Skip to main content

Features derived from blood pressure and intracranial pressure predict elevated intracranial pressure events in critically ill children.

Publication ,  Journal Article
Ackerman, K; Mohammed, A; Chinthala, L; Davis, RL; Kamaleswaran, R; Shafi, NI
Published in: Sci Rep
December 12, 2022

Clinicians frequently observe hemodynamic changes preceding elevated intracranial pressure events. We employed a machine learning approach to identify novel and differentially expressed features associated with elevated intracranial pressure events in children with severe brain injuries. Statistical features from physiologic data streams were derived from non-overlapping 30-min analysis windows prior to 21 elevated intracranial pressure events; 200 records without elevated intracranial pressure events were used as controls. Ten Monte Carlo simulations with training/testing splits provided performance benchmarks for 4 machine learning approaches. XGBoost yielded the best performing predictive models. Shapley Additive Explanations analyses demonstrated that a majority of the top 20 contributing features consistently derived from blood pressure data streams up to 240 min prior to elevated intracranial events. The best performing prediction model was using the 30-60 min analysis window; for this model, the area under the receiver operating characteristic window using XGBoost was 0.82 (95% CI 0.81-0.83); the area under the precision-recall curve was 0.24 (95% CI 0.23-0.25), above the expected baseline of 0.1. We conclude that physiomarkers discernable by machine learning are concentrated within blood pressure and intracranial pressure data up to 4 h prior to elevated intracranial pressure events.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Sci Rep

DOI

EISSN

2045-2322

Publication Date

December 12, 2022

Volume

12

Issue

1

Start / End Page

21473

Location

England

Related Subject Headings

  • ROC Curve
  • Machine Learning
  • Intracranial Pressure
  • Intracranial Hypertension
  • Humans
  • Child
  • Blood Pressure
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Ackerman, K., Mohammed, A., Chinthala, L., Davis, R. L., Kamaleswaran, R., & Shafi, N. I. (2022). Features derived from blood pressure and intracranial pressure predict elevated intracranial pressure events in critically ill children. Sci Rep, 12(1), 21473. https://doi.org/10.1038/s41598-022-25169-3
Ackerman, Kassi, Akram Mohammed, Lokesh Chinthala, Robert L. Davis, Rishikesan Kamaleswaran, and Nadeem I. Shafi. “Features derived from blood pressure and intracranial pressure predict elevated intracranial pressure events in critically ill children.Sci Rep 12, no. 1 (December 12, 2022): 21473. https://doi.org/10.1038/s41598-022-25169-3.
Ackerman K, Mohammed A, Chinthala L, Davis RL, Kamaleswaran R, Shafi NI. Features derived from blood pressure and intracranial pressure predict elevated intracranial pressure events in critically ill children. Sci Rep. 2022 Dec 12;12(1):21473.
Ackerman, Kassi, et al. “Features derived from blood pressure and intracranial pressure predict elevated intracranial pressure events in critically ill children.Sci Rep, vol. 12, no. 1, Dec. 2022, p. 21473. Pubmed, doi:10.1038/s41598-022-25169-3.
Ackerman K, Mohammed A, Chinthala L, Davis RL, Kamaleswaran R, Shafi NI. Features derived from blood pressure and intracranial pressure predict elevated intracranial pressure events in critically ill children. Sci Rep. 2022 Dec 12;12(1):21473.

Published In

Sci Rep

DOI

EISSN

2045-2322

Publication Date

December 12, 2022

Volume

12

Issue

1

Start / End Page

21473

Location

England

Related Subject Headings

  • ROC Curve
  • Machine Learning
  • Intracranial Pressure
  • Intracranial Hypertension
  • Humans
  • Child
  • Blood Pressure