Statistical Methods - Text Mining Techniques for Healthcare Provider Quality Determination - page 152

sacrifice some accuracy in the false positive prediction to greatly reduce the false negative rate. However,
as predictive modeling automatically incorporates regression models, the process of predictive modeling
is essential to health outcomes research.
In addition, the common practice of using the difference between observed and predicted outcomes
to rank the quality of providers should be reconsidered. As it is now, providers with low mortality can be
penalized compared to providers with high mortality since the differential between actual and predicted
can be much larger for providers with higher adverse outcomes.
references
Cerrito, P. (2008). Data Mining Healthcare and Clinical Databases with SAS . Cary, NC: SAS Insti-
tute.
Cerrito, P. B. (2007). Introduction to Data Mining with Enterprise Miner. Cary, NC: SAS Press.
Gamito, E. J., & Crawford, D. E. (2004). Artificial neural networks for predictive modeling in prostate
cancer. Current Oncology Reports , 6 (3), 216-221.
Hodgman, S. B. (2008). Predictive modeilng & outcomes. Professional Case Management , 13 (1),
19-23.
Powers, C. A., Meyer, C. M., Roebuck, M. C., & Vaziri, B. (2005). Predictive modeling of total healthcare
costs using pharmacy claims data: a comparison of alternative econometric cost modeling techniques.
Medical Care , 43 (11), 1065-1072.
Sylvia, M. L., Shadmi, E., Hsiao, C.-J., Boyd, C. M., Schuster, A. B., & Boult, C. (2006). Clinical features
of high risk older person identified by predictive modeling. Disease Management , 9 (1), 56-62.
Tewari, A., Porter, C., Peabody, J., Crawford, E., Demers, R., & Johnson, C. (2001). Predictive modeling
techniques in prostate cancer. Molecular Urology , 5 (4), 147-152.
Tropsha,A., & Golbraikh,A. (2007). Predictive QSAR modeling workflow, model applicability domains,
and virtual screening. Current Pharmaceutical Design , 13 (34), 3494-3504.
Weber, C., & Neeser, K. (2006). Using individualized predictive disease modeling to identify patients
with the potential to benefit from a disease management program for diabetes mellitus. Disease Man-
agement , 9 (4), 242-256.
Whitlock, T., & Johnston, K. (2006). Using predictive modeling to evaluate the financial effect of disease
management. Managed Care Interface , 19 (9), 29-34.