Sex-Specific Machine Learning Models to Predict Distant Metastasis in Liver Cancer

NCT07386639 | Completed

• 2 other identifiers: SEER-HCC-DM-Gender-202482504454
• Study Type: observational
• Target: 19,019
• Locations: 0 countries
• Sites: N/A

Brief Summary

This study looked at whether male and female patients with liver cancer (hepatocellular carcinoma, HCC) have different risks of the cancer spreading to distant parts of the body (distant metastasis). Liver cancer is much more common in men than in women, and women often have better survival rates. However, it was unclear if the factors that predict this spread are the same for both sexes. To answer this question, researchers analyzed information from a large, national cancer database (SEER) from 2004 to 2022, including 19,019 patients diagnosed with liver cancer. They studied factors like age, race, tumor stage, treatment received, and where patients lived. The team used advanced computer models (machine learning) to build separate prediction tools for men and women to estimate their risk of distant metastasis at the time of diagnosis.

Conditions

Hepatocellular Carcinoma; Liver Cancer; Neoplasm Metastasis

Keywords

Machine Learning; Prediction Model; Sex Factors; SEER Program; Retrospective Cohort Study

Outcome Measures

Primary Outcomes (1)

• Presence of Distant Metastasis at Diagnosis

  The area under the receiver operating characteristic curve (AUC) of the best-performing machine learning model for predicting distant metastasis in the male cohort, evaluated on the internal testing set.

  At completion of data analysis (2024).

Secondary Outcomes (1)

• Presence of distant metastasis at initial diagnosis

  At diagnosis (Data from SEER registries covering years 2004-2022).

Study Arms (1)

MALE and Female HCC Patients

A cohort of male patients (n=14,575) diagnosed with hepatocellular carcinoma (HCC) between 2004 and 2022, identified from the SEER database. This group was analyzed separately to identify sex-specific determinants and build a prediction model for distant metastasis.；A cohort of female patients (n=4,444) diagnosed with hepatocellular carcinoma (HCC) between 2004 and 2022, identified from the SEER database. This group was analyzed separately to identify sex-specific determinants and build a prediction model for distant metastasis.

Eligibility Criteria

• Age: 18 Years - 100 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

This study is a retrospective analysis of a pre-existing, de-identified population-based cancer registry (SEER). The study population consists of all adult patients meeting the above eligibility criteria who were diagnosed with hepatocellular carcinoma (HCC) within the specified period. Participants were not prospectively recruited for this study.

You may qualify if:

• Pathologically confirmed diagnosis of Hepatocellular Carcinoma (HCC).
• Diagnosis year between 2004 and 2022, inclusive.
• Case identified within the 22 registries of the Surveillance, Epidemiology, and End Results (SEER) database.

You may not qualify if:

• Missing information on race, marital status, tumor grade, or surgical status.
• Non-first primary malignancy or presence of multiple primary tumors.
• Incomplete TNM staging data.

Sponsors & Collaborators

• Tongji University: lead

MeSH Terms

Conditions

Carcinoma, Hepatocellular; Liver Neoplasms; Neoplasm Metastasis

Condition Hierarchy (Ancestors)

Adenocarcinoma; Carcinoma; Neoplasms, Glandular and Epithelial; Neoplasms by Histologic Type; Neoplasms; Digestive System Neoplasms; Neoplasms by Site; Digestive System Diseases; Liver Diseases; Neoplastic Processes; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Clinical Professor

Study Record Dates

• First Submitted: January 23, 2026
• First Posted: February 4, 2026
• Study Start: January 1, 2004
• Primary Completion: January 1, 2023
• Study Completion: December 1, 2025
• Last Updated: February 4, 2026

Record last verified: 2026-01

Data Sharing

• IPD Sharing: Will not share