Improvement of prognostic models for ESRD mortality by the bootstrap method with random hot deck imputation

Ting Ru Lin, Ching Jung Yang, I. Jen Chiang

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

Abstract

Prognostic models for end-stage renal disease (ESRD) have been researched extensively as an increasing prevalence internationally. Different machine learning and statistic algorithms for the models were proposed in studies corresponding to different medical datasets including a quantity of missing values for optimal outcomes. We approached this issue by applying stepwise logistic regression, ANN, and SVM algorithms to an ESRD dataset after case deletion and calculated areas under ROC curves of three algorithms as comparisons, resulting in 0.757, 0.664 and 0.704, respectively. The random hot deck, oversampling, and bootstrap methods were employed in data preprocessing to compensate the minor mortality. Afterward, average AUC of three algorithms approximated 0.90 (p

Original languageEnglish
Title of host publicationProceedings - 2014 IEEE International Conference on Granular Computing, GrC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages166-169
Number of pages4
ISBN (Print)9781479954643
DOIs
Publication statusPublished - Dec 11 2014
Externally publishedYes
Event2014 IEEE International Conference on Granular Computing, GrC 2014 - Hokkaido, Japan
Duration: Oct 22 2014Oct 24 2014

Other

Other2014 IEEE International Conference on Granular Computing, GrC 2014
CountryJapan
CityHokkaido
Period10/22/1410/24/14

Fingerprint

Learning systems
Logistics
Statistics

Keywords

  • ANN
  • end-stage renal diseases
  • oversampling
  • random hot deck imputation
  • stepwise logistic regression
  • SVM
  • the bootstrap method

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Cite this

Lin, T. R., Yang, C. J., & Chiang, I. J. (2014). Improvement of prognostic models for ESRD mortality by the bootstrap method with random hot deck imputation. In Proceedings - 2014 IEEE International Conference on Granular Computing, GrC 2014 (pp. 166-169). [6982828] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GRC.2014.6982828

Improvement of prognostic models for ESRD mortality by the bootstrap method with random hot deck imputation. / Lin, Ting Ru; Yang, Ching Jung; Chiang, I. Jen.

Proceedings - 2014 IEEE International Conference on Granular Computing, GrC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 166-169 6982828.

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

Lin, TR, Yang, CJ & Chiang, IJ 2014, Improvement of prognostic models for ESRD mortality by the bootstrap method with random hot deck imputation. in Proceedings - 2014 IEEE International Conference on Granular Computing, GrC 2014., 6982828, Institute of Electrical and Electronics Engineers Inc., pp. 166-169, 2014 IEEE International Conference on Granular Computing, GrC 2014, Hokkaido, Japan, 10/22/14. https://doi.org/10.1109/GRC.2014.6982828
Lin TR, Yang CJ, Chiang IJ. Improvement of prognostic models for ESRD mortality by the bootstrap method with random hot deck imputation. In Proceedings - 2014 IEEE International Conference on Granular Computing, GrC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 166-169. 6982828 https://doi.org/10.1109/GRC.2014.6982828
Lin, Ting Ru ; Yang, Ching Jung ; Chiang, I. Jen. / Improvement of prognostic models for ESRD mortality by the bootstrap method with random hot deck imputation. Proceedings - 2014 IEEE International Conference on Granular Computing, GrC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 166-169
@inproceedings{19e01a4f11e048be8bb33b57777b2443,
title = "Improvement of prognostic models for ESRD mortality by the bootstrap method with random hot deck imputation",
abstract = "Prognostic models for end-stage renal disease (ESRD) have been researched extensively as an increasing prevalence internationally. Different machine learning and statistic algorithms for the models were proposed in studies corresponding to different medical datasets including a quantity of missing values for optimal outcomes. We approached this issue by applying stepwise logistic regression, ANN, and SVM algorithms to an ESRD dataset after case deletion and calculated areas under ROC curves of three algorithms as comparisons, resulting in 0.757, 0.664 and 0.704, respectively. The random hot deck, oversampling, and bootstrap methods were employed in data preprocessing to compensate the minor mortality. Afterward, average AUC of three algorithms approximated 0.90 (p",
keywords = "ANN, end-stage renal diseases, oversampling, random hot deck imputation, stepwise logistic regression, SVM, the bootstrap method",
author = "Lin, {Ting Ru} and Yang, {Ching Jung} and Chiang, {I. Jen}",
year = "2014",
month = "12",
day = "11",
doi = "10.1109/GRC.2014.6982828",
language = "English",
isbn = "9781479954643",
pages = "166--169",
booktitle = "Proceedings - 2014 IEEE International Conference on Granular Computing, GrC 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Improvement of prognostic models for ESRD mortality by the bootstrap method with random hot deck imputation

AU - Lin, Ting Ru

AU - Yang, Ching Jung

AU - Chiang, I. Jen

PY - 2014/12/11

Y1 - 2014/12/11

N2 - Prognostic models for end-stage renal disease (ESRD) have been researched extensively as an increasing prevalence internationally. Different machine learning and statistic algorithms for the models were proposed in studies corresponding to different medical datasets including a quantity of missing values for optimal outcomes. We approached this issue by applying stepwise logistic regression, ANN, and SVM algorithms to an ESRD dataset after case deletion and calculated areas under ROC curves of three algorithms as comparisons, resulting in 0.757, 0.664 and 0.704, respectively. The random hot deck, oversampling, and bootstrap methods were employed in data preprocessing to compensate the minor mortality. Afterward, average AUC of three algorithms approximated 0.90 (p

AB - Prognostic models for end-stage renal disease (ESRD) have been researched extensively as an increasing prevalence internationally. Different machine learning and statistic algorithms for the models were proposed in studies corresponding to different medical datasets including a quantity of missing values for optimal outcomes. We approached this issue by applying stepwise logistic regression, ANN, and SVM algorithms to an ESRD dataset after case deletion and calculated areas under ROC curves of three algorithms as comparisons, resulting in 0.757, 0.664 and 0.704, respectively. The random hot deck, oversampling, and bootstrap methods were employed in data preprocessing to compensate the minor mortality. Afterward, average AUC of three algorithms approximated 0.90 (p

KW - ANN

KW - end-stage renal diseases

KW - oversampling

KW - random hot deck imputation

KW - stepwise logistic regression

KW - SVM

KW - the bootstrap method

UR - http://www.scopus.com/inward/record.url?scp=84920723207&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84920723207&partnerID=8YFLogxK

U2 - 10.1109/GRC.2014.6982828

DO - 10.1109/GRC.2014.6982828

M3 - Conference contribution

SN - 9781479954643

SP - 166

EP - 169

BT - Proceedings - 2014 IEEE International Conference on Granular Computing, GrC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -