Send to

Choose Destination
J Clin Monit Comput. 2019 Feb;33(1):39-51. doi: 10.1007/s10877-018-0139-y. Epub 2018 May 24.

Forewarning of hypotensive events using a Bayesian artificial neural network in neurocritical care.

Author information

Stats Research Ltd, Dingwall, Scotland, UK.
Department of Neurosurgery, Uppsala University Hospital, Uppsala, Sweden.
Institute of Neurological Sciences, Queen Elizabeth University Hospital, Clinical Physics, Glasgow, Scotland, UK.
Section of Neurosurgery, Uppsala University, Uppsala, Sweden.
Department of Medical Physics, James Cook University Hospital, Middlesbrough, UK.
Neurosurgical Trials Group, Newcastle University, Newcastle upon Tyne, UK.
Hospital San Gerardo, Neurorianimazione, Monza, Italy.
Department of Neurosurgery, Ruprecht-Karls-Universitat Hospital, Heidelberg, Germany.
Kaunas University of Technology, Kaunas, Lithuania.
Department of Neurosurgery, Vall d'Hebron University Hospital, Barcelona, Spain.
Department of Information Systems, University of Melbourne, Parkville, Australia.
Department of Clinical Physics, University of Glasgow, Glasgow, Scotland, UK.


Traumatically brain injured (TBI) patients are at risk from secondary insults. Arterial hypotension, critically low blood pressure, is one of the most dangerous secondary insults and is related to poor outcome in patients. The overall aim of this study was to get proof of the concept that advanced statistical techniques (machine learning) are methods that are able to provide early warning of impending hypotensive events before they occur during neuro-critical care. A Bayesian artificial neural network (BANN) model predicting episodes of hypotension was developed using data from 104 patients selected from the BrainIT multi-center database. Arterial hypotension events were recorded and defined using the Edinburgh University Secondary Insult Grades (EUSIG) physiological adverse event scoring system. The BANN was trained on a random selection of 50% of the available patients (n = 52) and validated on the remaining cohort. A multi-center prospective pilot study (Phase 1, n = 30) was then conducted with the system running live in the clinical environment, followed by a second validation pilot study (Phase 2, n = 49). From these prospectively collected data, a final evaluation study was done on 69 of these patients with 10 patients excluded from the Phase 2 study because of insufficient or invalid data. Each data collection phase was a prospective non-interventional observational study conducted in a live clinical setting to test the data collection systems and the model performance. No prediction information was available to the clinical teams during a patient's stay in the ICU. The final cohort (n = 69), using a decision threshold of 0.4, and including false positive checks, gave a sensitivity of 39.3% (95% CI 32.9-46.1) and a specificity of 91.5% (95% CI 89.0-93.7). Using a decision threshold of 0.3, and false positive correction, gave a sensitivity of 46.6% (95% CI 40.1-53.2) and specificity of 85.6% (95% CI 82.3-88.8). With a decision threshold of 0.3, > 15 min warning of patient instability can be achieved. We have shown, using advanced machine learning techniques running in a live neuro-critical care environment, that it would be possible to give neurointensive teams early warning of potential hypotensive events before they emerge, allowing closer monitoring and earlier clinical assessment in an attempt to prevent the onset of hypotension. The multi-centre clinical infrastructure developed to support the clinical studies provides a solid base for further collaborative research on data quality, false positive correction and the display of early warning data in a clinical setting.


Bayesian prediction; Clinical study results; Neuro-intensive care; Traumatic brain injury


Supplemental Content

Full text links

Icon for Springer
Loading ...
Support Center