Prospective Validation of an AI Model for Predicting Liver Metastasis in Colorectal Cancer

NCT07392567 | Recruiting

• 1 other identifier: TJ-IRB202601017
• Study Type: observational
• Target: 160
• Locations: 1 country
• Sites: 1

Brief Summary

This is a prospective, multicenter, observational study designed to validate the predictive accuracy of a pre-developed multimodal deep learning model. The model integrates preoperative contrast-enhanced CT scans, digitized postoperative pathology images, and standard clinical data to estimate the risk of liver metastasis within two years after curative surgery in patients with stage I-III colorectal cancer. The primary objective is to evaluate the model's performance in an independent, prospectively enrolled patient cohort. Participants will receive standard-of-care treatment according to clinical guidelines. The study involves no experimental interventions; it solely involves the collection and analysis of routinely generated clinical data. The goal is to assess the model's potential for clinical translation by providing a reliable tool for stratifying patients' risk of liver metastasis, which could inform personalized surveillance strategies.

Conditions

Colorectal Cancer Liver Metastasis

Keywords

colorectal cancer liver metastasis; deep learning; multimodal; predictive model

Outcome Measures

Primary Outcomes (1)

• Area Under the Receiver Operating Characteristic Curve (AUC)

  The discriminatory performance of the pre-specified multimodal deep learning model for predicting the occurrence of metachronous liver metastasis within 2 years after curative resection. The model integrates preoperative contrast-enhanced CT, digital pathology, and clinical data. Performance is evaluated on the entire prospectively enrolled validation cohort.

  2 years after surgery

Secondary Outcomes (1)

• Liver Metastasis-Free Survival (LMFS) by Risk Group

  From the date of surgery until the date of first documented liver metastasis or last follow-up, assessed up to 3 years.

Study Arms (1)

Prospective Validation Cohort

This single cohort consists of patients with stage I-III colorectal cancer who are prospectively enrolled after undergoing curative resection. No interventions are administered as part of this study. The cohort is used for the external validation of the pre-defined multimodal deep learning model's performance in predicting the risk of metachronous liver metastasis. All patients receive standard of care treatment and follow-up according to clinical guidelines.

Diagnostic Test: Multimodal Deep Learning Prediction Model

Interventions

Multimodal Deep Learning Prediction Model DIAGNOSTIC_TEST

This is a non-therapeutic, prognostic study. The intervention under investigation is the application of a pre-specified multimodal deep learning model that integrates preoperative CT imaging, digital pathology, and clinical data to stratify patients' risk of developing metachronous liver metastasis. This model functions as a prognostic tool and is not used to guide patient management in this study. Its performance is being evaluated prospectively against the actual clinical outcomes.

Prospective Validation Cohort

Eligibility Criteria

• Age: 18 Years - 75 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

This study population consists of adult patients (aged 18-75) with newly diagnosed, stage I-III primary colorectal cancer who are scheduled to undergo curative resection at one of the participating clinical centers. This prospective cohort will be used for the independent validation of a pre-developed multimodal deep learning model designed to predict the risk of metachronous liver metastasis. All participants will provide informed consent prior to enrollment.

You may qualify if:

• Age 18-75 years, any gender.
• Clinical diagnosis of primary colon or rectal adenocarcinoma (Stage I-III). Scheduled to undergo curative radical resection for colorectal cancer.
• Preoperative contrast-enhanced abdominal/pelvic CT scan performed within 1 month before surgery, with acceptable image quality.
• No evidence of distant metastasis (including synchronous liver metastasis) on preoperative examination.
• ECOG Performance Status of 0 or 1.
• Patient or their legal representative voluntarily participates and provides written informed consent.

You may not qualify if:

• Postoperative pathological confirmation of non-primary colorectal adenocarcinoma or presence of distant metastasis.
• Intraoperative determination of non-R0 resection, or performance of palliative surgery/ostomy only.
• History of other malignant tumors.
• Previous history of liver surgery or liver transplantation.
• Death within the perioperative period (within 30 days after surgery).
• Refusal to participate in follow-up, withdrawal of informed consent, or loss to follow-up.

Sponsors & Collaborators

• Tongji Hospital: lead

Study Sites (1)

Tongji Hospital

Wuhan, Hubei, China

RECRUITING

Central Study Contacts

Yang WU, M.D.

CONTACT

13636076910; 255001907@qq.com

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Prof.

Study Record Dates

• First Submitted: January 30, 2026
• First Posted: February 6, 2026
• Study Start: January 30, 2026
• Primary Completion (Estimated): January 30, 2028
• Study Completion (Estimated): January 30, 2029
• Last Updated: February 6, 2026

Record last verified: 2026-01

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)