Early risk stratification of sepsis-related liver injury via machine learning: a multicohort study

Key Points

• Sepsis-related liver injury risk can be predicted early using machine learning techniques, improving patient management.
• The random forest model demonstrated superior performance among predictive models assessed, providing reliable results.
• Prothrombin time emerged as a significant marker, emphasizing its potential for early monitoring of at-risk patients.
• Findings support the need for implementing machine learning in clinical settings for timely intervention planning.