Using AI on scans, pathology, and genetics to predict treatment response and risk in esophageal cancer
Multimodal AI-based Therapy Response Prediction and Risk Stratification for Esophageal Cancer
This project uses AI that combines CT scans, pathology images, and genetic data to try to predict how people with esophageal cancer will respond to treatment and what their prognosis may be.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 1500 (estimated) |
| Sex | All |
| Sponsor | Tongji Hospital Academic / other |
| Locations | 1 site (Wuhan, Other (Non U.s.)) |
| Trial ID | NCT07354295 on ClinicalTrials.gov |
What this trial studies
Researchers are developing an AI model that integrates radiomics (CT imaging features), pathomics (digital pathology), genomics, and other multi-omics data to capture different aspects of tumor biology. The model is trained on retrospective patient cohorts and then validated in prospective cohorts to test its real-world performance. No new treatments are given; the work is observational and focuses on predicting treatment response and clinical outcomes. Data quality requirements include pre-treatment CT scans and complete baseline clinical information.
Who should consider this trial
Good fit: Adults with histopathologically confirmed esophageal cancer who can provide informed consent, have complete baseline clinical data, no other primary malignancy, and have available pre-treatment CT imaging are ideal candidates.
Not a fit: Patients with poor-quality or missing imaging, another active primary cancer, severe systemic illness, or insufficient clinical/omic data are unlikely to benefit from the model.
Why it matters
Potential benefit: If successful, the AI tool could help tailor treatments and identify higher-risk patients earlier so clinicians can make more personalized care decisions.
How similar studies have performed: Previous radiomics and genomics studies in various cancers, including some retrospective work in esophageal cancer, have shown promising signals, but prospective validation of an integrated multimodal AI approach is still limited.
Eligibility criteria
Show full inclusion / exclusion criteria
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
Where this trial is running
Wuhan, Other (Non U.s.)
- Tongji hospital, Tongji medical college, Huazhong university of science and technology — Wuhan, Other (Non U.s.), China (Recruiting)
Study contacts
- Study coordinator: Shu Peng, Doctor
- Email: drpeng90@hotmail.com
- Phone: +8618571716422
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.