Journal article · 2026 · Open access

A multi-guideline clinical agent for vascular surgery: architecture, implementation, and benchmark evaluation

Vangelis G. Alexiou, Areti Vassiliou, Bauer E. Sumpio, George Geroulakos, Stavros K. Kakkos

Journal of the American Medical Informatics Association · Published 3 November 2026 · DOI 10.1093/jamia/ocag178

Open PDFView at the publisherCite this paper

In brief

“A multi-guideline clinical agent for vascular surgery: architecture, implementation, and benchmark evaluation” is a 2026 journal article by Vangelis G. Alexiou and 4 co-authors, published in Journal of the American Medical Informatics Association. OpenAlex counts 0 citations as of 17 November 2026. It is open access under a CC BY licence: the full text is free to read at Journal of the American Medical Informatics Association.

Citations
0
References
28
Authors
5

Abstract

BACKGROUND: The clinical practice guidelines (CPGs) published by the European Society for Vascular Surgery (ESVS) span approximately 1100 pages whose simultaneous cross-referencing is impractical at the point of care. Unguarded large language models (LLMs) carry hallucination risk, motivating a guideline-locked design. METHODS: We describe the architecture and development of a context-aware clinical agent encompassing the full ESVS corpus of 14 CPGs. The system extends a validated single-guideline GraphRAG prototype with an LLM-driven Guideline Router, an embedded Context Gate that withholds retrieval when decision-critical parameters are absent, dual-channel retrieval, and GPT-5 synthesis under a mandatory citation template. An automated benchmark assessed the final system on 55 vignettes, scored by 2 blinded LLM judges over 3 runs (330 judgments), with clinician adjudication of every flagged claim. RESULTS: The system stayed within its locked corpus, declined all out-of-scope queries, and achieved 98.4% guideline-routing recall. The Context Gate showed 91.9% specificity and 78.6% sensitivity for underspecified queries, and all 259 cited recommendations were verifiable within the locked corpus. Automated judges flagged an unsupported claim in 18.2% of items under a sensitive screening definition; on adjudication by 2 vascular surgeons, 7.3% of items contained a clinically consequential error, none graded capable of causing harm. Clinical acceptability of complete answers was not scored and is reserved for prospective expert evaluation. CONCLUSION: These results support the feasibility of a multi-guideline context-aware clinical agent for vascular surgery; citation traceability and locked-corpus provenance facilitate future auditability.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Alexiou, V. G., Vassiliou, A., Sumpio, B. E., Geroulakos, G., & Kakkos, S. K. (2026). A multi-guideline clinical agent for vascular surgery: architecture, implementation, and benchmark evaluation. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocag178

MLA 9

Alexiou, Vangelis G., et al. “A multi-guideline clinical agent for vascular surgery: architecture, implementation, and benchmark evaluation.” Journal of the American Medical Informatics Association, 2026. https://doi.org/10.1093/jamia/ocag178.

Chicago

Alexiou, Vangelis G., Areti Vassiliou, Bauer E. Sumpio, George Geroulakos, and Stavros K. Kakkos. 2026. “A multi-guideline clinical agent for vascular surgery: architecture, implementation, and benchmark evaluation.” Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocag178.

Harvard

Alexiou, V. G. et al. (2026) ‘A multi-guideline clinical agent for vascular surgery: architecture, implementation, and benchmark evaluation’, Journal of the American Medical Informatics Association. doi:10.1093/jamia/ocag178.

IEEE

V. G. Alexiou, A. Vassiliou, B. E. Sumpio, G. Geroulakos, and S. K. Kakkos, “A multi-guideline clinical agent for vascular surgery: architecture, implementation, and benchmark evaluation,” Journal of the American Medical Informatics Association, 2026, doi: 10.1093/jamia/ocag178.

BibTeX

@article{alexiou2026multi,
  title     = {{A multi-guideline clinical agent for vascular surgery: architecture, implementation, and benchmark evaluation}},
  author    = {Alexiou, Vangelis G. and Vassiliou, Areti and Sumpio, Bauer E. and Geroulakos, George and Kakkos, Stavros K.},
  journal   = {Journal of the American Medical Informatics Association},
  year      = {2026},
  doi       = {10.1093/jamia/ocag178},
  url       = {https://doi.org/10.1093/jamia/ocag178}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education

  • vascular surgery
  • large language models
  • graph-based retrieval-augmented generation
  • hallucination mitigation
  • auditability
  • clinical decision support

Work with this paper

Most-cited papers in Medicine

All highly cited Medicine papers

Questions about this paper

How do I cite this paper in APA style?

Alexiou, V. G., Vassiliou, A., Sumpio, B. E., Geroulakos, G., & Kakkos, S. K. (2026). A multi-guideline clinical agent for vascular surgery: architecture, implementation, and benchmark evaluation. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocag178

How many times has this paper been cited?

0 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Journal of the American Medical Informatics Association: sign in and open the PDF from this page.

Who wrote this paper?

Vangelis G. Alexiou, Areti Vassiliou, Bauer E. Sumpio, George Geroulakos, Stavros K. Kakkos.

What is the DOI of this paper?

10.1093/jamia/ocag178, permanently at https://doi.org/10.1093/jamia/ocag178. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.