An analytic approach to understanding and predicting healthcare coverage

Dursun Delen, Christie Fuller

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

1 Citation (Scopus)

Abstract

The inequality in the level of healthcare coverage among the people in the US is a pressing issue. Unfortunately, many people do not have healthcare coverage and much research is needed to identify the factors leading to this phenomenon. Hence, the goal of this study is to examine the healthcare coverage of individuals by applying popular analytic techniques on a wide-variety of predictive factors. A large and feature-rich dataset is used in conjunction with four popular data mining techniques - artificial neural networks, decision trees, support vector machines and logistic regression - to develop prediction models. Applying sensitivity analysis to the developed prediction models, the ranked importance of variables is determined. The experimental results indicated that the most accurate classifier for this phenomenon was the support vector machines that had an overall classification accuracy of 82.23% on the 10-fold holdout/test sample. The most important predictive factors came out as income, employment status, education, and marital status. The ability to identify and explain the reasoning of those likely to be without healthcare coverage through the application of accurate classification models can potentially be used in reducing the disparity in health care coverage.

Original languageEnglish
Title of host publicationInformatics, Management and Technology in Healthcare
PublisherIOS Press
Pages198-200
Number of pages3
ISBN (Print)9781614992752
DOIs
StatePublished - 1 Jan 2013
EventInternational Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2013 - Athens, Greece
Duration: 5 Jul 20137 Jul 2013

Publication series

NameStudies in Health Technology and Informatics
Volume190
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Conference

ConferenceInternational Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2013
CountryGreece
CityAthens
Period5/07/137/07/13

Fingerprint

Delivery of Health Care
Support vector machines
Healthcare Disparities
Decision trees
Health care
Decision Trees
Sensitivity analysis
Aptitude
Data Mining
Data mining
Logistics
Marital Status
Classifiers
Education
Neural networks
Logistic Models
Research
Support Vector Machine
Datasets

Keywords

  • analytics
  • data mining
  • Healthcare coverage
  • sensitivity analysis

Cite this

Delen, D., & Fuller, C. (2013). An analytic approach to understanding and predicting healthcare coverage. In Informatics, Management and Technology in Healthcare (pp. 198-200). (Studies in Health Technology and Informatics; Vol. 190). IOS Press. https://doi.org/10.3233/978-1-61499-276-9-198
Delen, Dursun ; Fuller, Christie. / An analytic approach to understanding and predicting healthcare coverage. Informatics, Management and Technology in Healthcare. IOS Press, 2013. pp. 198-200 (Studies in Health Technology and Informatics).
@inproceedings{9723ffbc965c4b36a81075916847d864,
title = "An analytic approach to understanding and predicting healthcare coverage",
abstract = "The inequality in the level of healthcare coverage among the people in the US is a pressing issue. Unfortunately, many people do not have healthcare coverage and much research is needed to identify the factors leading to this phenomenon. Hence, the goal of this study is to examine the healthcare coverage of individuals by applying popular analytic techniques on a wide-variety of predictive factors. A large and feature-rich dataset is used in conjunction with four popular data mining techniques - artificial neural networks, decision trees, support vector machines and logistic regression - to develop prediction models. Applying sensitivity analysis to the developed prediction models, the ranked importance of variables is determined. The experimental results indicated that the most accurate classifier for this phenomenon was the support vector machines that had an overall classification accuracy of 82.23{\%} on the 10-fold holdout/test sample. The most important predictive factors came out as income, employment status, education, and marital status. The ability to identify and explain the reasoning of those likely to be without healthcare coverage through the application of accurate classification models can potentially be used in reducing the disparity in health care coverage.",
keywords = "analytics, data mining, Healthcare coverage, sensitivity analysis",
author = "Dursun Delen and Christie Fuller",
year = "2013",
month = "1",
day = "1",
doi = "10.3233/978-1-61499-276-9-198",
language = "English",
isbn = "9781614992752",
series = "Studies in Health Technology and Informatics",
publisher = "IOS Press",
pages = "198--200",
booktitle = "Informatics, Management and Technology in Healthcare",

}

Delen, D & Fuller, C 2013, An analytic approach to understanding and predicting healthcare coverage. in Informatics, Management and Technology in Healthcare. Studies in Health Technology and Informatics, vol. 190, IOS Press, pp. 198-200, International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2013, Athens, Greece, 5/07/13. https://doi.org/10.3233/978-1-61499-276-9-198

An analytic approach to understanding and predicting healthcare coverage. / Delen, Dursun; Fuller, Christie.

Informatics, Management and Technology in Healthcare. IOS Press, 2013. p. 198-200 (Studies in Health Technology and Informatics; Vol. 190).

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

TY - GEN

T1 - An analytic approach to understanding and predicting healthcare coverage

AU - Delen, Dursun

AU - Fuller, Christie

PY - 2013/1/1

Y1 - 2013/1/1

N2 - The inequality in the level of healthcare coverage among the people in the US is a pressing issue. Unfortunately, many people do not have healthcare coverage and much research is needed to identify the factors leading to this phenomenon. Hence, the goal of this study is to examine the healthcare coverage of individuals by applying popular analytic techniques on a wide-variety of predictive factors. A large and feature-rich dataset is used in conjunction with four popular data mining techniques - artificial neural networks, decision trees, support vector machines and logistic regression - to develop prediction models. Applying sensitivity analysis to the developed prediction models, the ranked importance of variables is determined. The experimental results indicated that the most accurate classifier for this phenomenon was the support vector machines that had an overall classification accuracy of 82.23% on the 10-fold holdout/test sample. The most important predictive factors came out as income, employment status, education, and marital status. The ability to identify and explain the reasoning of those likely to be without healthcare coverage through the application of accurate classification models can potentially be used in reducing the disparity in health care coverage.

AB - The inequality in the level of healthcare coverage among the people in the US is a pressing issue. Unfortunately, many people do not have healthcare coverage and much research is needed to identify the factors leading to this phenomenon. Hence, the goal of this study is to examine the healthcare coverage of individuals by applying popular analytic techniques on a wide-variety of predictive factors. A large and feature-rich dataset is used in conjunction with four popular data mining techniques - artificial neural networks, decision trees, support vector machines and logistic regression - to develop prediction models. Applying sensitivity analysis to the developed prediction models, the ranked importance of variables is determined. The experimental results indicated that the most accurate classifier for this phenomenon was the support vector machines that had an overall classification accuracy of 82.23% on the 10-fold holdout/test sample. The most important predictive factors came out as income, employment status, education, and marital status. The ability to identify and explain the reasoning of those likely to be without healthcare coverage through the application of accurate classification models can potentially be used in reducing the disparity in health care coverage.

KW - analytics

KW - data mining

KW - Healthcare coverage

KW - sensitivity analysis

UR - http://www.scopus.com/inward/record.url?scp=84894281305&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-276-9-198

DO - 10.3233/978-1-61499-276-9-198

M3 - Conference contribution

C2 - 23823421

AN - SCOPUS:84894281305

SN - 9781614992752

T3 - Studies in Health Technology and Informatics

SP - 198

EP - 200

BT - Informatics, Management and Technology in Healthcare

PB - IOS Press

ER -

Delen D, Fuller C. An analytic approach to understanding and predicting healthcare coverage. In Informatics, Management and Technology in Healthcare. IOS Press. 2013. p. 198-200. (Studies in Health Technology and Informatics). https://doi.org/10.3233/978-1-61499-276-9-198