The AUC indicates the discrimination of the prediction model; the Hosmer-Lemeshow χ2 is a measure of the fit of data to the model, or calibration (higher p-values of the statistic indicating better calibration); the Brier score and pseudo-R2 assess overall performance (Brier scores range from 0 to 1, lower scores indicating better performance).
Multivariable Models Predictors | Log Odds [Wald 95% c.i.] | Area under ROC Curve [95% c.i.] | Hosmer-Lemeshow χ2 (p) | Brier Score [pseudo-R2] |
---|---|---|---|---|
≥3 ADL Dependencies (n = 1276) | ||||
Age | 1.105 [1.097, 1.113] | 0.807 [0.795, 0.820] | 5.110 [d.f. = 8] (0.746) | 0.076 [0.240] |
Gender | 0.632 [0.550, 0.725] | |||
JFI Score | 1.403 [1.359, 1.448] | |||
≥2 ADL Dependencies (n = 1752) | ||||
Age | 1.110 [1.103, 1.118] | 0.812 [0.801, 0.822] | 5.997 [d.f. = 8] (0.648) | 0.096 [0.274] |
Gender | 0.633 [0.561, 0.715] | |||
JFI Score | 1.423 [1.382, 1.464] |