Metraipolis › archive › dc_3841fa3d38ca

Improving O-RADS Risk Stratification from Ultrasound Reports: A Comparative Evaluation of Hybrid versus End-to-End LLM Reasoning Strategies — arXiv:2608.23061

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.23061
License (as archived): CC0-1.0
Archived: 2026-10-18T07:41:49.204Z
SHA-256 of the archived text: 044e63aa47606ffcc21b6963551dcca197ae6252cde4846f338bd919aa828cb9
Stable URL of this page: https://metraipolis.com/documento/dc_3841fa3d38ca

How to cite

Improving O-RADS Risk Stratification from Ultrasound Reports: A Comparative Evaluation of Hybrid versus End-to-End LLM Reasoning Strategies — arXiv:2608.23061 — arXiv (en), https://arxiv.org/abs/2608.23061 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3841fa3d38ca (Metraipolis archive dc_3841fa3d38ca, sha256 044e63aa47606ffcc21b6963551dcca197ae6252cde4846f338bd919aa828cb9)

BibTeX

@misc{dc3841fa3d38ca,
  title = {Improving O-RADS Risk Stratification from Ultrasound Reports: A Comparative Evaluation of Hybrid versus End-to-End LLM Reasoning Strategies — arXiv:2608.23061},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.23061},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3841fa3d38ca; sha256 044e63aa47606ffcc21b6963551dcca197ae6252cde4846f338bd919aa828cb9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23061. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Background: Automating clinical guideline-based decision-making with large language models (LLMs) remains challenging because of reliability, hallucination, and limited interpretability. We compared the performance of LLMs and reasoning strategies for automated Ovarian-Adnexal Reporting and Data System (O-RADS) classification from free-text pelvic ultrasound reports. Methods: In this retrospective study, consecutive patients with ovarian masses who underwent pelvic ultrasound were included. Eight LLMs were tested with three reasoning strategies: implicit-knowledge end-to-end, rule-informed end-to-end, and a feature-based hybrid architecture that decoupled feature extraction from rule-based classification. The reference standard was O-RADS categorization established by expert consensus. Results: A total of 310 women with 390 ovarian masses were evaluated. The feature-based hybrid architecture using Gemini 3.6 Flash demonstrated the best performance, achieving an accuracy of 99.2% (387 of 390) and almost perfect agreement with the reference standard (weighted kappa = 1.00; 95% CI: 0.99-1.00). Its performance surpassed that of original clinical reports (accuracy, 87.7% [342 of 390]; weighted kappa = 0.94; 95% CI: 0.91-0.96) and end-to-end LLM strategies (accuracy range, 65.6% [256 of 390] to 95.9% [374 of 390]). For structured feature extraction, Gemini 3.6 Flash demonstrated higher overall accuracy than Claude Fable 5 (98.9% vs 97.8%; P < 0.001). The hybrid architecture reduced misclassification errors and mitigated the overstaging tendency observed in original reports. Conclusion: The feature-based hybrid LLM architecture that separates clinical feature extraction from deterministic guideline execution enables highly accurate, reliable, and interpretable automated O-RADS classification, providing a promising approach for standardized, guideline-based clinical decision-making.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.23061 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T07:37:52.764Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).