Metraipolis › archive › dc_cc8733fdd053
Graph-Enhanced Retrieval-Augmented Generation for Postoperative Patient Question Answering: A Comparative Evaluation of Knowledge Graph, Retrieval-Augmented Generation, and Hybrid GraphRAG Approaches…
- Source
- Metraipolis archive
- Original
- https://doi.org/10.3390/bioengineering13101097
- License (as archived)
- CC-BY-4.0
- Archived
- 2026-10-07T09:13:18.573Z
- SHA-256 of the archived text
e9151271ec37f0591519afbfc393e3b23decb932b238af78a26ea968816852c4- Stable URL of this page
https://metraipolis.com/documento/dc_cc8733fdd053
How to cite
Graph-Enhanced Retrieval-Augmented Generation for Postoperative Patient Question Answering: A Comparative Evaluation of Knowledge Graph, Retrieval-Augmented Generation, and Hybrid GraphRAG Approaches… — Metraipolis archive, https://doi.org/10.3390/bioengineering13101097 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_cc8733fdd053 (Metraipolis archive dc_cc8733fdd053, sha256 e9151271ec37f0591519afbfc393e3b23decb932b238af78a26ea968816852c4)
BibTeX
@misc{dccc8733fdd053,
title = {Graph-Enhanced Retrieval-Augmented Generation for Postoperative Patient Question Answering: A Comparative Evaluation of Knowledge Graph, Retrieval-Augmented Generation, and Hybrid GraphRAG Approaches…},
howpublished = {Metraipolis archive},
url = {https://doi.org/10.3390/bioengineering13101097},
note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_cc8733fdd053; sha256 e9151271ec37f0591519afbfc393e3b23decb932b238af78a26ea968816852c4},
year = {2026}
}Archived text
Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://doi.org/10.3390/bioengineering13101097. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Articolo recente con licenza aperta: scheda dai metadati Crossref (journal-article). Titolo: Graph-Enhanced Retrieval-Augmented Generation for Postoperative Patient Question Answering: A Comparative Evaluation of Knowledge Graph, Retrieval-Augmented Generation, and Hybrid GraphRAG Approaches Autori: Srinivasagam Prabha, Bernardo G. Collaco, Carina Rosa Malena, Syed Ali Haider, Nadia Wood, Antonio Jorge Forte Pubblicato: 2026-09-22 · in: Bioengineering · editore: MDPI AG DOI: https://doi.org/10.3390/bioengineering13101097 Licenza dell'articolo: CC-BY-4.0 Abstract (testo degli autori, CC-BY-4.0): Background: Reliable access to postoperative guidance between clinic visits remains inconsistent, and the usefulness of large language models depends on how clinical knowledge is structured and retrieved. Knowledge graph-only (KG-only), vector retrieval-augmented generation (RAG-only), and hybrid graph-retrieval (GraphRAG) architectures have not been directly compared under controlled conditions for postoperative care. Objective: It was to compare these three pipelines on a curated postoperative question-answering benchmark using automated grounding metrics and blinded clinician review. Methods: A benchmark of 250 expert-authored questions (200 in-scope, 20 emergency-intent, 30 out-of-scope) was evaluated on an identical knowledge corpus using Gemini 2.5 Flash for generation and Gemini Embedding-001 for retrieval. Three blinded clinicians rated all 750 outputs; the primary outcome was majority-consensus accuracy across all 250 questions. GraphRAG is a multi-component pipeline that also includes query expansion, a second retrieval stage, evidence fusion, and a monotonic RAG fallback, and is therefore evaluated as a complete hybrid system rather than as graph retrieval in isolation. Results: Overall accuracy was 96.8% (95% CI: 93.8–98.4) for GraphRAG, 94.8% (95% CI: 91.3–96.9) for RAG-only, and 56.0% (95% CI: 49.8–62.0) for KG-only. Both retrieval-augmented systems outperformed KG-only (adjusted p < 0.001). The GraphRAG versus RAG-only difference was 2.0 percentage points, arose from five discordant question pairs and did not reach the Bonferroni-adjusted threshold (exact McNemar p = 0.062; adjusted p = 0.188). The monotonic RAG fallback determined 44.8% of GraphRAG outputs (112 of 250 queries). GraphRAG showed higher context recall (0.851 versus 0.796; adjusted p < 0.001), whereas RAG-only showed higher context precision. Estimated hallucination risk, derived from an LLM-as-a-judge procedure using Gemini 2.5 Flash rather than independent clinical adjudication, was 0.108, 0.132, and 0.436, respectively; the GraphRAG versus RAG-only difference was not significant (adjusted p = 0.771). Inter-rater agreement was high (Fleiss’ kappa = 0.854). Conclusions: Retrieval augmentation, rather than the choice of retrieval architecture, accounted for most of the difference observed. The incremental advantage of GraphRAG over a well-implemented RAG-only system was small, was not statistically significant after correction and reflects the complete hybrid system rather than graph augmentation alone. Emergency-intent accuracy was 75.0% for both retrieval-augmented systems; the architecture is therefore suited to supervised clinical workflows with clinician review, not autonomous patient-facing triage. Prospective validation on authentic patient messages and formal component ablations are required. Fonte: https://api.crossref.org/works/10.3390%2Fbioengineering13101097 — metadati Crossref, consultati il 2026-10-06. Interrogazione: «retrieval augmented generation».