Healthcare cost and predictive factors: high- and low-utilization model development.

Healthcare costs in the U.S. are the highest in the world and are increasing rapidly. With increasing costs, employers and health insurance companies are trying to contain the cost of healthcare. This study aims at developing a predictive model relating enrollees' healthcare insurance claims to their health risks while controlling for gender, age, and their previous year's claims. Our study findings suggest that age, gender, and a previous year's healthcare expenditure are strong predictors of healthcare cost and that none of the six biomarkers was a significant predictor. Even though these biomarkers failed to contribute to the predictive model, they are, nonetheless, important predictors of future chronic diseases, many of which are leading causes of death in the U.S.