Integrating Multimodal AI to Predict Treatment Response and Refine Risk Stratification in Esophageal Cancer (ECO)

Shu Peng

Status: Enrolling

Conditions: Esophageal Cancer

Study type: Observational

Funder types: Other

Identifiers

NCT07354295

4059393

Details and patient eligibility

About

This AI-driven model leverages multimodal data-such as radiomics, pathomics, genomics, and broader multi-omics profiles-to capture complementary aspects of tumor biology and predict treatment response and prognosis.

Full description

Built upon retrospective cohorts for model development and rigorously validated in prospective cohorts, the proposed AI predictive model integrates multimodal data (radiomics, pathomics, genomics, and multi-omics)-each reflecting distinct dimensions of tumor heterogeneity-to enable joint prediction of treatment response and clinical outcomes.

Enrollment: 1,500 estimated patients

Sex: All

Volunteers: No Healthy Volunteers

Inclusion criteria

1. Histopathologically diagnosed esophageal cancer
2. Complete baseline clinical data available (including demographic characteristics, ECOG performance score, TNM staging, etc.)
3. No other primary malignant tumors
4. Provision of informed consent
5. Availability of pre-treatment CT imaging

Exclusion criteria

1. Imaging data quality insufficient for analysis
2. Presence of another primary malignant tumor
3. Severe systemic disease

Trial design

1,500 participants in 4 patient groups

Surgical resection cohort

Description:

neither neoajuvant therapy nor anti-tumor treatment prior to surgery

neoadjuvant therapy cohort

Description:

received neoadjuvant therapy and esophagectomy

conservative treatment

Description:

concervative treatment includes chemo/immuno/radiotherapy and targeted theray

Endoscopic submucosal dissection (ESD)

Description:

Endoscopic submucosal dissection (ESD)