Skip to main content

Table 4 Breakdown of training sets by categories into which articles were classified by coders

From: Classifying publications from the clinical and translational science award program along the translational research spectrum: a machine learning approach

 

Training set 1

Training set 2

Combined training set

T0

106

56

162

T1/T2

18

46

68

T3/T4

44

50

94

TX

18

12

30

Total included in training set

186

164

350

Not included in training set

15

22

33

Total

201

186

387

  1. T0 through T4 are the phases of research along the translational spectrum. TX denotes publications that were determined by the coders to not fall into any of the T0 through T4 categories. Uncoded denotes publications on which no agreement could be reached by the coders as to the correct category. Note that there is one article that was determined to fall into both the T0 and T1 categories, thus resulting in a total of 387 codings for the 386 articles that were coded