Skip to main content
. Author manuscript; available in PMC: 2024 Dec 9.
Published in final edited form as: J Neurosci Methods. 2024 Jul 2;409:110209. doi: 10.1016/j.jneumeth.2024.110209

Table 3. Results from AD-SOLES study tagging validation.

Type Method Specificity Sensitivity (versus all methods) Precision TP FP TN FN
Model full text > 0 0.005 1 0.404 143 208 1 0
full text > 1 0.45 0.909 0.526 130 115 94 13
full text > 2 0.746 0.692 0.652 99 53 156 44
tiabkw 0.933 0.727 0.883 104 14 195 39
model sentence 0.861 0.762 0.793 109 29 180 34
Sex full text > 0 0.053 1 0.865 115 18 1 0
full text > 1 0.579 0.678 0.907 78 8 11 37
full text > 2 0.789 0.417 0.923 48 4 15 67
tiabkw 0.895 0.522 0.968 60 2 17 55
model sentence 0.632 0.991 0.942 114 7 12 1
Species full text > 0 N/A 1 0.521 99 91 0 0
full text > 1 0.143 1 0.559 99 78 13 0
full text > 2 0.407 0.626 0.534 62 54 37 37
tiabkw 0.967 0.98 0.97 97 3 88 2
model sentence 0.802 0.98 0.843 97 18 73 2
Outcome full text > 0 N/A 1 0.671 161 79 0 0
full text > 1 0.646 0.932 0.843 150 28 51 11
full text > 2 0.848 0.497 0.87 80 12 67 81
tiabkw 0.987 0.422 0.986 68 1 78 93
Intervention tiabkw N/A N/A 0.417 85 117 N/A N/A

TP: true positive, FP: false positive, TN: true negative, FN: false negative. N/A cells indicate that the measure cannot be calculated. Rows highlighted in blue indicate optimal approaches.