Enhancing Sepsis prognosis: Integrating social determinants and demographic variables into a comprehensive model for critically ill patients
Authors' conclusion
Adding patient-specific demographic and socioeconomic information to clinical metrics significantly improves sepsis mortality prediction.
Study context
- Population
- Critically ill patients with sepsis (MIMIC-IV database; external validation in Penn State Health cohort)MIMIC-IV dataset
- Participants
- 32,970 patients
- Comparison
- Combined model vs Sequential Organ Failure Assessment (SOFA) scores alone
- Outcome
- Sepsis mortality prediction (30-day mortality)
- Follow-up
- 30 days
Methodological detailsretrospective derivation, prospective external validation, Random Forest model
- Retrospective derivation
- Prospective external validation
- Random Forest model
Performance
As reported in the abstract
Predictive accuracy for sepsis mortality
30-day mortality (MIMIC-IV)
6,824
20.7%
Further findings
Significant predictors
- Day 2 SOFA, age, weight and comorbidities were significant predictors
External validation (Penn State Health cohort)
- Consistent performance; importance of delta SOFA between days 1 and 3
Original publication
Enhancing Sepsis prognosis: Integrating social determinants and demographic variables into a comprehensive model for critically ill patients. J Crit Care. Published 11 July 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →