Novel methods to predict increased intracranial pressure during intensive care and long-term neurologic outcome after traumatic brain injury: development and validation in a multicenter dataset.

OBJECTIVE

Intracranial pressure monitoring is standard of care after severe traumatic brain injury. Episodes of increased intracranial pressure are secondary injuries associated with poor outcome. We developed a model to predict increased intracranial pressure episodes 30 mins in advance, by using the dynamic characteristics of continuous intracranial pressure and mean arterial pressure monitoring. In addition, we hypothesized that performance of current models to predict long-term neurologic outcome could be substantially improved by adding dynamic characteristics of continuous intracranial pressure and mean arterial pressure monitoring during the first 24 hrs in the ICU.

DESIGN

Prognostic modeling. Noninterventional, observational, retrospective study.

SETTING AND PATIENTS

The Brain Monitoring with Information Technology dataset consisted of 264 traumatic brain injury patients admitted to 22 neuro-ICUs from 11 European countries.

INTERVENTIONS

None.

MEASUREMENTS

Predictive models were built with multivariate logistic regression and Gaussian processes, a machine learning technique. Predictive attributes were Corticosteroid Randomisation After Significant Head Injury-basic and International Mission for Prognosis and Clinical Trial design in TBI-core predictors, together with time-series summary statistics of minute-by-minute mean arterial pressure and intracranial pressure.

MAIN RESULTS

Increased intracranial pressure episodes could be predicted 30 mins ahead with good calibration (Hosmer-Lemeshow p value 0.12, calibration slope 1.02, calibration-in-the-large -0.02) and discrimination (area under the receiver operating curve = 0.87) on an external validation dataset. Models for prediction of poor neurologic outcome at six months (Glasgow Outcome Score 1-2) based only on static admission data had 0.72 area under the receiver operating curve; adding dynamic information of intracranial pressure and mean arterial pressure during the first 24 hrs increased performance to 0.90. Similarly, prediction of Glasgow Outcome Score 1-3 was improved from 0.68 to 0.87 when including dynamic information.

CONCLUSION

The dynamic information in continuous mean arterial pressure and intracranial pressure monitoring allows to accurately predict increased intracranial pressure in the neuro-ICU. Adding information of the first 24 hrs of intracranial pressure and mean arterial pressure monitoring to known baseline risk factors allows very accurate prediction of long-term neurologic outcome at 6 months.