Format:
1 Online-Ressource (33 p)
Series Statement:
Computer Science Preprint Archive Vol. 2002, Issue 8, pp 712-744
Content:
This paper aims to establish a patient's intracranial pressure (ICP) model in neurosurgical intensive care unit using neural network. Non-invasive physiological signals from patients including mean arterial pressure (MAP), heart rate (HR), end-tidal of carbon dioxide (EtCO2) and regional cerebral oxygenation (rSO2) were measured. However, ICP remains ill-defined, complicated and nonlinear because it is affected by many predictable and unpredictable factors. Our study employs the structure of recurrent network to develop a modified neural network algorithm called a simple recurrent neural network through time (SRNNTT). The proposed recurrent neural network combines Elman architecture of the simple recurrent network structure and back propagation through time. In order to demonstrate the performance of the proposed model, four kinds of neural-network classifiers have been tested on Mackey-Glass differential-delay equation which is a chaotic time series signal. Finally, we used this SRNNTT model to build the ICP model using data from six head-injured patients. Although the accuracy of the ICP model is still far from ideal, it achieves errors acceptable to neurosurgeons. This demonstrates the feasibility of applying this SRNNTT architecture to modeling ICP. Nevertheless, a longer series of patients' data is needed to retrain the networks, and to determine the extent of its applicability
Note:
Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments August 2002 erstellt
Language:
English
Bookmarklink