2026 Critical Care Congress Skip to main content
2026 Critical Care Congress Main banner
Final Program


Advance Program
Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Session Icons
Thought Leader Session
Thought Leader Session
Guidelines Session
Guidelines Session
Aging Adult Track
Aging Adult Track
Additional Registration Fee
Additional Registration Fee

Research Snapshot Theater: Future of Critical Care, Pediatric I

Enhancing Unplanned PICU Transfer Recognition With Semi-Automated PEWS

Tuesday, March 24, 2026
8:45 AM - 9:45 AM Central Time
Location: Connections Central - RST 03
  • AI

    Abraham Isak, MD

    UCLA Mattel Children's Hospital

    Disclosure(s): No relevant financial relationship(s) to disclose.

  • AK

    Audrey Kamzan, MD

    Division Chief, Pediatric Hospital Medicine
    UCLA Mattel Children's Hospital

    Disclosure information not submitted.

  • SH

    Scott Hu, MD

    NA
    UCLA Mattel Children's Hospital

    Disclosure information not submitted.

  • CL

    Christine Lee, MD

    Pediatric Hospitalist
    UCLA Mattel Children's Hospital

    Disclosure information not submitted.

Introduction: The pediatric early warning score (PEWS) is a validated scoring tool designed to predict pediatric patient decompensation in the acute care setting, with a goal of preventing delays in interventions or transfers to an intensive care unit (ICU). However, PEWS can be challenging to score accurately as it requires compiling several data points including vital sign data, physical exam findings, level of oxygen support, and other variables. A semi-automated PEWS tool offers the potential to enhance prediction accuracy by streamlining the scoring process, reducing human error, and enabling timely identification of patients at risk of deterioration. This can lead to effective early interventions and a less unplanned ICU transfers, ultimately improving patient outcomes and optimizing healthcare resource utilization. The aim of this study was to analyze historical cases of unplanned PICU transfers at our institution by reviewing PEWS scores at the time of transfer and assessing whether a semi-automated PEWS tool could have predicted the need for escalation earlier.


Methods: We analyzed the EHR of pediatric patients who experienced unplanned PICU transfers from 7/2021-7/2023, extracting PEWS scores at the time of transfer and applying the semi-automated tool to assess its predictive accuracy. Statistical analyses, including sensitivity, specificity, and ROC curve evaluation, will compare the tool’s performance against traditional clinician assessments. The primary outcome is the tool’s ability to predict unplanned transfers more accurately than existing methods.


Results: During the study period, there were 1263 patient admissions and 79 ICU transfers. Prior to implementation of the semi-automated tool, the area under the curve (AUC) was 0.59. After implementation of the tool, the AUC improved to 0.67 (95% confidence interval, 0.608-0.698).


Conclusions: A semi-automated PEWS tool demonstrated statistically significant improvement in its ability to predict ICU transfer. Future directions may include prospective validation in a clinical setting, workflow integration to assess real-time effectiveness, and potential refinements to the PEWS tool. If results are promising, further research may focus on implementation strategies to enhance early warning systems and improve patient outcomes.