Peer-reviewed article
Development and validation of a diagnostic model for early differentiation of sepsis and non-infectious SIRS in critically ill children - a data-driven approach using machine-learning algorithms
Florian Lamping, Thomas Jack, Nicole Rübsamen, Michael Sasse, Philipp Beerbaum et al. ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001This study develops a machine-learning diagnostic model to distinguish sepsis from non-infectious SIRS (systemic inflammatory response syndrome) in critically ill children using clinical and laboratory parameters. The model combines eight predictors and achieves better accuracy than existing biomarkers alone. While the research involves children in a pediatric intensive care unit, it is primarily a technical diagnostic study rather than an evaluation of child well-being or a health intervention.
Key points
- The diagnostic model achieved an AUC of 0.78 in validation, superior to single biomarkers (maximum AUC 0.63)
- The model uses four clinical parameters (PICU stay length, central line presence, core temperature, prior episodes) and four laboratory parameters (IL-6, platelets, procalcitonin, CRP)
- When achieving 100% sensitivity for sepsis detection, 28% of non-infectious SIRS cases were correctly identified
- The approach could potentially reduce antibiotic use by 30% in non-infectious SIRS cases
- External validation is needed to confirm generalizability across different populations and treatment settings
Limitations
This is a secondary analysis from a single German tertiary-care PICU with a small sepsis cohort (n=58), which limits generalizability. The study does not evaluate whether using this diagnostic model actually improves child health outcomes or reduces harm from delayed treatment or unnecessary antibiotics in clinical practice.
Abstract
BACKGROUND: Since early antimicrobial therapy is mandatory in septic patients, immediate diagnosis and distinction from non-infectious SIRS is essential but hampered by the similarity of symptoms between both entities. We aimed to develop a diagnostic model for differentiation of sepsis and non-infectious SIRS in critically ill children based on routinely available parameters (baseline characteristics, clinical/laboratory parameters, technical/medical support). METHODS: This is a secondary analysis of a randomized controlled trial conducted at a German tertiary-care pediatric intensive care unit (PICU). Two hundred thirty-eight cases of non-infectious SIRS and 58 cases of sepsis (as defined by IPSCC criteria) were included. We applied a Random Forest approach to identify the best set of predictors out of 44 variables measured at the day of onset of the disease. The developed diagnostic model was validated in a temporal split-sample approach. RESULTS: A model including four clinical (length of PICU stay until onset of non-infectious SIRS/sepsis, central line, core temperature, number of non-infectious SIRS/sepsis episodes prior to diagnosis) and four laboratory parameters (interleukin-6, platelet count, procalcitonin, CRP) was identified in the training dataset. Validation in the test dataset revealed an AUC of 0.78 (95% CI: 0.70-0.87). Our model was superior to previously proposed biomarkers such as CRP, interleukin-6, procalcitonin or a combination of CRP and procalcitonin (maximum AUC = 0.63; 95% CI: 0.52-0.74). When aiming at a complete identification of sepsis cases (100%; 95% CI: 87-100%), 28% (95% CI: 20-38%) of non-infectious SIRS cases were assorted correctly. CONCLUSIONS: Our approach allows early recognition of sepsis with an accuracy superior to previously described biomarkers, and could potentially reduce antibiotic use by 30% in non-infectious SIRS cases. External validation studies are necessary to confirm the generalizability of our approach across populations and treatment practices. TRIAL REGISTRATION: ClinicalTrials.gov number: NCT00209768; registration date: September 21, 2005.