Machine Learning-Based Risk Assessment: 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
Study 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.
Eligibility
Sex
ALL
Min age
18 Years
Max age
—
Healthy volunteers
No
Inclusion Criteria:
* 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.
* Ability to provide written informed consent, or inclusion under ethics committee-approved procedures.
Exclusion Criteria:
* 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.
Primary outcome measure(s)
Completion of a Prespecified Pathway-Concordant Action Within 60 Days — Day 0 to day 60 after the eligible index assessment. 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.
Trial sites (1)
Facility
City
Region
Status
Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology
This page summarises publicly available registry data for informational purposes — not medical advice. Eligibility is determined by each study team; patients should discuss participation with their clinician.
We use cookies to analyse site traffic and improve your experience. With your consent, we may also use cookies for advertising. You can change your choice at any time on our Cookie Policy page. See also our Privacy Policy.