Deep Learning Model Predicts Pathological Complete Response of Esophageal Squamous Cell Carcinoma Following Neoadjuvant Immunochemotherapy

Tongji Hospital300 enrolled

Overview

This study aims to develop and validate a deep learning model to predict pathological complete response (pCR) in patients with esophageal squamous cell carcinoma who have undergone neoadjuvant immunochemotherapy. Clinical, imaging, and pathological data from previously treated patients will be collected and analyzed. The model is expected to assist in predicting treatment outcomes and guide personalized therapeutic strategies.

This multicenter retrospective study will collect chest CT images and clinical data from patients with esophageal squamous cell carcinoma (ESCC) who underwent surgery following neoadjuvant immunochemotherapy between January 2019 and July 2025. Deep learning features will be extracted from the CT images to develop a predictive model of pathological complete response (pCR). The model's performance will be evaluated using metrics including the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Additionally, SHapley Additive exPlanations (SHAP) analysis will be employed to quantify the contribution of CT imaging features to the model's predictions. This study aims to improve early identification of responders to neoadjuvant immunochemotherapy and support personalized treatment strategies for ESCC patients.

Study Type

OBSERVATIONAL

Enrollment

300

Conditions

Esophageal Squamous Cell Carcinoma Neoadjuvant Immunochemotherapy Pathological Complete Response

Eligibility

Sex: ALLMin age: 18 Years

Medical Language ↔ Plain English

Inclusion Criteria: 1. Pathologically confirmed esophageal squamous cell carcinoma (ESCC). 2. Received at least one cycle of neoadjuvant chemotherapy combined with immunotherapy. 3. Underwent contrast-enhanced chest CT before initiation of neoadjuvant treatment. 4. Underwent contrast-enhanced chest CT after completion of neoadjuvant treatment and prior to surgery. Exclusion Criteria: 1. Diagnosis of other malignancies. 2. Received other anti-tumor therapies before or during neoadjuvant chemo-immunotherapy. 3. Incomplete clinical data. 4. Poor-quality CT imaging.

Outcomes

Primary Outcomes

Pathological Complete Response (pCR) Rate

The proportion of patients achieving complete pathological remission after neoadjuvant immunochemotherapy followed by surgery.

Time frame: Assessed at the time of surgery, within 1 month post-treatment.

Secondary Outcomes

Model Performance Metrics (AUC, Accuracy, Sensitivity, Specificity, PPV, NPV)

Evaluation of the deep learning model's predictive performance using receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

Time frame: At the time of model validation, approximately one year on average after the completion of the research.