Bayesian Optimization of Personalized Models for Patient Vital-Sign Monitoring
Open Access
- 19 December 2017
- journal article
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 22 (2) , 301-310
Abstract
Gaussian process regression (GPR) provides a means to generate flexible personalised models of timeseries of patient vital signs. These models can perform useful clinical inference in ways that population-based models cannot. A challenge for the use of personalised models is that they must be amenable to a wide range of parameterisations, to accommodate the plausible physiology of any patient in the population. Additionally, optimal performance is typically achieved when models are regularised in light of knowledge of the physiology of the individual patient. In this paper, we describe a method to build GP models with varying complexity (via covariance kernels) and regularisation (via fixed priors over hyperparameters) on a patient-specific level, for the purpose of robust vitalsign forecasting. To this end, our results present evidence in support of two main hypotheses: (i) the use of patientspecific models can out-perform population-based models for useful clinical tasks, such as vital-sign forecasting; and (ii) the optimal values of (hyper)parameters of these models are best determined by sophisticated methods of optimisation, due to high correlation between dimensions of the search space. The resulting models are sufficiently robust to inform clinicians of a patient's vital-sign trajectory, and warn of imminent deterioration.Keywords
Funding Information
- Engineering and Physical Sciences Research Council
- Royal Academy of Engineering/Man-AHL Research Chair
- Royal Academy of Engineering Research Fellowship
- Research Fellowship at Balliol College, Oxford
- EPSRC “Grand Challenge” Early-Career Fellowship
This publication has 18 references indexed in Scilit:
- Bayesian optimisation of Gaussian processes for identifying the deteriorating patient2017
- Multitask Gaussian Processes for Multivariate Physiological Time-Series AnalysisIEEE Transactions on Biomedical Engineering, 2014
- Predictive Monitoring of Mobile Patients by Combining Clinical Observations With Data From Wearable SensorsIEEE Journal of Biomedical and Health Informatics, 2014
- Gaussian processes for time-series modellingPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2013
- Gaussian Processes for Personalized e-Health Monitoring With Wearable SensorsIEEE Transactions on Biomedical Engineering, 2013
- An Extreme Function Theory for Novelty DetectionIEEE Journal of Selected Topics in Signal Processing, 2012
- Gaussian process regression in vital-sign early warning systems2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2012
- Factorial Switching Linear Dynamical Systems Applied to Physiological Condition MonitoringIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Gaussian Process Robust Regression for Noisy Heart Rate DataIEEE Transactions on Biomedical Engineering, 2008
- A Taxonomy of Global Optimization Methods Based on Response SurfacesJournal of Global Optimization, 2001