Blog → Can AI Predict Pediatric Sepsis Before It Happens?

Can AI Predict Pediatric Sepsis Before It Happens?

Listen to this article
0:00 –:–

Written by Joshua Belfer

Spoon Feed 
Using EHR data from the first 4 hours of ED care, machine learning models accurately predicted which children would develop sepsis within 48 hours—before organ dysfunction was present.

Predicting sepsis before the crash
Early sepsis recognition remains one of the greatest challenges for pediatric emergency care. In this PECARN-led multicenter study utilizing EHR data from over 2.3 million pediatric ED visits, machine learning models that predict future sepsis were developed and validated.

Using routinely collected ED data (vital signs, ESI, age, markers of medical complexity), two different models (logistic regression model and gradient tree boosting model) performed exceptionally well. The area under the receiver operating characteristic (AUROC) was 0.92 (95%CI 0.92–0.93) for the logistic regression model and 0.94 (95%CI 0.93–0.94) for the gradient tree boosting model. Additionally, the models had similarly high AUROCs when looking at septic shock. At a prespecified sensitivity of 90%, the gradient boosting model achieved a positive likelihood ratio of at least 4.7 for sepsis and 4.2 for septic shock.

Model performance was consistent across most demographic groups. However, the gradient tree boosting model, while the best-performing, is also complex, which could limit scalability.

How will this change my practice?
If recognition of sepsis is the cornerstone of the pediatric ER, then prediction of this life-threatening condition would be a paradigm shift. By predicting future Phoenix Sepsis Criteria-defined sepsis, the models created in this paper point toward a future where risk stratification mirrors our current sepsis definitions. This sets the stage for a world in which AI models can assist in recognizing and treating impending sepsis before patients even show signs of organ dysfunction.

AI models analyze and find patterns in large datasets better than humans. The EHR is ripe for this type of study. This may help us not only with sepsis but other conditions that are time-sensitive, diagnostically noisy, and rely on patterns across multiple (sometimes weak) signals. Appendicitis? Intussusception? DKA? I look forward to future work that pairs this kind of model with clinical gestalt to improve outcomes.

Source
Derivation and Validation of Predictive Models for Early Pediatric Sepsis. JAMA Pediatr. 2025 Dec 1;179(12):1318-1325. doi: 10.1001/jamapediatrics.2025.3892. PMID: 41082207; PMCID: PMC12519407.

View Critical Appraisal

Critical Appraisal

Title: Derivation and Validation of Predictive Models for Early Pediatric Sepsis.
Background: Sepsis is a leading cause of mortality in children, and early recognition is crucial for improving outcomes. Traditional methods have struggled to enhance early diagnosis, prompting exploration of machine learning approaches.
Study Question: Can machine learning models accurately predict the development of sepsis in pediatric patients within 48 hours of an ED visit?
Study Design: Multisite cohort study using electronic health record data for model derivation and validation.
Population: Children aged 2 months to less than 18 years visiting the ED, excluding those with certain ED dispositions.
Intervention: Machine learning models using logistic regression, ridge regression, and gradient tree boosting.
Comparison: Not applicable
Primary Outcome: Development of sepsis or septic shock within 48 hours of ED visit.
Secondary Outcomes: None reported
Key Statistics: Models were derived and validated using data from over 1.6 million ED visits. Gradient tree boosting models showed meaningful positive likelihood ratios.
Results: The gradient tree boosting models effectively predicted sepsis risk, indicating potential for clinical application in early sepsis detection.
Risk of Bias – Newcastle-Ottawa Scale:
  • Selection (3/4 stars) — Some concerns: Large, diverse sample but potential selection bias from retrospective data.
  • Comparability (1/2 stars) — Some concerns: Limited adjustment for potential confounders in model development.
  • Outcome (3/3 stars) — Low risk: Outcome assessment was robust with clear criteria for sepsis diagnosis.
Take Home: Machine learning models can enhance early detection of pediatric sepsis, potentially improving patient outcomes through timely intervention.
This critical appraisal is generated using a structured framework applied to the full text of the original article and is presented separately from the physician’s commentary.

Leave a Reply