Figure 4.
Internal calibration curves. A completely accurate prediction model will generate a plot where the probability of the actual observed and predicted corresponding completely and fall along the 45°line (dashed line). The apparent calibration curve (dotted line) represents the calibration of the model in the development data set, while the bias-corrected curve (solid line) is the calibration result after correcting the optimism with the 1000 bootstrap-resampling.
