Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
10355832 | Journal of Biomedical Informatics | 2005 | 9 Pages |
Abstract
Validation of AUC values across all models suggests that certain risk factors have remained important over the last decade. However, the lack of calibration suggests that small changes in patient populations and data collection methods quickly reduce the accuracy of patient level estimations over time. Possible solutions to this problem involve either recalibration of models using local data or development of new local models.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Science Applications
Authors
M.E. Matheny, L. Ohno-Machado, F.S. Resnic,