Skip to main content

Table 1 Relationship types and examples.

From: Mining clinical relationships from patient narratives

Relation type First argument type Second argument type Description Examples
has_target Investigation Intervention Locus Relates an intervention or an investigation to the bodily locus at which it is targeted. • This patient has had a [arg2] lymph node [arg1] biopsy
• ... he does need a [arg2] groin [arg1] dissection
has_finding Investigation Condition Result Relates a condition to an investigation that demonstrated its presence, or a result to the investigation that produced that result. • This patient has had a lymph node [arg1] biopsy which shows [arg2] melanoma
• Although his [arg1] PET scan is [arg2] normal ...
has_indication Drug or device Investigation Intervention Condition Relates a condition to a drug, intervention, or investigation that is targeted at that condition. • Her facial [arg2] pain was initially relieved by [arg1] co-codamol
has_location Condition Locus Relationship between a condition and a locus: describes the bodily location of a specific condition. • ... a biopsy which shows [arg1] melanoma in his right [arg2] groin
• Her [arg2] facial [arg1] pain was initially relieved by co-codamol
negation_modifies Negation sig nal Condition Relates a condition to its negation or uncertainty about it. • There was [arg1] no evidence of extra pelvic [arg2] secondaries
laterality_modifies Laterality signal Locus Intervention Relates a bodily locus or intervention to its sidedness: right, left, bilateral. • ... on his [arg1] right [arg2] second toe
[arg1] right [arg2] thoracotomy
sub_location_modifies Sub-location signal Locus Relates a bodily locus to other information about the location: upper, lower, extra, etc. [arg1] extra [arg2] pelvic
  1. Relationship types, their argument type constraints, a description and examples. Each example shows a single relation of the given type. Arguments are underlined and preceded by their argument number. (Adapted from the CLEF Annotation Guidelines, http://nlp.shef.ac.uk/clef/)
\