Skip to main content

Table 2 Main entities (entity types)—Count (number of occurrence) in the three EC corpora; numbers in the parentheses are nested occurrence for Chia corpus

From: A comparative study of pre-trained language models for named entity recognition in clinical trial eligibility criteria from multiple corpora

EliIE

 

Covance

 

Chia

 

Main entities

Count

Main entities

Count

Main entities

Count

Condition

4138

Condition

21,022

Condition

12,039 (127)

Drug

1465

Drug

13,671

Drug

3801 (24)

Qualifier

1715

Qualifier_Modifier

12,953

Qualifier

4157 (127)

Measurement

1029

Measurement

7732

Measurement

3305 (9)

Procedure_Device

652

Procedure

5635

Procedure

3595 (54)

Observation

1765

Observation

12,391

Observation

1216 (19)

Temporal_measurement

812

Temporal_constraint

11,326

Temporal

3580 (1066)

Anatomic_location

83

Anatomic_location

648

Negation

843 (0)

  

Negation_Cue

1551

Device

386 (2)

  

Event

4053

Multiplier

671 (8)

  

Permission_Cue

2108

Person

1666 (2)

  

Demographics

869

Value

4002 (60)

  

Device

360

Visit

165 (1)

  

Refractory_condition

662

Mood

616 (13)

  

Investigational_product

559

Reference_point

934 (116)