Presence

The assertion that a finding was present, absent, indeterminate, or unknown on an exam. Authoring guidance makes it the required first attribute of every finding model, with the value set “absent, present, indeterminate, unknown.”¹

Presence carries the project’s central claim that a negative is data. “Findings must cover negative assertions. When a radiologist states ‘no fracture’ or ‘upper abdomen is unremarkable,’ that’s an active observation of absence that needs to be captured… The presence: absent observation is clinically meaningful, it means the finding was looked for and not found.”¹

The dot-code convention. Value codes are generated by appending a dot and the value’s zero-based position in the attribute’s value list.² Where the standard ordering is used, that gives .0 absent, .1 present, .2 indeterminate, .3 unknown, which is the convention consuming code documents: “.1 = present, .0 = absent.”³ Across the 2,382 published definitions, 2,261 carry a presence attribute and 2,223 of those use that ordering.

Synonyms and near-synonyms

• Presence or absence and present/absent describe the same attribute.
• Detected is IHE IDR’s value for the same assertion.⁴
• Indeterminate means the exam could not determine it; unknown means it was not assessed. The two are distinct values, not spellings of one.
• Change from prior is the companion second attribute, not part of presence.

Identifier form

An ordinary OIFMA_[A-Z]{3,4}_[0-9]{6} attribute identifier with dot-suffixed value codes.

Where it is used

Finding model format, Exam Finding List, and Imaging Problem List.

Conflicts

Three disagreements are live.

1. The dot code is positional, not semantic. 38 published definitions order their presence values differently, so .0 means present rather than absent in those models. Most are CDE-derived or MassGeneral Brigham-contributed. Consuming code that hard-codes .1 as present is wrong for those definitions.
2. The value set is not shared with extraction. The extraction schema uses present, absent, indeterminate, and possible, where “‘possible’ covers hedged language like ‘raising the possibility of’, ‘suggestive of’, ‘cannot exclude’.”⁵ possible has no finding model counterpart and unknown has no extraction counterpart.
3. Spelling and placement vary. At least one definition spells the value “indeterminant,” and IHE IDR records an open question about whether presence should be the first child of a set or the value of the set itself.⁴

Footnotes

1. “Finding Models: Overview” ↩ ↩²

2. Value-code generation in the findingmodel package ↩

3. imaging-problem-list domain model, dev branch ↩

4. IHE IDR Phase II extract ↩ ↩²

5. Initial extraction plan ↩