{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T16:18:44Z","timestamp":1791476324283,"version":"4.3.4"},"reference-count":46,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Diabetes"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Gestational diabetes mellitus (GDM) is a prevalent chronic condition that affects maternal and fetal health outcomes worldwide, increasingly in underserved populations. While generative artificial intelligence (AI) and large language models (LLMs) have shown promise in health care, their application in GDM management remains underexplored.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to investigate whether retrieval-augmented generation techniques, when combined with knowledge graphs (KGs), could improve the contextual relevance and accuracy of AI-driven clinical decision support. For this, we developed and validated a graph-based retrieval-augmented generation (GraphRAG)\u2013enabled local LLM as a clinical support tool for GDM management, assessing its performance against open-source LLM tools.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n A prototype clinical AI assistant was developed using a GraphRAG constructed from 1212 peer-reviewed research articles on GDM interventions, retrieved from the Semantic Scholar API (2000\u20102024). The GraphRAG prototype integrated entity extraction, KG construction using Neo4j, and retrieval-augmented response generation. The performance was evaluated in a simulated environment using clinical and layperson prompts, comparing the outputs of the systems against ChatGPT (OpenAI), Claude (Anthropic), and BioMistral models across 5 common natural language generation metrics.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The GraphRAG-enabled local LLM showed higher accuracy in generating clinically relevant responses. It achieved a bilingual evaluation understudy score of 0.99, Jaccard similarity of 0.98, and BERTScore of 0.98, outperforming the benchmark LLMs. The prototype also produced accurate, evidence-based recommendations for clinicians and patients, demonstrating its feasibility as a clinical support tool.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n GraphRAG-enabled local LLMs show much potential for improving personalized GDM care by integrating domain-specific evidence and contextual retrieval. Our prototype proof-of-concept serves two purposes: (1) the local LLM architecture gives practitioners from underserved locations access to state-of-the-art medical research in the treatment of chronic conditions and (2) the KG schema may be feasibly built on peer-reviewed, indexed publications, devoid of hallucinations and contextualized with patient data. We conclude that advanced AI techniques such as KGs, retrieval-augmented generation, and local LLMs improve GDM management decisions and other similar conditions and advance equitable health care delivery in resource-constrained health care environments.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/76454","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T02:05:07Z","timestamp":1760493907000},"page":"e76454-e76454","source":"Crossref","is-referenced-by-count":4,"title":["GraphRAG-Enabled Local Large Language Model for Gestational Diabetes Mellitus: Development of a Proof-of-Concept"],"prefix":"10.2196","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8050-1360","authenticated-orcid":false,"given":"Edmund","family":"Evangelista","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7334-8363","authenticated-orcid":false,"given":"Fathima","family":"Ruba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3541-3124","authenticated-orcid":false,"given":"Salman","family":"Bukhari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7116-7607","authenticated-orcid":false,"given":"Amril","family":"Nazir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8235-5344","authenticated-orcid":false,"given":"Ravishankar","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,1,5]]},"reference":[{"issue":"3","key":"R1","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1108\/IMDS-07-2019-0401","article-title":"Design of blockchain-based precision health-care using soft systems methodology","volume":"120","author":"Sharma","journal-title":"IMDS"},{"issue":"1","key":"R2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01230-5","article-title":"A drug mix and dose decision algorithm for individualized type 2 diabetes management","volume":"7","author":"Nambiar","journal-title":"NPJ Digit Med"},{"issue":"23","key":"R3","doi-asserted-by":"publisher","first-page":"1749","DOI":"10.1056\/NEJM199912023412307","article-title":"Gestational diabetes mellitus","volume":"341","author":"Kjos","journal-title":"N Engl J Med"},{"issue":"3","key":"R4","doi-asserted-by":"publisher","first-page":"676","DOI":"10.2337\/dc09-1848","article-title":"International association of diabetes and pregnancy study groups recommendations on the diagnosis and classification of hyperglycemia in pregnancy","volume":"33","author":"International Association of Diabetes and Pregnancy Study Groups Consensus Panel","journal-title":"Diabetes Care"},{"issue":"2","key":"R5","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.35533","article-title":"Screening for gestational diabetes mellitus: is there a need for early screening for all women in developing countries?","volume":"15","author":"Akinyemi","journal-title":"Cureus"},{"issue":"1\/2","key":"R6","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1108\/ACI-10-2020-0094","article-title":"IDMPF: intelligent diabetes mellitus prediction framework using machine learning","volume":"21","author":"Ismail","journal-title":"ACI"},{"issue":"2","key":"R7","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.35103","article-title":"The effects of gestational diabetes on fetus: a surveillance study","volume":"15","author":"Ejaz","journal-title":"Cureus"},{"issue":"6","key":"R8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0097871","article-title":"Gestational diabetes mellitus in Africa: a systematic review","volume":"9","author":"Macaulay","journal-title":"PLoS ONE"},{"issue":"7","key":"R9","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.ogrm.2023.04.001","article-title":"Gestational diabetes: screening, diagnosis, treatment and management","volume":"33","author":"Stewart-Field","journal-title":"Obstetrics, Gynaecology & Reproductive Medicine"},{"issue":"7","key":"R10","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1007\/s11517-023-02800-7","article-title":"Prediction of gestational diabetes using deep learning and Bayesian optimization and traditional machine learning techniques","volume":"61","author":"Kurt","journal-title":"Med Biol Eng Comput"},{"issue":"3","key":"R11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5455\/njppp.2023.13.01032202306022023","article-title":"Fetomaternal outcome in patients with gestational diabetes mellitus","volume":"13","author":"Jani","journal-title":"Natl J Physiol Pharm Pharmacol"},{"issue":"6","key":"R12","first-page":"1","volume":"2","author":"Alum","journal-title":"Elite Journal of Medical Sciences"},{"issue":"3","key":"R13","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1093\/inthealth\/ihab054","article-title":"Barriers to screening, diagnosis and management of hyperglycaemia in pregnancy in Africa: a systematic review","volume":"14","author":"Hinneh","journal-title":"Int Health"},{"issue":"3","key":"R14","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1108\/JHR-08-2020-0372","article-title":"Preferences of participating in diabetes screening programs for postpartum women with gestational diabetes mellitus in a university hospital in Turkey","volume":"36","author":"Karakoc Kumsar","journal-title":"JHR"},{"issue":"1","key":"R15","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1186\/s12913-021-06077-0","article-title":"Health care professionals\u2019 perspectives on screening and management of gestational diabetes mellitus in public hospitals of South India - a qualitative study","volume":"21","author":"Sahu","journal-title":"BMC Health Serv Res"},{"key":"R16","doi-asserted-by":"crossref","unstructured":"Nikolaidis GF Duarte A Griffin S Lomas J . \u201cBeyond the mean\u201d in biomarkers modelling for economic evaluations: a case study in gestational diabetes mellitus. In: Baltagi BH Moscone F , editors. Recent Developments in Health Econometrics: A Volume in Honour of Andrew Jones. Vol 297. Emerald Publishing Limited; 2024:1108. [doi: 10.1108\/S0573-85552024297] ISBN: 978-1-83753-259-9","DOI":"10.1108\/S0573-85552024297"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2017.00056","article-title":"The challenges and recommendations for gestational diabetes mellitus care in India: a review","volume":"8","author":"Morampudi","journal-title":"Front Endocrinol (Lausanne)"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1186\/s40200-015-0169-7","article-title":"Gestational diabetes mellitus: challenges in diagnosis and management","volume":"14","author":"Mpondo","journal-title":"J Diabetes Metab Disord"},{"key":"R19","doi-asserted-by":"crossref","unstructured":"Pal A Umapathi LK Sankarasubbu M . Med-HALT: Medical Domain Hallucination Test for Large Language Models. Presented at: Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL); Dec 6-7, 2023:314-334; Singapore. [doi: 10.18653\/v1\/2023.conll-1.21]","DOI":"10.18653\/v1\/2023.conll-1.21"},{"issue":"3","key":"R20","doi-asserted-by":"publisher","DOI":"10.3390\/medicina60030445","article-title":"Integrating retrieval-augmented generation with large language models in nephrology: advancing practical applications","volume":"60","author":"Miao","journal-title":"Medicina (Kaunas)"},{"issue":"3-4","key":"R21","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1108\/ACI-01-2021-0022","article-title":"Classification models for likelihood prediction of diabetes at early stage using feature selection","volume":"20","author":"Oladimeji","journal-title":"ACI"},{"issue":"1","key":"R22","doi-asserted-by":"publisher","DOI":"10.1186\/s40842-024-00176-7","article-title":"The role of machine learning algorithms in detection of gestational diabetes; a narrative review of current evidence","volume":"10","author":"Kokori","journal-title":"Clin Diabetes Endocrinol"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2022.109237","article-title":"Population-centric risk prediction modeling for gestational diabetes mellitus: a machine learning approach","volume":"185","author":"Kumar","journal-title":"Diabetes Res Clin Pract"},{"key":"R24","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2023.1130139","article-title":"Machine learning applied in maternal and fetal health: a narrative review focused on pregnancy diseases and complications","volume":"14","author":"Mennickent","journal-title":"Front Endocrinol (Lausanne)"},{"issue":"3","key":"R25","doi-asserted-by":"publisher","first-page":"e1191","DOI":"10.1210\/clinem\/dgaa899","article-title":"Early prediction of gestational diabetes mellitus in the Chinese population via advanced machine learning","volume":"106","author":"Wu","journal-title":"The Journal of Clinical Endocrinology & Metabolism"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2023.3242261","article-title":"Digital health and machine learning technologies for blood glucose monitoring and management of gestational diabetes","volume":"17","author":"Lu","journal-title":"IEEE Rev Biomed Eng"},{"issue":"5","key":"R27","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1136\/gutjnl-2022-328406","article-title":"Gestational diabetes is driven by microbiota-induced inflammation months before diagnosis","volume":"72","author":"Pinto","journal-title":"Gut"},{"issue":"1","key":"R28","doi-asserted-by":"publisher","DOI":"10.1186\/s12884-023-05766-4","article-title":"Development of machine learning models to predict gestational diabetes risk in the first half of pregnancy","volume":"23","author":"Cubillos","journal-title":"BMC Pregnancy Childbirth"},{"key":"R29","doi-asserted-by":"crossref","unstructured":"Wu J Zhu J Qi Y et al. Medical Graph RAG: evidence-based medical large language model via graph retrieval-augmented generation. Presented at: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1). Jul 27 to Aug 1, 2025:Association for Computational Linguistics. 28443-28467; Vienna, Austria. [doi: 10.18653\/v1\/2025.acl-long.1381]","DOI":"10.18653\/v1\/2025.acl-long.1381"},{"issue":"3","key":"R30","doi-asserted-by":"publisher","first-page":"57","DOI":"10.3390\/informatics11030057","article-title":"Large language models in healthcare and medical domain: a review","volume":"11","author":"Nazi","journal-title":"Informatics (MDPI)"},{"issue":"5","key":"R31","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1097\/HEP.0000000000000834","article-title":"Development of a liver disease-specific large language model chat interface using retrieval-augmented generation","volume":"80","author":"Ge","journal-title":"Hepatology"},{"issue":"1","key":"R32","doi-asserted-by":"publisher","DOI":"10.1038\/s44184-024-00056-z","article-title":"Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation","volume":"3","author":"Stade","journal-title":"NPJ Ment Health Res"},{"issue":"6","key":"R33","doi-asserted-by":"publisher","first-page":"1436","DOI":"10.1093\/jamia\/ocad258","article-title":"Efficient healthcare with large language models: optimizing clinical workflow and enhancing patient care","volume":"31","author":"Tripathi","journal-title":"J Am Med Inform Assoc"},{"key":"R34","unstructured":"Ong JCL Jin L Elangovan K et al. Development and testing of a novel large language model-based clinical decision support system for medication safety in 12 clinical specialties. arXiv. Preprint posted online on Jan 29, 2024. [doi: 10.48550\/arXiv.2402.01741]"},{"key":"R35","unstructured":"Semantic Scholar API. Semantic Scholar. 2023. URL: https:\/\/www.semanticscholar.org\/product\/api [Accessed 18-03-2025]"},{"key":"R36","unstructured":"ChatGPT: optimizing language models for dialogue. OpenAI. 2023. URL: https:\/\/openai.com\/index\/chatgpt\/ [Accessed 14-12-2025]"},{"key":"R37","unstructured":"Trajanoska M Stojanov R Trajanov D . Enhancing knowledge graph construction using large language models. arXiv. Preprint posted online on May 8, 2023. [doi: 10.48550\/arXiv.2305.04676]"},{"key":"R38","unstructured":"Neo4j life sciences and healthcare network. Neo4j. URL: https:\/\/neo4j.com\/developer\/life-sciences-and-healthcare [Accessed 14-09-2025]"},{"key":"R39","doi-asserted-by":"crossref","unstructured":"Hu Y Lei Z Zhang Z Pan B Ling C Zhao L . GRAG: Graph Retrieval-Augmented Generation. In: Findings of the Association for Computational Linguistics: NAACL 2025. Association for Computational Linguistics; 2025. URL: https:\/\/aclanthology.org\/2025.findings-naacl.232\/ [Accessed 14-09-2025] [doi: 10.18653\/v1\/2025.findings-naacl.232]","DOI":"10.18653\/v1\/2025.findings-naacl.232"},{"key":"R40","unstructured":"Claude. 2023. URL: https:\/\/www.anthropic.com\/claude [Accessed 14-12-2025]"},{"key":"R41","doi-asserted-by":"crossref","unstructured":"Labrak Y Bazoge A Morin E Gourraud PA Rouvier M Dufour R . BioMistral: a collection of open-source pretrained large language models for medical domains. In: Findings of the Association for Computational Linguistics: ACL 2024. Association for Computational Linguistics; 2024. [Accessed 14-12-2025] [doi: 10.18653\/v1\/2024.findings-acl.348]","DOI":"10.18653\/v1\/2024.findings-acl.348"},{"key":"R42","unstructured":"Ngo NT Van Nguyen C Dernoncourt F Nguyen TH . Comprehensive and practical evaluation of retrieval-augmented generation systems for medical question answering. arXiv. Preprint posted online on Nov 14, 2024. [doi: 10.48550\/arXiv.2411.09213]"},{"key":"R43","doi-asserted-by":"crossref","unstructured":"Xiong G Jin Q Lu Z Zhang A . Benchmarking retrieval-augmented generation for medicine. In: Findings of the Association for Computational Linguistics: ACL 2024. Association for Computational Linguistics; 2024:6233-6251. [doi: 10.18653\/v1\/2024.findings-acl.372]","DOI":"10.18653\/v1\/2024.findings-acl.372"},{"key":"R44","unstructured":"Dobkin R . A man asked ChatGPT how to remove sodium chloride from his diet. It landed him in the hospital. The Independent. Aug 7, 2025. URL: https:\/\/www.independent.co.uk\/news\/health\/chatgpt-medical-advice-hospital-b2803992.html [Accessed 22-12-2025]"},{"issue":"9","key":"R45","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","article-title":"Evaluation and mitigation of the limitations of large language models in clinical decision-making","volume":"30","author":"Hager","journal-title":"Nat Med"},{"key":"R46","unstructured":"Ruba F Nazir A Evangelista E Bukhari S Loft L Sharma R . GraphRAG-architecture-of-a-local-LLM-for-gestational-diabetes-mellitus. GitHub. 2025. URL: https:\/\/github.com\/fathima-ruba\/GraphRAG-Architecture-of-a-local-LLM-for-Gestational-Diabetes-Mellitus [Accessed 08-12-2025]"}],"container-title":["JMIR Diabetes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/diabetes.jmir.org\/2026\/1\/e76454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:07:59Z","timestamp":1782842879000},"score":1,"resource":{"primary":{"URL":"https:\/\/diabetes.jmir.org\/2026\/1\/e76454"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,5]]},"references-count":46,"URL":"https:\/\/doi.org\/10.2196\/76454","relation":{},"ISSN":["2371-4379"],"issn-type":[{"value":"2371-4379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,5]]},"article-number":"v11i3e76454"}}