Development and validation of a sepsis risk index supporting early identification of ICU-acquired sepsis: an observational study
Authors' conclusion
The SRI provides critical care HCPs with an intuitive quantitative measure related to the risk of a patient having or acquiring a life-threatening infection.
Study context
- Population
- ICU patients in openly accessible critical care databases
- Outcome
- Diagnosis of sepsis and septic shock
Methodological detailsmachine learning model development and external validation, development on single-institution database, validation on multi-ICU database
- Machine learning model development and external validation
- Development on single-institution database
- Validation on multi-ICU database
Performance
As reported in the abstract
Diagnosis of sepsis and septic shock (validation database)
| Test or model | AUC, sepsis | AUC, septic shock | Sensitivity, sepsis | Specificity, sepsis | Sensitivity, septic shock | Specificity, septic shock |
|---|---|---|---|---|---|---|
| Developed model | 0.82 | 0.84 | 79.1% [75.1, 82.7] | 73.3% [72.8, 73.8] | 83.8% [80.8, 86.5] | 73.3% [72.8, 73.8] |
Developed model
AUC, sepsis0.82
AUC, septic shock0.84
Sensitivity, sepsis79.1% [75.1, 82.7]
Specificity, sepsis73.3% [72.8, 73.8]
Sensitivity, septic shock83.8% [80.8, 86.5]
Specificity, septic shock73.3% [72.8, 73.8]
Original publication
Development and validation of a sepsis risk index supporting early identification of ICU-acquired sepsis: an observational study. Anaesth Crit Care Pain Med. Published 2 October 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →