This Article Full Text (PDF) e-companion References Alert me when this article is cited Alert me if a correction is posted Services Email this article to a friend Similar articles in this journal Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Bertsimas, D. Articles by Wang, G. Search for Related Content

Algorithmic Prediction of Health-Care Costs

Operations Research Center, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139
Stanford Graduate School of Business, Stanford, California 94305
Medical Department, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139
D2Hawkeye, Waltham, Massachusetts 02453
D2Hawkeye, Waltham, Massachusetts 02453
ARC ThinkTank, Georgia Institute of Technology, Atlanta, Georgia 30332
Electrical Engineering and Computer Science Department, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139
dbertsim{at}mit.edu
margret{at}stanford.edu
mkane{at}med.mit.edu
ckryder{at}d2hawkeye.com
rpandey{at}d2hawkeye.com
vempala{at}cc.gatech.edu
gjw{at}alum.mit.edu

The rising cost of health care is one of the world's most important problems. Accordingly, predicting such costs with accuracy is a significant first step in addressing this problem. Since the 1980s, there has been research on the predictive modeling of medical costs based on (health insurance) claims data using heuristic rules and regression methods. These methods, however, have not been appropriately validated using populations that the methods have not seen. We utilize modern data-mining methods, specifically classification trees and clustering algorithms, along with claims data from over 800,000 insured individuals over three years, to provide rigorously validated predictions of health-care costs in the third year, based on medical and cost data from the first two years. We quantify the accuracy of our predictions using unseen (out-of-sample) data from over 200,000 members. The key findings are: (a) our data-mining methods provide accurate predictions of medical costs and represent a powerful tool for prediction of health-care costs, (b) the pattern of past cost data is a strong predictor of future costs, and (c) medical information only contributes to accurate prediction of medical costs of high-cost members.

Subject classifications: health care; cost predictions; prediction algorithms; claims data.
History: Received January 2007; revision received July 2008; accepted July 2008.