Skip to main content

Table 6 Identification performance of dictionary-based pathogen identification on the READBiomed-Pathogens data set, considering more/less frequent pathogenic organisms separately. More frequent means the top 10 pathogens as shown in Table 2, while the remaining pathogens have been grouped in the Less frequent category

From: Classifying literature mentions of biological pathogens as experimentally studied using natural language processing

More frequent

Precision

Recall

F1

Macro-average

0.9198

0.7335

0.8161

Micro-average

0.9141

0.7209

0.8061

Less frequent

Precision

Recall

F1

Macro-average

0.7771

0.8063

0.7914

Micro-average

0.8790

0.7245

0.7943