Development and Validation of an Artificial Intelligence Predictive Model to Accelerate Antibiotic Therapy for Critical Ill Children with Sepsis in the Pediatric ED with Pediatric ICU Disposition

Importance Pediatric sepsis accounts for over 72,000 US hospitalizations annually with significant mortality and morbidity. Many pediatric hospitals struggle to promptly identify and treat sepsis. This study demonstrates the feasibility of a multi-tiered artificial intelligence (AI) to enhance sepsis clinical decision-making within a complex emergency department (ED) workflow.

To develop and validate a local AI model predicting critical sepsis among ED patients who received a fluid bolus and a disposition to the Pediatric Intensive Care Unit (PICU) but had not yet received antibiotics. Design Retrospective observational cross-section study Setting Urban, quaternary-care, academic healthcare system Patients Pediatric ED patients Interventions None Measures and Main Results The “Sepsis on ED to PICU Disposition” (SEPD) model aimed to predict critical sepsis within 72 hours of PICU disposition using a dataset totaling 5,534 patient encounters for model training and testing. During silent implementation, 1,058 encounters were used for validation. The SEPD model outperformed a vendor-developed sepsis model with an AUROC of 81.8%, compared to 57.5%. The model also demonstrated better precision-recall performance, showing more balanced identification of true positives. During silent implementation, the SEPD model maintained similar sensitivity (85.29%) and specificity (60.45%) to those observed during model testing.

The SEPD model improved detection of critical sepsis among high-risk pediatric ED patients with a known PICU disposition, outperforming a vendor-developed sepsis model. Within a complex ED workflow, this model may facilitate timely sepsis identification and treatment in critically ill patients, who may have been missed during earlier stages of their ED course. Competing Interest Statement All authors have completed the ICMJE uniform disclosure form at www.icmje.org/coi_disclosure.pdf and declare: : no support from any organization for the submitted work; EO and NM are co-founders and have equity in Phrase Health a clinical decision support analytics company. They are Investigators on an R42 grant with Phrase Health from the National Library of Medicine (NLM) and National Center for Advancing Translational Science (NCATS). Both of them receive salary support from the NLM and NCATS, but no direct revenue from Phrase Health. Funding Statement Supported in part by the National Center for Advancing Translational Sciences of the National Institutes of Health under Award Number UL1TR002378 and KL2TR002381 (MVM). Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: The protocol for this retrospective analysis of model performance was reviewed and deemed not human subjects research by the Children's Healthcare of Atlanta Institutional Review Board. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes Footnotes Funding / Support: This work was supported by the Agency for Healthcare Research and Quality (AHRQ) and the National Center for Advancing Translational Sciences (NCATS) of the National Institutes of Health (NIH) grant numbers 5R03HS029417-02 (SK, EWO, MVM), UL1TR002378 (MVM) and KL2TR002381 (MVM). Data Availability Data sharing is not applicable to this article as no new datasets were generated or analyzed during the quality improvement project. This study used existing institutional data that cannot be shared publicly due to confidentiality agreements.