Machine learning-based clinical decision support tool for advanced ESCC in the immunotherapy era: a multi-center study

Key Points

• The research aims to develop a machine learning-based tool for personalized risk assessments in advanced esophageal squamous cell carcinoma (ESCC).
• Utilized the Boruta-RSF model incorporating available clinical variables.
• Developed a web calculator for user-friendly prognostic assessments.
• Conducted the study across multiple centers to ensure diverse data.
• The tool significantly improved personalized prognostic assessments.
• Optimized treatment strategies based on individual risk profiles.