Pediatric anesthesia & critical care
Microvascular phenotypes in pediatric sepsis identified by machine learning: prognostic implications for organ dysfunction and mortality
Primary result · MODS within 72 hResult — go to the resultAdjusted hazard ratio 2.47 95% CI 1.04–8.44Authors' conclusion
Three reproducible microvascular phenotypes in pediatric sepsis-Preserved, Partially Compensated, and Decompensated-were identified using bedside clinical, biomarker, and microcirculation data.
Study context
- Population
- Children with sepsis (median age 2.1 years [IQR 0.5–11.1]; 52% female)
- Participants
- 239 children
- Comparison
- Decompensated vs Preserved
- Preservedn = 52reference
- Partially Compensatedn = 75
- Decompensatedn = 112
- Primary endpoint
- Persistence of multiple organ dysfunction syndrome (MODS)
- Follow-up
- 72 h after admission
Methodological detailsmachine learning, unsupervised clustering, temporal derivation and validation cohorts
- Machine learning
- Unsupervised clustering
- Temporal derivation and validation cohorts
Primary result
MODS within 72 h · 72 h
Adjusted hazard ratio
2.47
95% CI 1.04–8.44
P = 0.042
By group
Decompensated vs Preserved
aHR 2.47 (95% CI 1.04–8.44); P = 0.042
As reported in the abstract
Further findings
Mortality · stepwise gradient
P = 0.023
Internal validation
- Phenotype assignments and outcome associations reproduced, confirming temporal stability
Original publication
Microvascular phenotypes in pediatric sepsis identified by machine learning: prognostic implications for organ dysfunction and mortality. Crit Care. Published 5 February 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →