Prospective Evaluation of a Locked Risk-Stratified Surveillance Strategy for Extrahepatic Metastasis in Hepatocellular Carcinoma

NCT07444905 | Active Not Recruiting

• 1 other identifier: MLEHM-010
• Study Type: observational
• Target: 1,523
• Locations: 1 country
• Sites: 1

Brief Summary

This is a multicenter prospective observational cohort study in adults with hepatocellular carcinoma (HCC) without baseline extrahepatic metastasis who are receiving routine clinical management and follow-up at participating centers. The study evaluates the real-world implementation and clinical utility of a locked machine learning-guided risk stratification strategy for predicting lung and bone metastasis and supporting risk-stratified surveillance. The locked strategy uses prespecified 12-month risk thresholds and linked care pathways and is implemented without retraining or threshold revision. No study-mandated treatment or surveillance assignment is performed; clinical care remains at physician discretion according to local practice. The study assesses model transportability and calibration, implementation outcomes (including completion of prespecified actions, timeliness of action, and treatment activation), clinically actionable detection outcomes, patient-important outcomes, and longer-term survival. Comparative analyses use centre- and calendar-epoch-aligned usual-care episodes as the primary observational comparator.

Conditions

HCC - Hepatocellular Carcinoma; Machine Learning; Evaluation

Outcome Measures

Primary Outcomes (1)

• Completion of a Prespecified Pathway-Concordant Action Within 60 Days

  Proportion of eligible index episodes with completion of at least one prespecified pathway-concordant action within 60 days after the eligible index assessment. A pathway-concordant action was defined as SOP-concordant multidisciplinary team review, escalated lung- or bone-metastasis-directed imaging, or referral.

  Day 0 to day 60 after the eligible index assessment.

Secondary Outcomes (2)

• Overall survival (OS)

  Up to 36 months

• Completion of a Prespecified Action Within 60 Days

  Completion of the prespecified risk-stratified surveillance or management action within 60 days after the first eligible locked risk assessment.

Other Outcomes (1)

• Incident Extrahepatic Metastasis

  Up to 36 months after the eligible index assessment.

Study Arms (1)

Prospective Observational Cohort

Adults with hepatocellular carcinoma without baseline extrahepatic metastasis enrolled in a prospective observational cohort to evaluate a locked machine learning-guided risk stratification strategy for predicting lung and bone metastasis and supporting risk-stratified surveillance in routine practice. No experimental interventions are assigned, and clinical management remains at physician discretion.

Other: Machine Learning-Based Risk Assessment

Interventions

Machine Learning-Based Risk Assessment OTHER

Point-of-care use of a locked machine learning-guided risk assessment tool with fixed thresholds and linked risk-stratified surveillance recommendations; no study-mandated treatment assignment is performed

Prospective Observational Cohort

Eligibility Criteria

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

Study Population

Adult patients with hepatocellular carcinoma (HCC) without evidence of extrahepatic metastasis at baseline who are receiving standard-of-care management and undergoing prospective follow-up in routine clinical practice. Participants are enrolled in a prospective observational cohort to evaluate a machine learning-based risk assessment strategy for predicting extrahepatic metastasis and supporting risk-adapted surveillance.

You may qualify if:

• Age ≥ 18 years.
• Diagnosis of hepatocellular carcinoma (HCC) confirmed by histopathology or accepted radiologic criteria per international guidelines.
• No evidence of extrahepatic metastasis at baseline evaluation.
• Receiving standard-of-care management with planned longitudinal follow-up in routine clinical practice.
• Availability of baseline clinical and imaging data required for risk assessment using the pre-specified machine learning model.

You may not qualify if:

• Confirmed extrahepatic metastasis at enrollment (baseline).
• History of other active malignancy within the past 5 years, except adequately treated non-melanoma skin cancer or in situ carcinoma.
• Incomplete baseline clinical information that precludes model-based risk assessment.
• Expected survival \< 3 months due to severe comorbidities.
• Participation in an interventional clinical trial that may substantially alter follow-up strategy or metastasis assessment.

Sponsors & Collaborators

• Tongji Hospital: lead

Study Sites (1)

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

Wuhan, Hubei, 430030, China

Location

MeSH Terms

Conditions

Carcinoma, Hepatocellular

Condition Hierarchy (Ancestors)

Adenocarcinoma; Carcinoma; Neoplasms, Glandular and Epithelial; Neoplasms by Histologic Type; Neoplasms; Liver Neoplasms; Digestive System Neoplasms; Neoplasms by Site; Digestive System Diseases; Liver Diseases

Study Officials

• Zhao Huang

  Tongji Hospital

  STUDY DIRECTOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Target Duration: 36 Months
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: professor

Study Record Dates

• First Submitted: February 24, 2026
• First Posted: March 3, 2026
• Study Start: February 1, 2022
• Primary Completion (Estimated): December 30, 2026
• Study Completion (Estimated): December 31, 2026
• Last Updated: June 3, 2026

Record last verified: 2026-05

Locations

CN (1)