Skip to content

AI-Based Prediction of Treatment Response and Recurrence in Gastric Cancer

AI-Based Prediction of Treatment Response and Recurrence in Gastric Cancer

Status
Recruiting
Phases
Unknown
Study type
Observational
Source
CRIS
Registry ID
KCT0012373
Enrollment
3200
Registered
2026-07-31
Start date
2025-12-03
Completion date
Unknown
Last updated
2026-08-03

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

Conditions

None listed

Interventions

None listed

Sponsors

Gachon University Gil Medical Center
Lead Sponsor

Eligibility

Sex/Gender
All

Inclusion criteria

Inclusion criteria: Inclusion Criteria • Patients with histologically confirmed gastric cancer. • Patients who received anti-cancer treatment (e.g., surgical intervention, endoscopic resection, or systemic pharmacotherapy) following gastric cancer diagnosis. • Patients with at least one of the following data types available pre- or post-treatment: o Radiological/Endoscopic Imaging: Chest CT, abdominal CT/ultrasound, or endoscopic images. o Pathology: Histopathological slides or tissue biopsy reports. o Laboratory/Genomic Data: Blood tests or Next-Generation Sequencing (NGS) data. • Patients with linkable temporal metadata across imaging, pathology, and genomic datasets (e.g., feasibility of pre- and post-treatment RECIST(Response Evaluation Criteria in Solid Tumors) response evaluation).

Exclusion criteria

Exclusion criteria: Exclusion Criteria • Unusable imaging or pathological slide data due to poor quality (e.g., severe artifacts, low resolution). • Withdrawal of patient consent or existence of re-identification risk. • Unclear history of anti-cancer treatment or uncertain timing of therapeutic response evaluation. • Synchronous double primary cancer or severe systemic comorbidities that significantly confound gastric cancer prognosis. • Follow-up duration of less than 1 month.

Design outcomes

Primary

MeasureTime frame
Predictive accuracy of the multimodal transformer model for chemotherapeutic response: Sensitivity, Specificity, Receiver Operating Characteristic Curve(AUROC), C-index

Secondary

MeasureTime frame
Predictive performance of the multimodal transformer model for post-treatment recurrence risk: Receiver Operating Characteristic Curve(AUROC), C-index

Countries

Korea, Republic of

Contacts

Public ContactSeung Yoon Nam

Gachon University Gil Medical Center

nams@gachon.ac.kr+82-32-458-2737

Outcome results

None listed

Source: CRIS (via WHO ICTRP) · Data processed: Aug 10, 2026