Skip to main content

Table 3 Comparison of classification performance between the ā€œtraditional modelā€, versus the random forest model that considered additional variables

From: Developing a random forest algorithm to identify patent foramen ovale and atrial septal defects in Ontario administrative databases

Model

Test accuracy

Test sensitivity

Test specificity

Traditional*

0.68

0.36

0.96

Final random forest model (original)

0.76

0.66

0.85

Final random forest model (tuned)

0.76

0.75

0.76

  1. *Patients were assigned as a PFO based only on ā€˜any stroke or TIA within 1Ā year of closureā€™, and if not, they were assigned as ASD