The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index; 5 of the 17 sources its claims cite were checked for support.
Unlocking electronic health records: a hybrid graph RAG approach to safe clinical AI for patient QA
Open accessAbstract
MediGRAF combines Neo4j Text2Cypher structured retrieval with vector embeddings over unstructured clinical notes for patient-level QA on MIMIC-IV.
Overview
CoChat Summary
## TL;DR
MediGRAF is a hybrid graph RAG system for patient-level EHR question answering that combines Text2Cypher graph retrieval with vector search over unstructured notes. In a 10-patient MIMIC-IV evaluation, it achieved 100% recall on factual queries and strong expert-rated performance on complex questions, with 0/10 unsafe responses.
## Key findings
- On simple queries (n=100), the Cypher-only system achieved 80% accuracy, precision 0.8, recall 0.8, and F1 0.8; the hybrid system achieved 100% accuracy and recall, with precision/F1 not applicable because outputs were enriched responses rather than discrete answers.
- On medium-complexity queries (n=31), the Cypher-only system achieved 51.6% accuracy, precision 0.806, recall 0.688, and F1 0.742; the hybrid system achieved 100% accuracy and recall.
- For 10 complex queries evaluated by two clinical reviewers, the hybrid system scored high on factual accuracy and completeness: Evaluator 1 rated both at 4.40±1.02 and 4.40±0.92, and Evaluator 2 rated both at 4.90±0.30.
- No complex-query responses were flagged as unsafe by either evaluator (0/10 cases). The paper also reports a mean expert quality score of 4.25/5 for complex inference tasks and 100% recall for factual queries.
## Methods
- The paper presents MediGRAF, a hybrid Graph RAG system combining Neo4j Text2Cypher for structured retrieval with OpenAI text-embedding-3-small vectors for semantic search over discharge summaries and radiology reports.
- Evaluation used MIMIC-IV version 3.1 data from 10 patients, producing 5,973 nodes and 5,963 relationships; the cohort included 4 single-encounter patients and 6 multi-encounter patients (2–9 admissions), with 89 free-text documents embedded.
- The evaluation dataset comprised 141 QA pairs manually curated by three independent clinicians; simple/medium queries were assessed with precision/recall/F1/accuracy, and complex queries were judged by two hospital physicians using 5-point Likert scales plus a binary safety metric.
## Limitations
- The authors state the evaluation scope was only 10 patients and two evaluators, which limits generalisability; they explicitly call for more patients, more clinical experts, and multiple institutions.
- The paper notes context window limitations for hospital-wide queries and source-attribution ambiguity from context flattening; this limits transparency and requires filtering/pagination or future citation-aware generation.
- The use of Likert scales for complex queries is subjective because there was no discrete ground truth for inference-based responses; this is stated in the paper.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures






Verification
Claims the paper makes
5 Valid · 2 Not valid · 9 Not checked · 51 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, this wealth of information presents a paradoxical challenge: while more data are available than ever before, manually reviewing current and historical admission notes has become increasingly time-consuming and cognitively demanding, potentially leading to overlooked clinically significant information (1).”
§ Unlocking electronic health records: a hybrid graph RAG approach to safe clinical AI for patient QA > Introduction
What the sources say
- Partly supportedcites [1] Asgari, 2024, Impact of electronic health record use on cognitive load and burnout among clinicians: narrative review, JMIR Med Inform sourceExperimental — accuracy not yet measured
In “Factors Impacting the Usability of EHR Systems” (page not available), the review says clinicians must expend more effort filtering large volumes of information and that EHR use can increase cognitive burden and lead to missed important information. “Disadvantages” (page not available) also describes substantial time spent obtaining information from medical records. These passages support the general concern, but do not specifically establish that reviewing current and historical admission notes has become increasingly time-consuming. (LLM, conf=0.84)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Notably, no responses were flagged as potentially unsafe by either evaluator (0/10 cases), addressing a primary concern with LLM applications in healthcare.”
§ Unlocking electronic health records: a hybrid graph RAG approach to safe clinical AI for patient QA > Results > Clinical expert evaluation
plainn = 10- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Vector embedding processing successfully transformed all 89 free-text documents (25 discharge summaries and 64 radiology reports) into searchable vector representations.”
§ Unlocking electronic health records: a hybrid graph RAG approach to safe clinical AI for patient QA > Results > Graph database implementation and statistics
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Overall Quality scores were consistently strong (4.30±1.00 and 4.20±0.75 for Evaluators 1 and 2, respectively).”
§ Unlocking electronic health records: a hybrid graph RAG approach to safe clinical AI for patient QA > Results > Clinical expert evaluation
boostedn = 10- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Attempts to retrieve multiple queries across all patients resulted in context overflow, as the input tokens exceeded the language model’s processing capacity (128 k tokens for GPT-4o-mini).”
§ Unlocking electronic health records: a hybrid graph RAG approach to safe clinical AI for patient QA > Results > Error analysis and failure modes
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
22 more claims
Create a free account to see all 67 claims and to verify the 3 references still open.
- It may state two separate claims as one. 29
- Probably not a substantial claim. 15
- Borderline: one of the tests for a substantial claim is unclear. 1
Citations
Cites
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025 · cited 1×
“Research by Zubiaga and others highlights that without access to external veridical knowledge, LLMs are prone to “hallucinations” generating plausible but factually incorrect information (7, 8, 16, 17).”
Large language models encode clinical knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2023) · Nature · doi:10.1038/s41586-023-06291-2 · Cited by 4,083
MIMIC-IV, a freely accessible electronic health record dataset
Johnson, A. E. W., Bulgarelli, L., Shen, L., Gayles, A., Shammout, A., Horng, S., Pollard, T. J., Hao, S., Moody, B., Gow, B., et al. (2023) · Scientific Data · doi:10.1038/s41597-022-01899-x · Cited by 3,401 · cited 1×
“The pipeline begins with query processing, where natural language input from clinicians undergoes initial analysis to identify key entities, temporal constraints, and query intent.”
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-T., Rocktäschel, T., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.11401 · Cited by 3,101
Self-citationAnalyzing and Interpreting Data From Likert-Type Scales
Sullivan, G. M., & Artino, A. R. (2013) · Journal of Graduate Medical Education · doi:10.4300/jgme-5-4-18 · Cited by 3,044 · cited 1×
“This model is distinct from the lighter model used for query translation, ensuring the final response prioritizes reasoning capabilities and safety.”
Malkov, Y. A., & Yashunin, D. A. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2889473 · Cited by 1,904 · cited 1×
“The schema represents eight primary node types, capturing distinct clinical entities as detailed in Table 2.”
Mining electronic health records: towards better research applications and clinical care
Jensen, P. B., Jensen, L. J., & Brunak, S. (2012) · Nature Reviews Genetics · doi:10.1038/nrg3208 · Cited by 1,680
Evaluating Large Language Models Trained on Code
Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. D. O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.03374 · Cited by 1,436
The future landscape of large language models in medicine
Clusmann, J., Kolbinger, F. R., Muti, H. S., Carrero, Z. I., Eckardt, J.-N., Laleh, N. G., Löffler, C. M. L., Schwarzkopf, S.-C., Unger, M., Veldhuizen, G. P., et al. (2023) · Communications Medicine · doi:10.1038/s43856-023-00370-1 · Cited by 1,045 · cited 2×
“Recent advances in large language models (LLMs) have demonstrated transformative potential for natural language processing in healthcare (5, 6).”
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question AnsweringPreprint
Yasunaga, M., Ren, H., Bosselut, A., Liang, P., & Leskovec, J. (2021) · North American Chapter of the Association for Computational Linguistics · doi:10.48550/arxiv.2104.06378 · Cited by 939
Cited by
Monika, W., Dewi, D. A., Nasution, A. H., Onan, A., & Murakami, Y. (2026) · Information · doi:10.3390/info17070660 · Cited by 1
“Recent studies include hybrid medical RAG, knowledge-graph medical QA, clinical decision support, electronic health records, and evidence-based hallucination reduction [28,32,52,61,63,90,107,109].”
Zhao, Y., Miao, Y., Guo, R., Luo, Y., Wang, H., & Wu, Y. X. (2026) · Journal of Medical Internet Research · doi:10.2196/90046 · Cited by 2
Large Language Models and the return of knowledge engineering
Bellazzi, R. (2026) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2026.106461
Wang, X., Ren, H., Wang, X., Han, Z.-R., & Qin, P.-W. (2026) · International Symposium on Bioinformatics and Computational Biology (BCB) · doi:10.1145/3820664.3820702
“However, for precise, multi-step relational queries crucial to TCM clinical reasoning—such as identifying the molecular targets of a formula by examining its component herbs—pure vector retrieval methods face challenges [3].”
Riad, A. K. I., Barek, M. A., Shahriar, H., Francia, G., Ahamed, S. I., El-Sheikh, E., & Rawajfih, Y. (2026) · IEEE International Conference on Digital Health (ICDH) · doi:10.1109/icdh72779.2026.00012 · Cited by 1
“Consequently, ensuring end-to-end privacy preservation is essential for safe deployment in clinical environments [8].”
Metadata
- Authors
- Thio, S., Lewis, M., Denaxas, S., & Dobson, R. J. B.
- Affiliations
- Engineering and Physical Sciences Research Council (GB)
- University College London (GB)
- National and Kapodistrian University of Athens (GR)
- University of London (GB)
- Corresponding author
- Thio, Samuel
- Venue
- Frontiers in Digital Health
- Publisher
- Frontiers Media SA
- Published
- 2026-03-11
- Volume
- 8
- Pages
- 1780700-1780700
- ISSN
- 2673-253X (ISSN-L)
- PMC
- PMC13014479
- OpenAlex
- W7135012900
- Semantic Scholar
- 71172130332d3a3d60e5073beb294bf14429fcdb
- Cited by
- 6
- References
- 17
- Citations by year
- 2026: 6
- FWCI
- 11.72
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Digital Health (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Research Portal (King's College London) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- UK Research and Innovation
- National Institute for Health and Care Research
- University College London
- NIHR Maudsley Biomedical Research Centre
- Engineering and Physical Sciences Research Council (EP/Y035216/1)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Electronic Health Records Systems
- Keywords
- electronic health records, graph-based retrieval-augmented generation, medical information retrieval, large language models, hallucination mitigation, vector embeddings, semantic search, MIMIC-IV
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Unlocking electronic health records: a hybrid graph RAG approach to safe clinical AI for patient QA. https://app.cochat.ai/papers/10.3389/fdgth.2026.1780700
- The paper
- Thio, S., Lewis, M., Denaxas, S., & Dobson, R. J. B. (2026). Unlocking electronic health records: a hybrid graph RAG approach to safe clinical AI for patient QA. Frontiers in Digital Health. https://doi.org/10.3389/fdgth.2026.1780700
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.