Predicting intensive care unit readmissions using probabilistic fuzzy systems

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

6 Citations (Scopus)

Abstract

We propose the application of probabilistic fuzzy systems (PFS) to model the prediction of early readmission in intensive care unit patients and compare it with the gold-standard method - logistic regression based on the APACHE II score. PFS are characterized by the combination of the linguistic description of the system with the statistical properties of data. On one hand, results point that PFS models perform comparably to the gold-standard method, with AUC values of 0.66±0.03. On the other hand, results also show that PFS models use a significant lower number of variables which, from the clinical practice point of view, suggests improved gains in terms of simplicity
Original languageEnglish
Title of host publication2013 IEEE International Conference on Fuzzy Systems (FUZZ - IEEE 2013), 7-10 July 2013, Hyderabad, India
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages1-7
ISBN (Electronic)978-1-4799-0022-0
ISBN (Print)978-1-4799-0021-3
DOIs
Publication statusPublished - 2013
Event2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2013) - Hyderabad International Convention Center, Hyderabad, India
Duration: 7 Jul 201310 Jul 2013
http://www.isical.ac.in/~fuzzieee2013/

Publication series

NameIEEE International Conference on Fuzzy Systems

Conference

Conference2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2013)
Abbreviated titleFUZZ-IEEE 2013
Country/TerritoryIndia
CityHyderabad
Period7/07/1310/07/13
Internet address

Fingerprint

Dive into the research topics of 'Predicting intensive care unit readmissions using probabilistic fuzzy systems'. Together they form a unique fingerprint.

Cite this