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

doi:10.1109/FUZZ-IEEE.2013.6622414

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

Information Systems IE&IS

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

8 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 language	English
Title of host publication	2013 IEEE International Conference on Fuzzy Systems (FUZZ - IEEE 2013), 7-10 July 2013, Hyderabad, India
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	1-7
ISBN (Electronic)	978-1-4799-0022-0
ISBN (Print)	978-1-4799-0021-3
DOIs	https://doi.org/10.1109/FUZZ-IEEE.2013.6622414
Publication status	Published - 2013
Event	2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2013) - Hyderabad International Convention Center, Hyderabad, India Duration: 7 Jul 2013 → 10 Jul 2013 http://www.isical.ac.in/~fuzzieee2013/

Conference

Conference	2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2013)
Abbreviated title	FUZZ-IEEE 2013
Country/Territory	India
City	Hyderabad
Period	7/07/13 → 10/07/13
Internet address	http://www.isical.ac.in/~fuzzieee2013/

Access to Document

10.1109/FUZZ-IEEE.2013.6622414

Cite this

Fialho, A. S., Kaymak, U., Cismondi, F., Vieira, S. M., Reti, S. R., Sousa, J. M. C., & Finkelstein, S. N. (2013). Predicting intensive care unit readmissions using probabilistic fuzzy systems. In 2013 IEEE International Conference on Fuzzy Systems (FUZZ - IEEE 2013), 7-10 July 2013, Hyderabad, India (pp. 1-7). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/FUZZ-IEEE.2013.6622414

@inproceedings{4d2a24ea5820461a82f7d72991fc70f0,

title = "Predicting intensive care unit readmissions using probabilistic fuzzy systems",

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",

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

year = "2013",

doi = "10.1109/FUZZ-IEEE.2013.6622414",

language = "English",

isbn = "978-1-4799-0021-3",

pages = "1--7",

booktitle = "2013 IEEE International Conference on Fuzzy Systems (FUZZ - IEEE 2013), 7-10 July 2013, Hyderabad, India",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2013), FUZZ-IEEE 2013 ; Conference date: 07-07-2013 Through 10-07-2013",

url = "http://www.isical.ac.in/\textasciitilde{}fuzzieee2013/",

}

Fialho, AS, Kaymak, U, Cismondi, F, Vieira, SM, Reti, SR, Sousa, JMC & Finkelstein, SN 2013, Predicting intensive care unit readmissions using probabilistic fuzzy systems. in 2013 IEEE International Conference on Fuzzy Systems (FUZZ - IEEE 2013), 7-10 July 2013, Hyderabad, India. Institute of Electrical and Electronics Engineers, Piscataway, pp. 1-7, 2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2013), Hyderabad, India, 7/07/13. https://doi.org/10.1109/FUZZ-IEEE.2013.6622414

Predicting intensive care unit readmissions using probabilistic fuzzy systems. / Fialho, A.S.; Kaymak, U.; Cismondi, F. et al.
2013 IEEE International Conference on Fuzzy Systems (FUZZ - IEEE 2013), 7-10 July 2013, Hyderabad, India. Piscataway: Institute of Electrical and Electronics Engineers, 2013. p. 1-7.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Predicting intensive care unit readmissions using probabilistic fuzzy systems

AU - Fialho, A.S.

AU - Kaymak, U.

AU - Cismondi, F.

AU - Vieira, S.M.

AU - Reti, S.R.

AU - Sousa, J.M.C.

AU - Finkelstein, S.N.

PY - 2013

Y1 - 2013

N2 - 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

AB - 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

U2 - 10.1109/FUZZ-IEEE.2013.6622414

DO - 10.1109/FUZZ-IEEE.2013.6622414

M3 - Conference contribution

SN - 978-1-4799-0021-3

SP - 1

EP - 7

BT - 2013 IEEE International Conference on Fuzzy Systems (FUZZ - IEEE 2013), 7-10 July 2013, Hyderabad, India

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2013)

Y2 - 7 July 2013 through 10 July 2013

ER -

Predicting intensive care unit readmissions using probabilistic fuzzy systems

Abstract

Conference

Access to Document

Fingerprint

Cite this