Fig 1.
Deriving the nine-variable prognostic model.
Table 1.
Descriptive statistics of development and validation databases.
Table 2.
Final variables of logistic regression model.
Table 3.
Primary outcome probability for final model variables.
Table 4.
Number of predicted and actual events in validation database.
Fig 2.
Area under receiver operating characteristic of: A) logistic regression model on the development database; B) PE-SCORE model on development database; and C) PE-SCORE model on validation database.
Table 5.
Discrimination and calibration metrics.
Fig 3.
Precision recall curves of: A) logistic regression model on the development database; B) PE-SCORE model on the development database; and C) PE-SCORE model on the validation database.
Fig 4.
Calibration curves of logistic regression on development and PE-SCORE model on both databases.
Fig 5.
Proportions with primary outcome by calculated PE-SCORE.
Legend: Panels A and B show 2D stacked column charts stratified by the proportions of patients with primary composite outcome positive (lower column) and the outcome negative groups (upper column) for each PE-SCORE calculation in the development and validation databases. Panels C and D show column charts for the number of patients with primary outcome positive next to the number with death for each PE-SCORE calculation in the development and validation databases.
Table 6.
Performance of PE-SCORE model at two risk thresholds on both databases.