Table 3 Calibration test results on external validation dataset. Calibration-in-the-large indicates whether predicted probabilities are, on average, too high (value below 0) or too low (value above 0). Conversely, the calibration slope quantifies whether predicted risks are, on average, too extreme (value below 1) or too invariant (value above 1)

From: Logistic regression has similar performance to optimised machine learning algorithms in a clinical setting: application to the discrimination between type 1 and type 2 diabetes in young adults