Skip to content

Construction and clinical evaluation of early screening model for gastrointestinal tumors based on machine learning and data mining

Construction and clinical evaluation of early screening model for gastrointestinal tumors based on machine learning and data mining

Status
Recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600127865
Enrollment
Unknown
Registered
2026-07-08
Start date
2025-02-12
Completion date
Unknown
Last updated
2026-07-13

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Esophageal cancer, gastric cancer, colon cancer

Interventions

Index test:Based on the screened DNA methylation, CNV, and fragment features, machine learning methods such as logistic regression are used to construct early screening models (including tumor predict

Sponsors

Beijing Chest Hospital, Capital Medical University
Lead Sponsor

Eligibility

Sex/Gender
All
Age
30 Years to 80 Years

Inclusion criteria

Inclusion criteria: 1. Age between 30 and 80 years old; 2. Participants must be able to undergo endoscopy and other related tests; 3. Healthy control participants need to have negative endoscopy and/or pathology results, no other cancers, and must not have had previous endoscopy results showing gastrointestinal tumors (esophageal, gastric, or colorectal cancer) or precancerous lesions; 4. Participants with gastrointestinal tumors (esophageal, gastric, or colorectal cancer) or precancerous lesions must be diagnosed via endoscopy and/or pathology, should not have other systemic or organ malignancies, and must not have had surgery, radiotherapy, or chemotherapy before blood collection; 5. Other cancers (including but not limited to lung, breast, and liver cancer) must be primary, single-type cancers, and participants must not have had surgery, radiotherapy, or chemotherapy before blood collection; 6. Benign diseases include irritable bowel syndrome, mild to moderate atrophic gastritis, reflux esophagitis, etc.; 7. Participants must fully understand the nature of this study, the related tests, and any risks of participation, and be able to comprehend and voluntarily sign the informed consent form.

Exclusion criteria

Exclusion criteria: 1. The blood sample volume is too small, less than 8 mL, making DNA methylation testing and WGS sequencing impossible; 2. Incomplete information about the blood sample (including sample collection time, sample number, participant's age, gender, medical history, imaging results, endoscopy, and pathology results, etc.); 3. Blood sample quality control fails, including samples that don’t meet collection and processing requirements, repeatedly frozen and thawed, hemolyzed, contaminated by microbes, tested with problematic reagents (expired, contaminated, improperly stored, etc.), or other human errors during testing; 4. Pregnant women, breastfeeding women, or women planning to conceive; 5. Any situation the study doctor considers unsuitable for inclusion.

Design outcomes

Primary

MeasureTime frame
DNA methylation region;cfDNA fragment features;Copy Number Variation;

Countries

China

Contacts

Public ContactYuqi He

Beijing Chest Hospital, Capital Medical University

endohe@163.com+86 18911378010

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Jul 23, 2026