Abstract
This paper proposes to model blood-gas information relating to ICU patients using an interval type-2 fuzzy logic system (IT2FLS). The system includes three sub-models, one for relative dead space (Kd), one for carbon-dioxide production volume (VCO2) and the other for shunt. All systems are validated with real data obtained from the Sheffield Royal Hallamshire Hospital Patient Data Management System (PDMS). A set of 68 data retrieved from 13 patients were used for validation of Kd, a set of 82 data from 5 patients were used for validation of VCO2 and a final set of 96 data from 12 patients were used for validation of shunt. Model performances are then compared with previously developed machine-learning models. It is shown that IT2FLS reduces the prediction mean square error (MSE) of Kd from 53.88 to 28.91, the prediction MSE for VCO2 from 451.89 to 389.02 and the prediction MSE for shunt from 25.48 to 22.91. The correlation for Kd is also improved from 0.5430 to 0.6846. It is concluded that IT2FLS represents an effective approach for improving the estimation of such vital model parameters.
The original version of this chapter was inadvertently published with an incorrect chapter pagination 988–993 and DOI 10.1007/978-3-319-32703-7_193. The page range and the DOI has been re-assigned. The correct page range is 994–999 and the DOI is 10.1007/978-3-319-32703-7_194. The erratum to this chapter is available at DOI: 10.1007/978-3-319-32703-7_260
An erratum to this chapter can be found at http://dx.doi.org/10.1007/978-3-319-32703-7_260
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Wang, A. (2008), Hybrid modelling and decision support for ventilator management in intensive care units, PhD thesis, the University of Sheffield
Goode, K.M. (2001), Model based development of a fuzzy logic advisor for artificially ventilated patients, PhD thesis, the University of Sheffield.
Wang, A., Mahfouf, M., Mills, G.H., Panoutsos, G., Linkens, D.A., Goode, K., Kwok H.F. and Denaï, M. (2010) Intelligent model-based advisory system for the management of ventilated intensive care patients: Hybrid blood gas patient model, Computer Methods and Program in engineering, Vol. 99 Issue 2, pp. 195-207
Kwok, H.F. (2003), SIVA: An intelligent advisory system for intensive care ventilator, PhD thesis, the University of Sheffield.
Kwok, H. F., Linkens, D. A., Mahfouf, M. and Mills, G. H. (2004). SIVA: A hybrid knowledge-and-model-based advisory system for intensive care ventilators, IEEE Transactions on Information Technology in Biomedicine 8(2): 161-172
Kwok, H. F., Mills, G. H., Mahfouf, M. and Linkens, D. A. (2001), Model-based neuro-fuzzy control of FiO2 for intensive care mechanical ventilation, Critical Care, 5(supp1): P002-S1
Wang, A., Panoutsos, G.,,Mahfouf, M., Mills, G.H., (2008), Goal-directed therapy for general ICU patients using aggregated multi-objective optimization, 17th World Congress, The International Federation of Automatic Control, Seoul, Korea.
Mohammad-Samuri, S. (2012), Modeling and clinical decision support for critically ill patients in ICU using electrical impedance tomography (EIT), PhD thesis, the University of Sheffield.
Wu, D. and Mendel, J.M. (2014), Designing practical interval type-2 fuzzy logic system made simple, IEEE World Congress on Computational Intelligence, Beijing, China.
Mendel, J.M. and John, R. (2002) Type 2-fuzzy sets made simple, IEEE on Fuzzy Systems, Vol 10. No 2 pp: 2002)
Wu, D. and Mendel, J.M. (2009) enhanced Karnik-Mendel algorithms, IEEE Trans on Fuzzy Systems, vol. 17, no.4, pp. 923-934
Wu, D. and Nie, M. (2011) Comparison practical implementation of type-reduction algorithms for type-2 fuzzy sets and systems, IEEE International Conference on Fuzzy Systems, Taiwan, pp. 2131-2138
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Indera-Putera, S.H., Mahfouf, M., Mills, G.H. (2016). Blood-Gas Modelling for Artificially Ventilated Patients Using Interval Type-2 Fuzzy Logic System. In: Kyriacou, E., Christofides, S., Pattichis, C. (eds) XIV Mediterranean Conference on Medical and Biological Engineering and Computing 2016. IFMBE Proceedings, vol 57. Springer, Cham. https://doi.org/10.1007/978-3-319-32703-7_194
Download citation
DOI: https://doi.org/10.1007/978-3-319-32703-7_194
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-32701-3
Online ISBN: 978-3-319-32703-7
eBook Packages: EngineeringEngineering (R0)