Skip to main content

Table 5 Prediction of the labels with or without (w/o) adding the MeSH terms. We considered various thresholds for the minimum frequency of the terms, in relation to the number of articles in which they appear

From: Automatic classification of experimental models in biomedical literature to support searching for alternative methods to animal experiments

 

w/o MeSH

thresholds

  

0

10

25

50

100

invertebrates

0.95

1.00

1.00

0.89

0.89

0.90

in_vivo

0.88

0.88

0.88

0.89

0.89

0.88

human

0.86

0.83

0.76

0.87

0.91

0.70

organs

0.82

0.84

0.82

0.75

0.82

0.84

primary_cells

0.75

0.60

0.67

0.89

0.67

0.80

immortal_cell_lines

0.83

0.91

1.00

0.77

0.75

0.71

in_silico

0.75

0.87

0.80

0.80

0.80

0.75

others

0.78

0.64

0.69

0.72

0.80

0.59

All (average)

0.83

0.82

0.83

0.82

0.82

0.77