Mining lung cancer patient data to assess healthcare resource utilization

Gloria Phillips-Wren, Phoebe Sharkey, Sydney E Dy

Research output: Contribution to journalArticle

Abstract

The objective of this study is to assess the utilization of healthcare resources by lung cancer patients related to their demographic characteristics, socioeconomic markers, ethnic backgrounds, medical histories, and access to healthcare resources in order to guide medical decision making and public policy. The study compares alternative data mining techniques in combination with traditional regression methods and uses propensity scoring to differentiate the predictive power of various models. The study demonstrates that data mining methods can be applied to large, complex, public-use Medicare insurance claims files to reveal insights such as geographic variation in healthcare delivery practice patterns for lung cancer. The results indicate that decision trees and artificial neural networks, particularly when used in combination, can produce better predictive and descriptive models than regression alone to guide healthcare decisions.

Original languageEnglish (US)
Pages (from-to)1611-1619
Number of pages9
JournalExpert Systems with Applications
Volume35
Issue number4
DOIs
StatePublished - Nov 2008

Fingerprint

Data mining
Insurance
Decision trees
Decision making
Neural networks

Keywords

  • Data mining
  • Healthcare utilization
  • Lung cancer
  • Medicare claims data
  • Propensity score

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications

Cite this

Mining lung cancer patient data to assess healthcare resource utilization. / Phillips-Wren, Gloria; Sharkey, Phoebe; Dy, Sydney E.

In: Expert Systems with Applications, Vol. 35, No. 4, 11.2008, p. 1611-1619.

Research output: Contribution to journalArticle

Phillips-Wren, Gloria ; Sharkey, Phoebe ; Dy, Sydney E. / Mining lung cancer patient data to assess healthcare resource utilization. In: Expert Systems with Applications. 2008 ; Vol. 35, No. 4. pp. 1611-1619.
@article{8b954a7760e14e4c9ce7e1e69b3613a5,
title = "Mining lung cancer patient data to assess healthcare resource utilization",
abstract = "The objective of this study is to assess the utilization of healthcare resources by lung cancer patients related to their demographic characteristics, socioeconomic markers, ethnic backgrounds, medical histories, and access to healthcare resources in order to guide medical decision making and public policy. The study compares alternative data mining techniques in combination with traditional regression methods and uses propensity scoring to differentiate the predictive power of various models. The study demonstrates that data mining methods can be applied to large, complex, public-use Medicare insurance claims files to reveal insights such as geographic variation in healthcare delivery practice patterns for lung cancer. The results indicate that decision trees and artificial neural networks, particularly when used in combination, can produce better predictive and descriptive models than regression alone to guide healthcare decisions.",
keywords = "Data mining, Healthcare utilization, Lung cancer, Medicare claims data, Propensity score",
author = "Gloria Phillips-Wren and Phoebe Sharkey and Dy, {Sydney E}",
year = "2008",
month = "11",
doi = "10.1016/j.eswa.2007.08.076",
language = "English (US)",
volume = "35",
pages = "1611--1619",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "4",

}

TY - JOUR

T1 - Mining lung cancer patient data to assess healthcare resource utilization

AU - Phillips-Wren, Gloria

AU - Sharkey, Phoebe

AU - Dy, Sydney E

PY - 2008/11

Y1 - 2008/11

N2 - The objective of this study is to assess the utilization of healthcare resources by lung cancer patients related to their demographic characteristics, socioeconomic markers, ethnic backgrounds, medical histories, and access to healthcare resources in order to guide medical decision making and public policy. The study compares alternative data mining techniques in combination with traditional regression methods and uses propensity scoring to differentiate the predictive power of various models. The study demonstrates that data mining methods can be applied to large, complex, public-use Medicare insurance claims files to reveal insights such as geographic variation in healthcare delivery practice patterns for lung cancer. The results indicate that decision trees and artificial neural networks, particularly when used in combination, can produce better predictive and descriptive models than regression alone to guide healthcare decisions.

AB - The objective of this study is to assess the utilization of healthcare resources by lung cancer patients related to their demographic characteristics, socioeconomic markers, ethnic backgrounds, medical histories, and access to healthcare resources in order to guide medical decision making and public policy. The study compares alternative data mining techniques in combination with traditional regression methods and uses propensity scoring to differentiate the predictive power of various models. The study demonstrates that data mining methods can be applied to large, complex, public-use Medicare insurance claims files to reveal insights such as geographic variation in healthcare delivery practice patterns for lung cancer. The results indicate that decision trees and artificial neural networks, particularly when used in combination, can produce better predictive and descriptive models than regression alone to guide healthcare decisions.

KW - Data mining

KW - Healthcare utilization

KW - Lung cancer

KW - Medicare claims data

KW - Propensity score

UR - http://www.scopus.com/inward/record.url?scp=48949088710&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48949088710&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2007.08.076

DO - 10.1016/j.eswa.2007.08.076

M3 - Article

AN - SCOPUS:48949088710

VL - 35

SP - 1611

EP - 1619

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 4

ER -