An artificial intelligence-assisted comprehensive model for predicting lymph node metastasis in superficial esophageal squamous cell carcinoma: a diagnostic study - PubMed
6 hours ago
- #esophageal cancer
- #lymph node metastasis
- #AI-assisted diagnosis
- Study aimed to predict lymph node (LN) metastasis in superficial esophageal squamous cell carcinoma (ESCC) using an AI-assisted model.
- Combined model integrates CT-based radiomic features and clinical risk factors for prediction.
- Analyzed 473 patients from two centers, with LN metastasis present in 13.9% of training cohort and 10.0% of external cohort.
- Higher pathological T stage, poorer tumor differentiation, and larger tumor size were significant predictors of LN metastasis.
- Combined model achieved high predictive accuracy with AUCs of 0.95 (training), 0.93 (internal validation), and 0.88 (external validation).
- Model can improve treatment decision-making and enable personalized therapeutic strategies for superficial ESCC patients.