Skip to main content

Table 2 Distribution of classifier scores among ‘included’ and ‘excluded’ evaluation records and related performance metrics

From: Machine learning reduced workload for the Cochrane COVID-19 Study Register: development and evaluation of the Cochrane COVID-19 Study Classifier

Classifier Score

90–99

80–89

70–79

60–69

50–59

40–49

30–39

20–29

10–19

0–9

Totals

Included N

1037

417

256

157

122

85

74

66

63

33

2310

Excluded N

23

39

62

62

69

87

149

188

395

1338

2412

Totals

1060

456

318

219

191

172

223

254

458

1371

Precision

0.98

0.91

0.81

0.72

0.64

0.49

0.33

0.26

0.14

0.02

Cumulative recall

0.45

0.63

0.74

0.81

0.86

0.90

0.93

0.96

0.99

1.00

Cumulative precision

0.98

0.96

0.93

0.91

0.89

0.86

0.81

0.77

0.68

0.49

0.98

Threshold classifier score

7

Screened included Na

2285

Screened excluded Na

1299

Precision

0.64

Discarded (‘Lost’) included Na

25

Discarded excluded Na

1113

Recall

0.99

Net workload reduction Na

1138

Net workload reduction %a

24.1%

  1. aAt threshold score = 7