Predicting intracranial pressure monitor placement in children with traumatic brain injury - a prospective cohort study to develop a clinical decision support tool

Sep 28, 2026

Uploaded by jay

Clinicians decide whether to place an intracranial pressure (ICP) monitor in pediatric traumatic brain injury (TBI) without an accurate clinical decision support tool. A prospective observational cohort study from September 2014 to January 2024 developed and validated a predictive model that estimates ICP monitor placement and can update as new information arrives. Data from 389 children admitted to a pediatric ICU were analyzed; outcome performance and exclusion criteria are reported, including model comparisons and accuracy metrics.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Abstract

Introduction

Materials and Methods

Results

Conclusions

Keywords

Research and Applications Predicting intracranial pressure monitor placement in children with traumatic brain injury: a prospective cohort study to develop a clinical decision support tool Seth Russell , MS 1, Peter E. DeWitt , PhD 1, Laura Helmkamp, MS2, Kathryn Colborn, PhD, MSPH2,3, Charlotte Gray, MPH4, Margaret Rebull, MA1, Yamila L. Sierra, MPH5, Rachel Greer, BA4, Lexi Petruccelli, BA4, Sara Shankman, CPNP-AC, DNP4,6, Todd C. Hankinson, MD, MBA2,7, Fuyong Xing, PhD3, David J. Albers , PhD 1, Tellen D. Bennett , MD, MS􀀃 , 1,2,6 1 Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO 80045, United States, 2Adult and Child Center for Health Outcomes Research and Delivery Science (ACCORDS), University of Colorado School of Medicine, Aurora, CO 80045, United States, 3 Department of Biostatistics and Informatics, Colorado School of Public Health, Aurora, CO 80045, United States, 4Children’s Hospital Colorado Research Institute, Aurora, CO 80045, United States, 5 Department of Medicine, University of Colorado School of Medicine, Aurora, CO 80045, United States, 6Section of Critical Care Medicine, Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO 80045, United States, 7 Pediatric Neurosurgery, University of Colorado School of Medicine, Aurora, CO 80045, United States 􀀃 Corresponding author: Tellen D. Bennett, MD, MS, Departments of Biomedical Informatics and Pediatrics (Critical Care), Attending Physician, Pediatric Intensive Care Unit, University of Colorado School of Medicine, Children’s Hospital Colorado, 1890 N. Revere Court, Mail Stop 600, Aurora, CO 80045, United States ([tell.bennett@cuanschutz.edu](tell.bennett@cuanschutz.edu)) Abstract Objective: Clinicians currently make decisions about placing an intracranial pressure (ICP) monitor in children with traumatic brain injury (TBI) without the benefit of an accurate clinical decision support tool. The goal of this study was to develop and validate a model that predicts placement of an ICP monitor and updates as new information becomes available. Materials and Methods: A prospective observational cohort study was conducted from September 2014 to January 2024. The setting included one US hospital designated as an American College of Surgeons Level 1 Pediatric Trauma Center. Participants were 389 children with acute TBI admitted to the ICU who had at least one Glasgow Coma Scale (GCS) score ≤ 8 or intubation with at least one GCS-Motor ≤ 5. We excluded children who received ICP monitors prior to arrival, those with GCS ¼ 3 and bilateral fixed, dilated pupils, and those with a do not resuscitate order. Results: Of the 389 participants, 138 received ICP monitoring. Several machine learning models, including a recurrent neural network (RNN), were developed and validated using 4 combinations of input data. The best performing model, an RNN, achieved an F1 of 0.71 within 720 minutes of hospital arrival. The cumulative F1 of the RNN from minute 0 to 720 was 0.61. The best performing non-neural network model, standard logistic regression, achieved an F1 of 0.36 within 720 minutes of hospital arrival. Conclusions: These findings will contribute to design and implementation of a multidisciplinary clinical decision support tool for ICP monitor placement in children with TBI. Key words: pediatrics; traumatic brain injury; intracranial pressure; intracranial hypertension; clinical decision support; machine learning. Introduction Traumatic brain injury (TBI) causes approximately 2200 deaths and 35 000 hospitalizations in US children annually.1 Increased intracranial pressure (ICP) can exacerbate severe TBI and worsen patient outcomes. Decision-making about placement of an ICP monitor is important because ICP monitors can detect elevated ICP and guide treatment. Decisions about secondary medical and surgical therapies with significant risks such as hypothermia, barbiturates, and decompressive sur

FAQs

What was the study objective?

To develop and validate a model that predicts whether an ICP monitor should be placed in children with traumatic brain injury and updates predictions as new information becomes available.

How was the study designed and what time period was included?

It used a prospective observational cohort design conducted from September 2014 to January 2024 in a U.S. hospital designated as an American College of Surgeons Level 1 Pediatric Trauma Center.

Which model performed best and what was its accuracy?

An RNN achieved the best performance, reaching an F1 of 0.71 within 720 minutes of hospital arrival, with a cumulative F1 of 0.61 from minute 0 to 720.

Sep 28, 2026

Uploaded by jay