Clinical Report: Creation and assessment of a clinical risk prediction model for cardiomyopathy resulting from sepsis
Overview
This study developed and validated a risk-prediction model for sepsis-induced cardiomyopathy (SICM) using clinical data from patients with sepsis. The model demonstrated predictive performance with C-statistic values of 0.80 in the derivation cohort and 0.76 in the external validation cohort.
Background
Sepsis-induced cardiomyopathy (SICM) is a significant complication of sepsis, leading to increased mortality and multi-organ failure. Accurate risk prediction is crucial for early detection and intervention. This study addresses these gaps by creating a clinically applicable prediction model based on routinely available clinical variables.
Data Highlights
Predictor
Value
C-statistic (derivation cohort)
0.80
C-statistic (internal validation cohort)
0.79
C-statistic (external validation cohort)
0.76
Key Findings
The prediction model was derived from a cohort of 956 patients with sepsis.
Five independent predictors were identified: serum phosphate concentration, neutrophil percentage, troponin concentration, heart rate, and Charlson Comorbidity Index.
External validation was conducted with an independent cohort of 104 patients.
Clinical Implications
The validated prediction model can assist clinicians in identifying patients at high risk for SICM, enabling timely interventions. Utilizing routinely available clinical variables enhances its applicability in critical care settings.
Conclusion
The development of this risk-prediction model represents a significant advancement in the assessment of SICM risk.
