Approximately two-thirds of healthcare costs are accounted for by 10% of the patients. Identifying such high-cost patients early can help improve their health and reduce costs. Data from the Arizona Health Care Cost Containment System provides a unique opportunity to exploit state-of-the-art data analysis algorithms to mine data and provide actionable findings that can aid cost containment. A novel data mining approach is proposed for this challenging healthcare problem of predicting patients who are likely to be high-risk in the future. This study indicates that the proposed approach is highly effective and can benefit further research on cost containment.

Original languageEnglish (US)
Pages (from-to)114-132
Number of pages19
JournalInternational Journal of Biomedical Engineering and Technology
Issue number1-2
StatePublished - 2010


  • Data mining
  • Healthcare expenditures
  • High-cost patients
  • Imbalanced data classification
  • Medicaid
  • Non-random sampling
  • Predictive risk modelling
  • Risk adjustment
  • Skewed data

ASJC Scopus subject areas

  • Biomedical Engineering


Dive into the research topics of 'Predictive risk modelling for forecasting high-cost patients: A real-world application using Medicaid data'. Together they form a unique fingerprint.

Cite this