PREDICTING TOTAL HEALTH-CARE COSTS OF MEDICAID RECIPIENTS - AN ARTIFICIAL NEURAL SYSTEMS-APPROACH

Although medical treatment costs have escalated beyond the reach gi ma ny Americans, a thorough total cost model is essential before implemen ting cost containment strategies. This study offers a prediction model of the total treatment cost for a Mississippi Medicaid patient. Artif icial neural systems (ANS) are proposed as a methodology for the predi ction of health care costs of postmenopausal women who are Medicaid re cipients. The results of the neural networks along with traditional re gression analysis are presented. Artificial neural systems overcome ma ny of the problems associated with the estimation of this model, such as the identification of the appropriate Junctional form and dealing w ith both qualitative and quantitative aspects of these large claims da tabases. Neural networks are shown to provide superior forecasts. In a ddition preliminary results for the presentation of significance tests of individual causal variables using neural networks is presented. (C ) 1997 Elsevier Science Inc.