Abstract

Rapidly rising healthcare costs represent one of the major issues plaguing the healthcare system. Data from the Arizona Health Care Cost Containment System, Arizona's Medicaid program provide a unique opportunity to exploit state-of-the-art machine learning and data mining algorithms to analyze data and provide actionable findings that can aid cost containment. Our work addresses specific challenges in this real-life healthcare application with respect to data imbalance in the process of building predictive risk models for forecasting high-cost patients. We survey the literature and propose novel data mining approaches customized for this compelling application with specific focus on non-random sampling. Our empirical study indicates that the proposed approach is highly effective and can benefit further research on cost containment in the healthcare industry.

Original languageEnglish (US)
Title of host publicationCommunications in Computer and Information Science
Pages493-506
Number of pages14
Volume25 CCIS
DOIs
StatePublished - 2008
Event1st International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2008 - Funchal, Madeira, Portugal
Duration: Jan 28 2008Jan 31 2008

Publication series

NameCommunications in Computer and Information Science
Volume25 CCIS
ISSN (Print)18650929

Other

Other1st International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2008
CountryPortugal
CityFunchal, Madeira
Period1/28/081/31/08

Fingerprint

Sampling
Costs
Data mining
Health care
Learning systems
Industry

Keywords

  • data mining
  • future high-cost patients
  • health care expenditures
  • imbalanced data classification
  • Medicaid
  • non-random sampling
  • Predictive risk modeling
  • risk adjustment
  • skewed data

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Moturu, S. T., Liu, H., & Johnson, W. (2008). Understanding the effects of sampling on healthcare risk modeling for the prediction of future high-cost patients. In Communications in Computer and Information Science (Vol. 25 CCIS, pp. 493-506). (Communications in Computer and Information Science; Vol. 25 CCIS). https://doi.org/10.1007/978-3-540-92219-3_37

Understanding the effects of sampling on healthcare risk modeling for the prediction of future high-cost patients. / Moturu, Sai T.; Liu, Huan; Johnson, William.

Communications in Computer and Information Science. Vol. 25 CCIS 2008. p. 493-506 (Communications in Computer and Information Science; Vol. 25 CCIS).

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

Moturu, ST, Liu, H & Johnson, W 2008, Understanding the effects of sampling on healthcare risk modeling for the prediction of future high-cost patients. in Communications in Computer and Information Science. vol. 25 CCIS, Communications in Computer and Information Science, vol. 25 CCIS, pp. 493-506, 1st International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2008, Funchal, Madeira, Portugal, 1/28/08. https://doi.org/10.1007/978-3-540-92219-3_37
Moturu ST, Liu H, Johnson W. Understanding the effects of sampling on healthcare risk modeling for the prediction of future high-cost patients. In Communications in Computer and Information Science. Vol. 25 CCIS. 2008. p. 493-506. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-540-92219-3_37
Moturu, Sai T. ; Liu, Huan ; Johnson, William. / Understanding the effects of sampling on healthcare risk modeling for the prediction of future high-cost patients. Communications in Computer and Information Science. Vol. 25 CCIS 2008. pp. 493-506 (Communications in Computer and Information Science).
@inproceedings{5d2a0da4e4cb43cb83e5d040e5db0112,
title = "Understanding the effects of sampling on healthcare risk modeling for the prediction of future high-cost patients",
abstract = "Rapidly rising healthcare costs represent one of the major issues plaguing the healthcare system. Data from the Arizona Health Care Cost Containment System, Arizona's Medicaid program provide a unique opportunity to exploit state-of-the-art machine learning and data mining algorithms to analyze data and provide actionable findings that can aid cost containment. Our work addresses specific challenges in this real-life healthcare application with respect to data imbalance in the process of building predictive risk models for forecasting high-cost patients. We survey the literature and propose novel data mining approaches customized for this compelling application with specific focus on non-random sampling. Our empirical study indicates that the proposed approach is highly effective and can benefit further research on cost containment in the healthcare industry.",
keywords = "data mining, future high-cost patients, health care expenditures, imbalanced data classification, Medicaid, non-random sampling, Predictive risk modeling, risk adjustment, skewed data",
author = "Moturu, {Sai T.} and Huan Liu and William Johnson",
year = "2008",
doi = "10.1007/978-3-540-92219-3_37",
language = "English (US)",
isbn = "3540922180",
volume = "25 CCIS",
series = "Communications in Computer and Information Science",
pages = "493--506",
booktitle = "Communications in Computer and Information Science",

}

TY - GEN

T1 - Understanding the effects of sampling on healthcare risk modeling for the prediction of future high-cost patients

AU - Moturu, Sai T.

AU - Liu, Huan

AU - Johnson, William

PY - 2008

Y1 - 2008

N2 - Rapidly rising healthcare costs represent one of the major issues plaguing the healthcare system. Data from the Arizona Health Care Cost Containment System, Arizona's Medicaid program provide a unique opportunity to exploit state-of-the-art machine learning and data mining algorithms to analyze data and provide actionable findings that can aid cost containment. Our work addresses specific challenges in this real-life healthcare application with respect to data imbalance in the process of building predictive risk models for forecasting high-cost patients. We survey the literature and propose novel data mining approaches customized for this compelling application with specific focus on non-random sampling. Our empirical study indicates that the proposed approach is highly effective and can benefit further research on cost containment in the healthcare industry.

AB - Rapidly rising healthcare costs represent one of the major issues plaguing the healthcare system. Data from the Arizona Health Care Cost Containment System, Arizona's Medicaid program provide a unique opportunity to exploit state-of-the-art machine learning and data mining algorithms to analyze data and provide actionable findings that can aid cost containment. Our work addresses specific challenges in this real-life healthcare application with respect to data imbalance in the process of building predictive risk models for forecasting high-cost patients. We survey the literature and propose novel data mining approaches customized for this compelling application with specific focus on non-random sampling. Our empirical study indicates that the proposed approach is highly effective and can benefit further research on cost containment in the healthcare industry.

KW - data mining

KW - future high-cost patients

KW - health care expenditures

KW - imbalanced data classification

KW - Medicaid

KW - non-random sampling

KW - Predictive risk modeling

KW - risk adjustment

KW - skewed data

UR - http://www.scopus.com/inward/record.url?scp=78049402991&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78049402991&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-92219-3_37

DO - 10.1007/978-3-540-92219-3_37

M3 - Conference contribution

SN - 3540922180

SN - 9783540922186

VL - 25 CCIS

T3 - Communications in Computer and Information Science

SP - 493

EP - 506

BT - Communications in Computer and Information Science

ER -