Lymph Node Metastasis in Early Esophageal Squamous Cell Carcinoma

NCT07050576 | Recruiting

• 1 other identifier: Early-ESCC-LNM-2024
• Study Type: observational
• Target: 500
• Locations: 1 country
• Sites: 1

Brief Summary

This study aims to develop a predictive model using deep learning and radiomics to assess the likelihood of lymph node metastasis in patients with early-stage esophageal squamous cell carcinoma (ESCC). Lymph node metastasis is a critical factor in determining the treatment approach and prognosis for ESCC patients. By analyzing medical imaging data, we hope to create a non-invasive method that can assist doctors in making more accurate treatment decisions. This research could improve patient outcomes by enabling earlier and more tailored interventions.

Conditions

ESCC; Lymph Node Metastasis; Radiomics

Keywords

ESCC; Lymph node metastasis; radiomics

Outcome Measures

Primary Outcomes (1)

• AUC(the area under the curve) values of the model

  The performance and clinical relevance of the models were assessed by analyzing the area under the curve (AUC).

  4 years

Study Arms (2)

A

A total of 400 patients with early-stage ESCC from our center were divided into training and test sets.

Diagnostic Test: The prediction model of lymph node metastasis in early esophageal squamous cell carcinoma

B

A total of 100 patients with early-stage ESCC from other center were defined as external validation

Diagnostic Test: The prediction model of lymph node metastasis in early esophageal squamous cell carcinoma

Interventions

The prediction model of lymph node metastasis in early esophageal squamous cell carcinoma DIAGNOSTIC_TEST

The predictive performance of the model was validated in the test set. The optimal prediction model was determined based on the AUC and ACC. To assess the robustness of the chosen model, ROC analysis was conducted on the external validation set.

A; B

Eligibility Criteria

• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

The radiomics features that affects the prediction of LNM in early-stage ESCC. All patients with early-stage ESCC from the hospitals

You may qualify if:

• Patients with pathologically confirmed early-stage (T1) ESCC
• Preoperative contrast-enhanced CT data within 2 weeks before surgery
• Without any treatment before surgical resection

You may not qualify if:

• Patients who underwent neoadjuvant therapy or endoscopic treatment
• Insufficient CT imaging or poor CT quality
• Incomplete pathology results
• Presence of metastatic disease

Sponsors & Collaborators

• The First Affiliated Hospital of Anhui Medical University: lead

Study Sites (1)

The First Affiliated Hospital of Anhui Medical University

Hefei, Anhui, 230022, China

RECRUITING

MeSH Terms

Conditions

Lymphatic Metastasis

Condition Hierarchy (Ancestors)

Neoplasm Metastasis; Neoplastic Processes; Neoplasms; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Central Study Contacts

Hao Zheng, MD

CONTACT

+86 139 1793 6873; pojunayfy@gmail.com

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: June 26, 2025
• First Posted: July 3, 2025
• Study Start: May 1, 2024
• Primary Completion: October 1, 2025
• Study Completion: November 30, 2025
• Last Updated: July 3, 2025

Record last verified: 2024-09

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)