up schedule, and outcome definitions. The primary outcome is progression-free survival assessed by blinded independent central imaging review. Overall survival is a key secondary outcome. Additional outcomes include tumor response, duration of response, safety, quality of life, treatment delivery, and implementation measures. This trial evaluates the clinical utility of a prespecified AI system rather than developing or optimizing another prediction model.

Conditions

Unresectable Hepatocellular Carcinoma

Keywords

Artificial Intelligence; Machine Learning; Clinical Decision Support System; Immune Checkpoint Inhibitors; First-Line Systemic Therapy

Outcome Measures

Primary Outcomes (1)

• Progression-Free Survival Assessed by Blinded Independent Central Review Using RECIST Version 1.1

  Progression-free survival is defined as the time from prospective participant registration to the first radiographically documented disease progression according to RECIST version 1.1, as determined by blinded independent central review, or death from any cause, whichever occurs first. Participants without either event will be censored at the date of their last adequate radiographic tumor assessment. Imaging assessments will follow the same prespecified schedule in both study groups.

  From participant registration until radiographic disease progression or death from any cause, whichever occurs first, assessed up to 27 months

Secondary Outcomes (7)

• Overall Survival

  From participant registration until death from any cause, assessed up to 44 months

• Objective Response Rate Assessed by Blinded Independent Central Review Using RECIST Version 1.1

  From participant registration through the last tumor assessment before disease progression or initiation of new anticancer therapy, assessed up to 27 months

• Duration of Response

  From the first documented response that is subsequently confirmed until radiographic disease progression or death from any cause, assessed up to 27 months

• Disease Control Rate

  From participant registration through the last tumor assessment before disease progression or initiation of new anticancer therapy, assessed up to 27 months

• Time to Treatment Failure

  From participant registration until failure of the initial first-line treatment strategy or death from any cause, assessed up to 27 months

Study Arms (2)

AI-Assisted Treatment Selection

EXPERIMENTAL

At hospitals randomized to the AI-assisted strategy, eligible participants will receive first-line ICI-based systemic therapy selected with support from a locked AI clinical decision-support system. The system will use prespecified pretreatment information to compare and rank clinically appropriate, guideline-concordant treatment options. The AI output is advisory, and the final treatment decision remains with the multidisciplinary team and the participant.

Other: AI-Assisted Clinical Decision Support Strategy

Usual-Care Treatment Selection

ACTIVE COMPARATOR

At hospitals randomized to the usual-care strategy, eligible participants will receive first-line ICI-based systemic therapy selected through the standard multidisciplinary decision-making process without access to the AI output. Treatment selection will be based on contemporary guidelines, clinical characteristics, contraindications, treatment availability, clinician judgment, and participant preferences.

Other: Usual-Care Multidisciplinary Treatment-Selection Strategy

Interventions

AI-Assisted Clinical Decision Support Strategy OTHER

A locked AI clinical decision-support system will analyze prespecified pretreatment information and provide the multidisciplinary team with patient-specific estimates and a comparative ranking of clinically appropriate first-line ICI-based treatment options. The recommendation is advisory and does not replace clinical judgment or shared decision-making.

AI-Assisted Treatment Selection

Usual-Care Multidisciplinary Treatment-Selection Strategy OTHER

First-line ICI-based treatment will be selected through the hospital's usual multidisciplinary decision-making process without access to the AI clinical decision-support system. Participants will otherwise undergo the same eligibility assessment, follow-up schedule, and outcome ascertainment as participants in the AI-assisted arm.

Usual-Care Treatment Selection

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Age 18 years or older.
• Hepatocellular carcinoma confirmed by histology or cytology, or diagnosed using accepted noninvasive radiologic criteria.
• Unresectable hepatocellular carcinoma for which first-line systemic therapy is indicated, including Barcelona Clinic Liver Cancer stage B disease that is unsuitable for or no longer benefiting from locoregional therapy, or stage C disease.
• No prior systemic anticancer therapy for unresectable hepatocellular carcinoma.
• Child-Pugh class A liver function.
• Eastern Cooperative Oncology Group performance status of 0 or 1.
• Eligible and intended to receive at least one protocol-specified, guideline-concordant immune checkpoint inhibitor-based first-line regimen, as determined by the treating clinician before exposure to the study AI recommendation.
• Eligibility confirmed and prospective participant registration completed before the final first-line treatment regimen is selected.
• Baseline contrast-enhanced computed tomography or magnetic resonance imaging suitable for assessment according to Response Evaluation Criteria in Solid Tumors version 1.1 is available before initiation of first-line systemic therapy.
• Required pretreatment clinical data are available within the protocol-specified assessment windows.
• Able to provide written informed consent.

You may not qualify if:

• Known combined hepatocellular-cholangiocarcinoma or another primary liver malignancy other than hepatocellular carcinoma.
• A contraindication or clinical condition that makes all protocol-specified immune checkpoint inhibitor-based first-line regimens inappropriate according to applicable prescribing information and routine clinical practice.
• Initiation of systemic therapy or completion of the final first-line regimen decision before prospective participant registration.
• Exposure of the treating clinical team to the participant-specific AI recommendation before confirmation of eligibility and registration.
• Concurrent anticancer treatment for another malignancy that would materially interfere with treatment selection or study outcome assessment.
• Planned participation in another interventional study that dictates first-line systemic treatment or would interfere with study outcome assessment.
• Inability to undergo protocol-required tumor imaging or follow-up assessments.

Sponsors & Collaborators

• Tongji Hospital: lead

Study Sites (1)

Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology

Wuhan, Hubei, 430030, China

Location

Study Officials

• Zhao Huang

  Tongji Hospital

  STUDY DIRECTOR

Central Study Contacts

Zhao Huang, M.D

CONTACT

+86 13006378908; huangzhao@tjh.tjmu.edu.cn

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Masking Details: The trial is open-label at the participant, care-provider, and site-investigator levels because the use of AI-assisted decision support cannot be concealed. However, de-identified imaging studies for the primary progression-free survival endpoint will be assessed by an independent central review committee blinded to cluster assignment, AI recommendations, treatment-selection rationale, and treating hospital and, where feasible, the treatment regimen received.
• Purpose: TREATMENT
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: professor

Model Details: Twenty-six participating hospitals, each constituting one cluster, will be centrally randomized in a 1:1 ratio to either the AI-assisted treatment-selection strategy or the usual-care treatment-selection strategy. The hospital, rather than the individual participant, is the unit of randomization. All eligible participants prospectively enrolled at a hospital will receive the treatment-selection strategy assigned to that hospital throughout the trial. Hospitals will not cross over between strategies.

Study Record Dates

• First Submitted: July 22, 2026
• First Posted: July 27, 2026
• Study Start: October 1, 2026
• Primary Completion (Estimated): December 1, 2028
• Study Completion (Estimated): December 1, 2029
• Last Updated: July 27, 2026

Record last verified: 2026-07

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, ICF, ANALYTIC CODE
• Time Frame: Data will become available beginning 12 months after publication of the primary study results and will remain available for 5 years.
• Access Criteria: Access may be granted to qualified researchers whose methodologically sound proposal has been approved by the study Data Access Committee. Requests must describe the research objectives, proposed analyses, investigator qualifications, data-security procedures, and applicable ethics approval. Approved researchers must sign a data-use agreement prohibiting participant re-identification, unauthorized redistribution, and use beyond the approved proposal. Data will be accessed through an institutionally approved secure data environment, subject to applicable legal and institutional requirements.

Locations

CN (1)