Comprehensive risk factor-based nomogram for predicting one-year mortality in patients with sepsis-associated...

Area of Science:

• Critical Care Medicine
• Neurology
• Data Science in Healthcare

Background:

• Sepsis-associated encephalopathy (SAE) is a severe complication of sepsis, causing diffuse brain dysfunction.
• Predicting long-term mortality in SAE patients is crucial for effective clinical management and treatment strategies.

Purpose of the Study:

• To develop and validate a prognostic nomogram for predicting 1-year mortality in adult patients with SAE.
• To compare the predictive performance of the developed nomogram against established clinical scoring systems.

Main Methods:

• Retrospective cohort study utilizing the MIMIC IV database with 3,882 SAE patients.
• Development of a prognostic nomogram using LASSO and multivariate logistic regression for 1-year mortality prediction.
• Validation of the nomogram's discrimination, calibration, and clinical utility using AUC, calibration plots, and decision curve analysis.

Main Results:

• The nomogram demonstrated strong predictive performance with AUCs of 0.881 (training) and 0.859 (validation).
• Calibration plots confirmed good agreement between predicted and observed 1-year mortality.
• Decision curve analysis indicated superior net benefit compared to Glasgow Coma Scale and SOFA scores.

Conclusions:

• A robust and clinically applicable nomogram for predicting 1-year mortality in SAE patients has been developed.
• The nomogram offers superior predictive accuracy over existing scoring systems.
• This tool has the potential to significantly enhance clinical decision-making and patient management in critical care settings.