In this review, 17 of 19 studies that compared performance reported gains from adding SNOMED CT to language models, but only 19 of 37 made direct comparisons.

The paper

The paper's details are OpenAlex's; the citation count is OpenAlex's, 16 Oct 2026. The line on the paper is machine-written, as noted under Why it matters.

Why it matters

Written by Claude (claude-sonnet-5-5) on 16 Oct 2026 from the paper's abstract (as the publisher's record at Crossref publishes it) and its OpenAlex record. Machine-written context to help a reader: it is not evidence, it moves no number, and it may be wrong. The quoted sentence is the claim; where it stands is computed from the record. If it misreads the paper, tell the stewards.

The story so far

1. 1

   What the authors did

   The authors searched five databases (ACM Digital Library, ACL Anthology, IEEE Xplore, PubMed and Embase) for studies from 2018 to 2023, following PRISMA-ScR guidelines. They extracted and synthesised data on model types, integration methods, tasks and performance metrics from 37 studies.

   Machine-written from the paper's abstract, as noted under Why it matters.

2. 2

   What they found

   • Of the 37 studies, most added SNOMED CT to model inputs (28/37, 76%), usually by using concept descriptions to expand training text.
   • Medical concept normalization was the most frequent end task (15/37, 41%).
   • Reported gains ranged widely, from 0.87% to 131.66%, and some studies showed no improvement or a decline on certain metrics.

   Machine-written from the paper's abstract, as noted under Why it matters.

3. 3

   What has been checked on Ecdysis

   Exuvia registered the claim on 16 October 2026, with a test written from the paper. No check has been filed yet.

What would check it

How far it has been checked

1. 1
   Same data, same methodverification · not yet

   Not yet: re-run the paper's analysis on its own data, where the authors have published it.

2. 2
   New data, same methodreproduction · not yet

   Not yet: the same method on new data covering the claim's population and period. Established needs one.

3. 3
   The designrobustness tests and arguments · not yet

   Nothing yet: change the method or the data and see whether it holds (a robustness test), or argue that the method does not test what the claim says.

How sure is the record?

Share this finding

Ready-made posts, written from the record. You post them yourself, from your own account; nothing is ever posted for anyone.

Click a post's text to select all of it. Both posts give the claim's standing on the record, and the longer one says what the checks show and what they do not; the wording changes when the record does. The longer post quotes the paper first, then gives the machine-written headline, marked as such; edit it as you like. To cite the claim, see Cite this claim.

What would prove it wrong

Refuted if a re‑analysis finds that less than 50 % or more than 52 % of the 37 studies provide direct comparisons, or that fewer than 88 % or more than 90 % of those with direct comparisons report performance improvements.

The test as Exuvia registered it on 16 Oct 2026, written from the paper's words.

The wider literature

Other claims from the same paper

• uncheckedA scoping review of 37 studies found three ways of integrating SNOMED CT into LLMs, most often by adding it to the model's inputs (28 of 37).“Three main approaches for integrating SNOMED CT were identified: (1) incorporating SNOMED CT into LLM inputs (28/37, 76%), primarily using concept descriptions to expand training corpora; (2) integra…”
• uncheckedAmong 37 reviewed studies that added SNOMED CT to large language models, medical concept normalization was the most common end task, at 15 studies (41%).“The most frequent end task was medical concept normalization (15/37, 41%), followed by entity extraction or typing and classification.”

Headlines are machine-written from the paper's abstract, or from the quote and the paper's title where no abstract is open; each claim's own words are quoted beneath its headline.