Mohamad Samuri, Suzani (2012) Modelling and Clinical Decision Support for Critically-Ill Patients in ICU using Electrical Impedance Tomography (EIT). PhD thesis, University of Sheffield.
Temporary Embargo (access restricted until embargo expiry date) until 20 July 2022.
Request a copy
The choice of appropriate ventilator settings is crucial especially for patients with severely impaired respiratory system to improve the benefit-to-risk ratio of mechanical ventilator by providing adequate gas exchange whilst reducing the risk of ventilator-induced lung injury. However, known bedside measures to guide the clinician in adjusting the ventilator settings are limited in that they tend to give global information regarding the performance of the lungs. Electrical impedance tomography (EIT) is relatively new technique and has been the subject of intensive research since its development in the early 1980s by Barber and Brown. One of the advances in EIT is the development of an absolute EIT system (aEIT) that can estimate absolute values of lung resistivity and lung volumes. In this thesis, a series of calibration and improvements on the aEIT system conducted by the Sheffield’s Group have shown some promising results that allow the system to be the base for the development of a decision support system for guiding respiratory therapy hence enhancing the clinician’s expertise with rapid and precise adjustments of ventilator settings. In this research, the intelligent EIT-based decision support system (IEDSS) is developed to provide advice for optimal changes in ventilator settings. The IEDSS is a knowledge-based decision support system which exploits the expert knowledge in deriving the rules for optimal ventilator settings based on blood gases information and the quantitative parameters of the aEIT system. The performance of IEDSS has been validated in a series of simulation scenarios to mimic the real patients’ state evolution in the intensive care unit. This simulation has fused the information on blood gasses from the extended version of ventilated patient mathematical model and information on the regional lung behavior from the aEIT related models. The results show that not only the IEDSS can generate good ventilator setting advice but also it is able to minimise the risks of lung injuries in all the simulated patients.
|Item Type:||Thesis (PhD)|
|Keywords:||absolute electrical impedance tomography, mechanical ventilation, decision support system|
|Academic Units:||The University of Sheffield > Faculty of Engineering (Sheffield) > Automatic Control and Systems Engineering (Sheffield)|
|Depositing User:||Mrs Suzani Mohamad Samuri|
|Date Deposited:||20 Aug 2012 15:47|
|Last Modified:||08 Aug 2013 08:49|