Outcome Prediction for Patients with Traumatic Brain Injury with Dynamic Features from Intracranial Pressure and Arterial Blood Pressure Signals: A Gaussian Process Approach
Previous work has been demonstrated that tracking features describing the dynamic and time-varying patterns in brain monitoring signals provide additional predictive information beyond that derived from static features based on snapshot measurements. To achieve more accurate predictions of outcomes of patients with traumatic brain injury (TBI), we proposed a statistical framework to extract dynamic features from brain monitoring signals based on the framework of Gaussian processes (GPs). GPs provide an explicit probabilistic, nonparametric Bayesian approach to metric regression problems. This not only provides probabilistic predictions, but also gives the ability to cope with missing data and infer model parameters such as those that control the function’s shape, noise level and dynamics of the signal. Through experimental evaluation, we have demonstrated that dynamic features extracted from GPs provide additional predictive information in addition to the features based on the pressure reactivity index (PRx). Significant improvements in patient outcome prediction were achieved by combining GP-based and PRx-based dynamic features. In particular, compared with the a baseline PRx-based model, the combined model achieved over 30 % improvement in prediction accuracy and sensitivity and over 20 % improvement in specificity and the area under the receiver operating characteristic curve.
KeywordsGaussian process Intracranial pressure Dynamic features and outcome prediction
Dr Mengling Feng’s fellowship is funded by A*STAR Graduate Scholarship (AGS). Marco A F Pimentel is supported by the RCUK Digital Economy Program grant number EP/G036861/1 (Oxford Centre for Doctoral Training in Healthcare Innovation) and FCT – Fundação para a Ciência e a Tecnologia – under grant SFRH/DB/79799/2011.
Conflict of Interest Statement
We declare that we have no conflicts of interest.
- 1.Abad N, Druzgalski C (2009) Medical and engineering support and needs in neurological intensive care units. In: Proceedings of the PAHCE'09, Mexico City, Mexico, pp 157–159Google Scholar
- 2.Arindam C, Prasanth BN, Andy JK (2002) A data parallel approach for large-scale Gaussian process modeling. Proceeding of SDMGoogle Scholar
- 8.Czosnyka M, Hutchinson PJ, Balestreri M, Hiler M, Smielewski P, Pickard JD (2006) Monitoring and interpretation of intracranial pressure after head injury. Acta Neurochir Suppl 96(4):121–125Google Scholar
- 10.Edward S, Zoubin G (2005) Sparse Gaussian processes using pseudo-inputs. NIPSGoogle Scholar
- 11.Feng M, Loy LY, Zhang F, Guan CT et al.(2011) Artifact removal for intracranial pressure monitoring Signals. In: A Robust Solution with Signal Decomposition. Proceedings of 33rd international conference of the IEEE Engineering in Medicine and Biology Society (EMBC)Google Scholar
- 20.Marmarou A, Anderson JRL, Ward JD, Choi SC, Young HF, Eisenberg HM, Foulkes MA, Marshall LF, Jane JA (1991) Impact of ICP instability and hypotension on outcome in patients with severe heal trauma. J Neurosurg 75:59–66Google Scholar
- 21.Marmarou A (2000) Increased intracranial pressure in head injury and influence of blood volume. J Neurotrauma 9:327–333Google Scholar
- 22.Rasmussen E, Williams CKI (2006) Gaussian processes for machine learning. MIT Press, ISBN 0-262-18253, usGoogle Scholar
- 23.Roberts S, Osborne M, Ebden M, Reece S, Gibson N, Aigrain S (2012) Gaussian processes for time-series modelling. Philosophical Transactions of the Royal Society (Part A), 371(1984): onlineGoogle Scholar