← Back to the feed
Space & aviationResearch findings

Automated Common Data Element Extraction from Sarcoma Case Reports

Original published 2026.11.14 03:23 KSTAdded to Blackdeck 2026.11.17 02:59 KST

What has changed?

Large language model agents automatically derive CDE schemas from sarcoma case report abstracts

Key points

  1. Common data elements (CDEs) support clinical data comparability but are typically defined manually
  2. Large language model agents derived a CDE schema from 24,588 PubMed abstracts
  3. Of 1,570 consolidated CDEs, 53 were supported by at least 50 abstracts, with 79.2% extraction success rate

Connect it to your work

72,909 candidate CDEs were proposed, consolidated into 1,570, with 53 validated by at least 50 abstracts

What remains unproven

This research note is based on an abstract; check the original for test conditions and application scope.

Originals used for this note

Links open the original publisher in a new tab.

  1. arxivAgentic induction of common data elements and information extraction from sarcoma case report abstracts