@inproceedings{112a688381ec499381471fe07235c287,
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 = "Medicaid, Predictive risk modeling, data mining, future high-cost patients, health care expenditures, imbalanced data classification, non-random sampling, risk adjustment, skewed data",
author = "Moturu, {Sai T.} and Huan Liu",
year = "2008",
month = dec,
day = "1",
doi = "10.1007/978-3-540-92219-3_37",
language = "English (US)",
isbn = "3540922180",
series = "Communications in Computer and Information Science",
pages = "493--506",
booktitle = "Biomedical Engineering Systems and Technologies - International Joint Conference, BIOSTEC 2008, Revised Selected Papers",
note = "1st International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2008 ; Conference date: 28-01-2008 Through 31-01-2008",
}