Comments on 'Evaluating the added predictive ability of a new marker: From area under the ROC curve to reclassification and beyond' by M. J. Pencina, R. B. D'Agostino Sr, R. B. D'Agostino Jr, R. S. Vasan, Statistics in Medicine (DOI: 10.1002/sim.2929).

摘要

In 1998,I co-authored an editorial [1] that identified three major problems related to cardiovascular risk assessment and risk reduction: (a) measurement of risk factors and collection of clinical data relevant to patient risk; (b) interpretation of risk-related data with estimation of risk in absolute terms (e.g. risk of an event per year) as well as relative terms (i.e. low, intermediate, or high compared with others of the same age and sex); and (c) on the basis of risk estimation results, intervention to minimize disease risk or to prevent risk factor development in the future. We noted that problems existed in each of these critical steps, and called for further research in each of these areas to achieve better control of cardiovascular risk factors in the clinical setting. Since the editorial appeared, much work has focused on the second of the three issues above-improvements in the statistical assessment and interpretation of risk. The article by Pencina and colleagues in this issue [2] contributes to this area and is a definite step forward in the assessment of new risk factors. It remains to be seen, of course, whether it can have an impact on either of the other two steps, each of which remains highly important for the clinical application of the new statistical approach.