FigureĀ 3
Receiver operating characteristic curves of variables predicting future anti-bradycardia pacing. For each predictor value cut-off, the sensitivity (true positive rate) is plotted against 1-specificity (false positive rate) and the points are joined to form a curve (interrupted lines). An ideal predictor would have a point passing through the top-left-hand corner of the graph, and a useless predictor would lie on the diagonal line joining the lower-left- and top-right-hand corners of the graph. An area under the curve (c statistic) of 1 indicates perfect prediction whilst an area of 0.5 indicates random predictions.16

Receiver operating characteristic curves of variables predicting future anti-bradycardia pacing. For each predictor value cut-off, the sensitivity (true positive rate) is plotted against 1-specificity (false positive rate) and the points are joined to form a curve (interrupted lines). An ideal predictor would have a point passing through the top-left-hand corner of the graph, and a useless predictor would lie on the diagonal line joining the lower-left- and top-right-hand corners of the graph. An area under the curve (c statistic) of 1 indicates perfect prediction whilst an area of 0.5 indicates random predictions.16

Close
This Feature Is Available To Subscribers Only

Sign In or Create an Account

Close

This PDF is available to Subscribers Only

View Article Abstract & Purchase Options

For full access to this pdf, sign in to an existing account, or purchase an annual subscription.

Close