Normalizing acronyms and abbreviations to aid patient understanding of clinical texts: ShARe/CLEF eHealth Challenge 2013, Task 2

Table 1 ^aParticipant system performances from [32, 34] compared against a majority sense baseline performance

Short form normalization system	Unique predictions by the system	Annotations comparable with reference standard	Accuracy
^aUTHealthCCB.B.1	3,774	3,774	71.9*
Majority Sense Baseline	3,774	3,774	69.6
^aUTHealthCCB.B.2	3,774	3,774	68.3
^aLIMSI.1	3,896	3,611	66.4
^aTHCIB.B.1	3,774	3,774	65.7*
^aTeamHealthLanguageLABS	2,987	2,633	46.7*
^aWVU.1	3,068	2,359	42.6

*Indicates that the difference in accuracy is statistically significant with the system immediately below (p < 0.01)

ISSN: 2041-1480