TRV-2026-2994Version 1 · Published

Saved · see the current record

Why this version exists

Certified into the record

The exact text we saved

This is the version exactly as it was saved, character for character. The SHA-256 hash below is a 64-character code worked out from that text. Run the same text through SHA-256 and you get the same code; change a single letter and the code comes out completely different. Each version also stores the previous version’s hash, which chains them together so no version can be swapped out quietly.

TRUVACE RECORD VERSION
record: TRV-2026-2994
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-11-17T12:02:13.477963Z
status: published
lens: g_space
sector: health
headline: Decoding Complications: Large Language Model-Based Classification of Free-Text Entries in Clinical Stroke Registries
dek: Clinical registries capture adverse events (AEs) in free-text fields that are rarely analyzed. We developed a reproducible large language model (LLM)-assisted workflow using 11,216 free-text entries from 18,069 patients in the German Stroke Registry; 9,146 informative entries were retained after filtering. Embedding-based clustering showed poor separation, whereas an LLM-guided taxonomy identified 89 leaf labels. On the model-assisted 1,000-entry development set used for model and prompt selection, GPT-5.4 reach…
gain_title: In a German Stroke Registry study, GPT-5.4 labelled 300 held-out free-text entries at 96.5% weighted F1 against clinician consensus, and the free text documented 1,345 more adverse-event instances (+19.6%) than the structured field for comparable concepts.
problem_title: (none)
trace_subject: (none)
gain_reading: In a German Stroke Registry study, GPT-5.4 labelled 300 held-out free-text entries at 96.5% weighted F1 against clinician consensus, and the free text documented 1,345 more adverse-event instances (+19.6%) than the structured field for comparable concepts.
gain_evidence: weighted F1 against clinician consensus was 96.5% (94.6-98.1) for frozen GPT-5.4 labels | free text documented 1,345 additional instances (+19.6% over 6,867 structured instances)
problem_reading: (none)
problem_evidence: (none)
quick_read: Researchers built a workflow using a large language model to classify free-text adverse-event entries in the German Stroke Registry. They started with 11,216 entries from 18,069 patients and kept 9,146 informative ones. An LLM-guided taxonomy produced 89 leaf labels, while embedding-based clustering separated the entries poorly.

On 300 held-out entries, frozen GPT-5.4 labels reached a weighted F1 of 96.5% against clinician consensus. A locally run open model, Qwen 3.5 27B, reached 90.5%, which suggests a route for sites that cannot send data to external services.

The free text recorded 1,345 more instances of adverse events than the structured field where a comparable one existed, and 7,546 instances with no structured equivalent, most often pneumonia, urinary tract infection and delirium. Adding these complication concepts improved prediction of good functional outcome and death only slightly, and the improvement was minimal once the discharge NIHSS score was included.
limitation: Gains in outcome prediction were minimal once the discharge NIHSS score was included, and the test on a second corpus only showed the software ran end to end rather than validating accuracy.
tag: Evidence-backed gain
key_points: The registry data covered 11,216 free-text entries from 18,069 patients; 9,146 informative entries remained after filtering. | Embedding-based clustering separated entries poorly, so the team used an LLM-guided taxonomy with 89 leaf labels. | On a 1,000-entry development set used for model and prompt selection, GPT-5.4 reached F1 92.4% (95% CI 91.4-93.4). | On 300 held-out entries, weighted F1 against clinician consensus was 96.5% for GPT-5.4 and 90.5% for locally run Qwen 3.5 27B. | Free text documented 1,345 extra instances (+19.6%) over 6,867 structured instances, plus 7,546 instances of events with no structured equivalent. | Complication concepts raised the area under the curve by 0.025 for good functional outcome and 0.018 for death, with minimal gains after adding the discharge NIHSS score. | On 1,979 public coronary-trial fragments from ClinicalTrials.gov, the software ran end to end.
rundown: The team addressed a common gap: registries capture adverse events in free-text fields that are rarely analysed. They filtered 11,216 entries down to 9,146 informative ones and tried embedding-based clustering, which separated them poorly. An LLM-guided taxonomy then produced 89 leaf labels.

The 1,000-entry development set was model-assisted and used to pick the model and prompt, where GPT-5.4 reached F1 92.4%. The more telling test was 300 held-out entries compared with clinician consensus, where frozen GPT-5.4 labels scored 96.5% weighted F1 and local Qwen 3.5 27B scored 90.5%.

Compared with structured documentation, the free text recorded 19.6% more instances of comparable adverse-event concepts and a further 7,546 instances without a structured equivalent. Adding the complication concepts raised AUC by 0.025 for good functional outcome and 0.018 for death beyond baseline covariates and the structured count, but gains were minimal after including the discharge NIHSS score. A run on 1,979 coronary-trial fragments showed the software works on a second text corpus.
sources:
- peer_reviewed | Journal of Medical Systems | https://doi.org/10.1007/s10916-026-02486-y | 2026-11-16
prev: 0000000000000000000000000000000000000000000000000000000000000000
SHA-256 hash
f4a4aebc31475b7ddd8afa52a53e44ba2f478fd67a660db7b6dc0e07fddbdc3b
Previous version’s hash
0000000000000000000000000000000000000000000000000000000000000000
Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-2994 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.