Skip to main content

Table 7 Agreement between annotators for each tag

From: Automatic de-identification of French electronic health records: a cost-effective approach exploiting distant supervision and deep learning models

Tag

Fleiss

O

0.93 (0.922,0.939)

STR

0.96 (0.945,0.976)

ZIP

0.895 (0.847,0.942)

VILLE

0.947 (0.922,0.973)

PATIENT

0.887 (0.852,0.922)

DATE

0.948 (0.929,0.967)

DOCTOR

0.949 (0.935,0.963)

PHONE

0.992 (0.986,0.998)

EMAIL

1 (1,1)