{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T16:33:12Z","timestamp":1789057992917,"version":"build-2803163510"},"reference-count":34,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Can Assoc Radiol J"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:p>\n                    <jats:bold>Purpose:<\/jats:bold>\n                    Large language models (LLMs) have the potential to support clinical decision-making but often lack training on the latest clinical guidelines. Retrieval-augmented generation (RAG) may enhance guideline adherence by dynamically integrating external information. This study evaluates the performance of two LLMs, GPT-4o and o1-mini, with and without RAG, in adhering to Canadian radiology guidelines for incidental hepatobiliary findings.\n                    <jats:bold>Methods:<\/jats:bold>\n                    A customized RAG architecture was developed to integrate guideline-based recommendations into LLM prompts. Clinical cases were curated and used to prompt models with and without RAG. Primary analyses assessed the rate of guideline adherence with comparisons made between LLMs with and without RAG. Secondary analyses evaluated reading ease, grade level, and response times for generated outputs.\n                    <jats:bold>Results:<\/jats:bold>\n                    A total of 319 clinical cases were evaluated. Adherence rates were 81.7% for GPT-4o without RAG, 97.2% for GPT-4o with RAG, 79.3% for o1-mini without RAG, and 95.1% for o1-mini with RAG. Model performance differed significantly across groups, with RAG-enabled configurations outperforming their non-RAG counterparts (\n                    <jats:italic toggle=\"yes\">P<\/jats:italic>\n                    &lt; .05). RAG-enabled models demonstrated improved reading ease and lower grade level scores; however, all model outputs remained at advanced comprehension levels. Response times for RAG-enabled models increased slightly due to additional retrieval processing but remained clinically acceptable.\n                    <jats:bold>Conclusions:<\/jats:bold>\n                    RAG-enabled LLMs significantly improved adherence to Canadian radiology guidelines for incidental hepatobiliary findings without compromising readability or response times. This approach holds promise for advancing evidence-based care and warrants further validation across broader clinical settings.\n                  <\/jats:p>","DOI":"10.1177\/08465371251323124","type":"journal-article","created":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T23:52:10Z","timestamp":1740700330000},"page":"674-682","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":22,"title":["Evaluating Adherence to Canadian Radiology Guidelines for Incidental Hepatobiliary Findings Using RAG-Enabled LLMs"],"prefix":"10.1177","volume":"76","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1556-8343","authenticated-orcid":false,"given":"Nicholas","family":"Dietrich","sequence":"first","affiliation":[{"name":"Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada"},{"name":"Institute of Biomedical Engineering, University of Toronto, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brett","family":"Stubbert","sequence":"additional","affiliation":[{"name":"Schulich School of Medicine &amp; Dentistry, Western University, London, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2025,2,27]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.39305"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1056\/aidbp2300192"},{"key":"e_1_3_2_4_2","unstructured":"McDuff D Schaekermann M Tu T et al. Towards accurate differential diagnosis with large language models. Published online November 30 2023. http:\/\/arxiv.org\/abs\/2312.00164"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03097-1"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.68521"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmjhci-2023-100978"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00261-015-0605-7"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00261-015-0349-4"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1177\/0846537120928349"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2017.07.018"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2013.05.022"},{"key":"e_1_3_2_13_2","unstructured":"OpenAI. GPT-4o-2024-08-06. Large language model. Published online August 6 2024."},{"key":"e_1_3_2_14_2","doi-asserted-by":"crossref","unstructured":"OpenAI. o1-mini-2024-09-12. Large language model. Published online September 12 2024.","DOI":"10.46607\/iamj12092024"},{"key":"e_1_3_2_15_2","unstructured":"OpenAI. text-embedding-ada-002. Embedding model. Published online December 15 2022."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.15420\/cfr.2017:13:1"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1056\/AIcs2300235"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1080\/10862967509547131"},{"key":"e_1_3_2_19_2","article-title":"Derivation of new readability formulas for navy enlisted personnel","author":"Kincaid JP","year":"1975","unstructured":"Kincaid JP, Fishburne RP, Rogers RL, Chissom BS. Derivation of new readability formulas for navy enlisted personnel. Technical Report Research Branch Report, Naval Technical Training Command; 1975.","journal-title":"Technical Report Research Branch Report, Naval Technical Training Command;"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1037\/h0057532"},{"key":"e_1_3_2_21_2","unstructured":"Python Package Index (PyPI). textstat. Published online July 17 2024."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01091-y"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.241489"},{"key":"e_1_3_2_24_2","unstructured":"Ranjit M Ganapathy G Manuel R Ganu T. Retrieval augmented chest X-ray report generation using OpenAI GPT models. Published online May 5 2023. http:\/\/arxiv.org\/abs\/2305.03660"},{"key":"e_1_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Ji Y Li Z Meng R et al. RAG-RLRC-LaySum at BioLaySumm: integrating retrieval-augmented generation and readability control for Layman summarization of biomedical texts. Published online May 21 2024. http:\/\/arxiv.org\/abs\/2405.13179","DOI":"10.18653\/v1\/2024.bionlp-1.75"},{"key":"e_1_3_2_26_2","unstructured":"Jiang W Zhang S Han B Wang J Wang B Kraska T. PipeRAG: fast retrieval-augmented generation via algorithm-system co-design. Published online March 8 2024. http:\/\/arxiv.org\/abs\/2403.05676"},{"key":"e_1_3_2_27_2","unstructured":"Zhu Y Gu JC Sikora C et al. Accelerating inference of retrieval-augmented generation via sparse context selection. Published online May 25 2024. http:\/\/arxiv.org\/abs\/2405.16178"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3677052.3698671"},{"key":"e_1_3_2_29_2","unstructured":"Kang B Kim J Yun TR Kim CE. Prompt-RAG: pioneering vector embedding-free retrieval-augmented generation in Niche domains exemplified by Korean medicine. Published online January 20 2024. https:\/\/doi.org\/10.48550\/arXiv.2401.11246"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300068"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-024-01435-w"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-79110-x"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1097\/CCE.0000000000001131"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.40969"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinimag.2024.110276"}],"container-title":["Canadian Association of Radiologists Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/08465371251323124","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/08465371251323124","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/08465371251323124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T13:55:18Z","timestamp":1777384518000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/08465371251323124"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,27]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1177\/08465371251323124"],"URL":"https:\/\/doi.org\/10.1177\/08465371251323124","relation":{},"ISSN":["0846-5371","1488-2361"],"issn-type":[{"value":"0846-5371","type":"print"},{"value":"1488-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,27]]}}}