Skip to content

Advertisement

Open Access

Novel models to predict elevated intracranial pressure during intensive care and long-term neurological outcome after TBI

  • F Guiza1,
  • B Depreitere1,
  • I Piper2,
  • G Van den Berghe1 and
  • G Meyfroidt1
Critical Care201216(Suppl 1):P291

https://doi.org/10.1186/cc10898

Published: 20 March 2012

Keywords

European CountryMachine LearningArterial PressureEmergency MedicineMean Arterial Pressure

Introduction

Elevated intracranial pressure (ICP) episodes are associated with poor outcome and should be prevented. We developed models to predict these episodes 30 minutes in advance, and to predict long-term neurological outcome by using dynamic characteristics of continuous ICP and mean arterial pressure (MAP) monitoring.

Methods

The Brain-IT [1] dataset has records for 264 patients from 22 neuro-ICUs in 11 European countries. Logistic regression and Gaussian processes (machine learning method) were used. CRASH [2] and IMPACT [3] predictors were used together with dynamic data.

Results

Predictions of elevated ICP episodes (Figure 1) were externally validated with good calibration and discrimination (AUROC 0.87). Prediction of poor neurological outcome at 6 months (GOS 1 to 2) with static data had 0.72 AUROC; adding dynamic information increased performance to 0.9 (Table 1).
Figure 1
Figure 1

Elevated ICP episode.

Table 1

Model performance

 

Elevated ICP

GOS 1 to 2 static

GOS 1 to 2 dynamic

AUROC

0.87

0.72

0.90

HL P value

0.12

0.51

0.95

Brier scaled

39.4%

7.7%

46%

Conclusion

Dynamic data in continuous MAP and ICP monitoring allows prediction of elevated ICP. Adding information of the first 24 hours of ICP and MAP to known risk factors allows accurate prediction of neurological outcome at 6 months.

Authors’ Affiliations

(1)
UZ Leuven, Belgium
(2)
Southern General Hospital, Glasgow, UK

References

  1. Piper I, et al: Acta Neurochir. 2003, 145: 615-628. 10.1007/s00701-003-0066-6.View ArticlePubMedGoogle Scholar
  2. Murray GD, et al: J Neurotrauma. 2007, 24: 329-337. 10.1089/neu.2006.0035.View ArticlePubMedGoogle Scholar
  3. CRASH Trial Collaborators: BMJ. 2008, 336: 425-429.View ArticleGoogle Scholar

Copyright

© Guiza et al.; licensee BioMed Central Ltd. 2012

This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Advertisement