A greedy-based oversampling approach to improve the prediction of mortality in MERS patients

Turki Turki, Zhi Wei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Predicting mortality of Middle East respiratory syndrome (MERS) patients with identified outcomes is a core goal for hospitals in deciding whether a new patient should be hospitalized or not in the presence of limited resources of the hospitals. We present an oversampling approach that we call Greedy-Based Oversampling Approach (GBOA). We evaluate our approach and compare it against the standard oversampling approach from a classification perspective on real dataset collected from the Saudi Ministry of Health using two popular supervised classification methods, Random Forests and Support Vector Machines. Our results demonstrate that our approach outperforms the other standard approach from a classification perspective by giving the highest accuracy with statistical significance on the 20 simulations of the real dataset.

Original languageEnglish (US)
Title of host publication10th Annual International Systems Conference, SysCon 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467395182
DOIs
StatePublished - Jun 13 2016
Event10th Annual International Systems Conference, SysCon 2016 - Orlando, United States
Duration: Apr 18 2016Apr 21 2016

Publication series

Name10th Annual International Systems Conference, SysCon 2016 - Proceedings

Other

Other10th Annual International Systems Conference, SysCon 2016
CountryUnited States
CityOrlando
Period4/18/164/21/16

Fingerprint

Support vector machines
Health

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Networks and Communications

Keywords

  • Classification
  • Intelligent Decision-Making
  • MERS
  • Oversampling
  • Random Forests
  • Support Vector Machines

Cite this

Turki, T., & Wei, Z. (2016). A greedy-based oversampling approach to improve the prediction of mortality in MERS patients. In 10th Annual International Systems Conference, SysCon 2016 - Proceedings [7490617] (10th Annual International Systems Conference, SysCon 2016 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SYSCON.2016.7490617
Turki, Turki ; Wei, Zhi. / A greedy-based oversampling approach to improve the prediction of mortality in MERS patients. 10th Annual International Systems Conference, SysCon 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. (10th Annual International Systems Conference, SysCon 2016 - Proceedings).
@inproceedings{f636d9af0d7e4415800fa6e9410ae375,
title = "A greedy-based oversampling approach to improve the prediction of mortality in MERS patients",
abstract = "Predicting mortality of Middle East respiratory syndrome (MERS) patients with identified outcomes is a core goal for hospitals in deciding whether a new patient should be hospitalized or not in the presence of limited resources of the hospitals. We present an oversampling approach that we call Greedy-Based Oversampling Approach (GBOA). We evaluate our approach and compare it against the standard oversampling approach from a classification perspective on real dataset collected from the Saudi Ministry of Health using two popular supervised classification methods, Random Forests and Support Vector Machines. Our results demonstrate that our approach outperforms the other standard approach from a classification perspective by giving the highest accuracy with statistical significance on the 20 simulations of the real dataset.",
keywords = "Classification, Intelligent Decision-Making, MERS, Oversampling, Random Forests, Support Vector Machines",
author = "Turki Turki and Zhi Wei",
year = "2016",
month = "6",
day = "13",
doi = "https://doi.org/10.1109/SYSCON.2016.7490617",
language = "English (US)",
series = "10th Annual International Systems Conference, SysCon 2016 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "10th Annual International Systems Conference, SysCon 2016 - Proceedings",
address = "United States",

}

Turki, T & Wei, Z 2016, A greedy-based oversampling approach to improve the prediction of mortality in MERS patients. in 10th Annual International Systems Conference, SysCon 2016 - Proceedings., 7490617, 10th Annual International Systems Conference, SysCon 2016 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 10th Annual International Systems Conference, SysCon 2016, Orlando, United States, 4/18/16. https://doi.org/10.1109/SYSCON.2016.7490617

A greedy-based oversampling approach to improve the prediction of mortality in MERS patients. / Turki, Turki; Wei, Zhi.

10th Annual International Systems Conference, SysCon 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. 7490617 (10th Annual International Systems Conference, SysCon 2016 - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A greedy-based oversampling approach to improve the prediction of mortality in MERS patients

AU - Turki, Turki

AU - Wei, Zhi

PY - 2016/6/13

Y1 - 2016/6/13

N2 - Predicting mortality of Middle East respiratory syndrome (MERS) patients with identified outcomes is a core goal for hospitals in deciding whether a new patient should be hospitalized or not in the presence of limited resources of the hospitals. We present an oversampling approach that we call Greedy-Based Oversampling Approach (GBOA). We evaluate our approach and compare it against the standard oversampling approach from a classification perspective on real dataset collected from the Saudi Ministry of Health using two popular supervised classification methods, Random Forests and Support Vector Machines. Our results demonstrate that our approach outperforms the other standard approach from a classification perspective by giving the highest accuracy with statistical significance on the 20 simulations of the real dataset.

AB - Predicting mortality of Middle East respiratory syndrome (MERS) patients with identified outcomes is a core goal for hospitals in deciding whether a new patient should be hospitalized or not in the presence of limited resources of the hospitals. We present an oversampling approach that we call Greedy-Based Oversampling Approach (GBOA). We evaluate our approach and compare it against the standard oversampling approach from a classification perspective on real dataset collected from the Saudi Ministry of Health using two popular supervised classification methods, Random Forests and Support Vector Machines. Our results demonstrate that our approach outperforms the other standard approach from a classification perspective by giving the highest accuracy with statistical significance on the 20 simulations of the real dataset.

KW - Classification

KW - Intelligent Decision-Making

KW - MERS

KW - Oversampling

KW - Random Forests

KW - Support Vector Machines

UR - http://www.scopus.com/inward/record.url?scp=84979220351&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84979220351&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/SYSCON.2016.7490617

DO - https://doi.org/10.1109/SYSCON.2016.7490617

M3 - Conference contribution

T3 - 10th Annual International Systems Conference, SysCon 2016 - Proceedings

BT - 10th Annual International Systems Conference, SysCon 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Turki T, Wei Z. A greedy-based oversampling approach to improve the prediction of mortality in MERS patients. In 10th Annual International Systems Conference, SysCon 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. 7490617. (10th Annual International Systems Conference, SysCon 2016 - Proceedings). https://doi.org/10.1109/SYSCON.2016.7490617