Skip to content

Establishment of a comprehensive clinical decision model for gastric stromal tumor based on multimodal machine learning

Establishment of a comprehensive clinical decision model for gastric stromal tumor based on multimodal machine learning

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2500106116
Enrollment
Unknown
Registered
2025-07-17
Start date
2025-08-01
Completion date
Unknown
Last updated
2025-07-21

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

Conditions

Gastric stromal tumor

Interventions

Retrospective Modeling:None
Prospective Validation:None

Sponsors

The First Affiliated Hospital, Zhejiang University School of Medicine
Lead Sponsor

Eligibility

Sex/Gender
All
Age
14 Years to 75 Years

Inclusion criteria

Inclusion criteria: 1. 14-75 years old; 2. Retrospective modeling stage: based on white light gastroscopy, ultrasound gastroscopy, abdominal enhanced CT and pathological grading; 3. Prospective study: based on white light gastroscopy, ultrasound gastroscopy, abdominal enhanced CT to determine the pathological grading; 4. Patients receive regular treatment: patients in both retrospective and prospective stage studies need to receive endoscopic treatment or surgical treatment.

Exclusion criteria

Exclusion criteria: 1. Patients who have not signed the informed consent form and are unwilling to undergo endoscopic or surgical treatment; 2. Patients with severe coagulation disorders; 3. Patients with severe underlying diseases who cannot tolerate anesthesia; 4. Patients with severe underlying diseases who cannot tolerate endoscopic or surgical treatment; 5. Postoperative pathological diagnosis in prospective studies does not consider stromal tumors; 6. The patient's main clinical data are missing.

Design outcomes

Primary

MeasureTime frame
Accuracy of multimodal models for predicting risk grading of gastric stromal tumors;

Secondary

MeasureTime frame
Sensitivity of multimodal models for predicting risk grading of gastric stromal tumors;Specificity of multimodal models for predicting risk grading of gastric stromal tumors;AUC of multimodal models for predicting risk grading of gastric stromal tumors;

Countries

China

Contacts

Public ContactLu Chao

The First Affiliated Hospital, Zhejiang University School of Medicine

zyyyluchao@zju.edu.cn+86 157 0008 1347

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026