Development and validation of a machine learning model for predicting 6-month mortality in patients with infective endocarditis

Key Points

• The aim is to develop and validate a machine learning model for predicting 6-month mortality in patients with infective endocarditis.
• Developed a machine learning model named EST for accuracy assessment.
• Compared EST's performance to conventional and other machine learning models.
• Emphasized the need for external and multicenter validation to confirm results.
• The EST model demonstrated high predictive accuracy for 6-month mortality.
• Outperformed conventional methods and other machine learning models.
• The model shows potential for future risk stratification despite being exploratory.