JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Transcriptome analysis and artificial intelligence for predicting lymph node metastasis of esophageal squamous cell carcinoma

  • 0Department of Thoracic Surgery, Gaozhou People's Hospital Affiliated to Guangdong Medical University, Maoming, China.
Journal of Thoracic Disease +

|

June 18, 2025

|

June 18, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

This study combined transcriptome analysis and artificial intelligence (AI) to accurately predict lymph node metastasis (LNM) in esophageal squamous cell carcinoma (ESCC). The developed AI model improves prediction accuracy, aiding clinical staging and surgical decisions for ESCC patients.

Area Of Science

  • Oncology
  • Genomics
  • Bioinformatics

Background

  • Lymph node metastasis (LNM) is critical for esophageal squamous cell carcinoma (ESCC) treatment decisions.
  • Current LNM diagnostic methods for ESCC lack sufficient accuracy.
  • Accurate LNM staging is essential for effective clinical management of ESCC.

Purpose Of The Study

  • To investigate the utility of combining transcriptome analysis with artificial intelligence (AI) for predicting LNM in ESCC.
  • To develop and validate an effective predictive model for LNM in ESCC patients.

Main Methods

  • RNA sequencing (RNA-seq) identified differentially expressed genes in ESCC with LNM.
  • Random forest algorithms selected candidate genes and built an AI predictive model.
  • Logistic regression, Kaplan-Meier analysis, and ROC curves (AUC) were used for validation.

Main Results

  • RNA-seq identified 2,837 differentially expressed genes; <i>SIM2, CUX1</i>, and <i>CYP4B1</i> were key diagnostic genes.
  • Patients with LNM exhibited worse overall survival (OS); gene expression correlated with OS.
  • The logistic regression model achieved an AUC of 0.83, and the AI model achieved an AUC of 0.78.

Conclusions

  • AI and transcriptome analysis offer a robust approach for predicting LNM in ESCC.
  • The developed risk model enhances prediction accuracy for LNM.
  • This predictive model can inform clinical staging and pre-operative decision-making for ESCC.

Keywords: