Probabilistic fuzzy prediction of mortality in intensive care units

Author

Fialho, A.S. ; Kaymak, U. ; Almeida, R.J. ; Cismondi, F. ; Vieira, S.M. ; Reti, S.R. ; Sousa, J.M.C. ; Finkelstein, S.N.

Author_Institution

Eng. Syst. Div., Massachusetts Inst. of Technol., Cambridge, MA, USA

fYear

2012

fDate

10-15 June 2012

Firstpage

1

Lastpage

8

Abstract

In the present work, we propose the application of probabilistic fuzzy systems (PFS) to model the prediction of mortality in septic shock patients. This technique is characterized by the combination of the linguistic description of the system with the statistical properties of data. Preliminary results for this particular clinical problem point that PFS models, besides performing as accurately as first order Takagi-Sugeno fuzzy models, also provide probability measures that provide additional clinical information upon which physicians can act on.

Keywords

fuzzy set theory; hospitals; patient treatment; probability; statistics; PFS; Takagi-Sugeno fuzzy models; clinical information; clinical problem point; intensive care units; linguistic description; mortality; probabilistic fuzzy prediction; probabilistic fuzzy systems; septic shock patients; statistical properties; Electric shock; Fuzzy systems; Maximum likelihood estimation; Parameter estimation; Predictive models; Probabilistic logic; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Systems (FUZZ-IEEE), 2012 IEEE International Conference on

Conference_Location

Brisbane, QLD

ISSN

1098-7584

Print_ISBN

978-1-4673-1507-4

Electronic_ISBN

1098-7584

Type

conf

DOI

10.1109/FUZZ-IEEE.2012.6251261

Filename

6251261