Leveraging Medical Knowledge Graphs Into Large Language Models for Diagnosis Prediction: Design and Application Study
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Background: Electronic health records (EHRs) and routine documentation practices play a vital role in patients’ daily care, providing a holistic record of health, diagnoses, and treatment. However, complex and verbose EHR narratives can overwhelm health care providers, increasing the risk of diagnostic inaccuracies. While large language models (LLMs) have showcased their potential in diverse language tasks, their application in health care must prioritize the minimization of diagnostic errors and the prevention of patient harm. Integrating knowledge graphs (KGs) into LLMs offers a promising approach because structured knowledge from KGs could enhance LLMs’ diagnostic reasoning by providing contextually relevant medical information. Objective: This study introduces DR.KNOWS (Diagnostic Reasoning Knowledge Graph System), a model that integrates Unified Medical Language System–based KGs with LLMs to improve diagnostic predictions from EHR data by retrieving contextually relevant paths aligned with patient-specific information. Methods: DR.KNOWS combines a stack graph isomorphism network for node embedding with an attention-based path ranker to identify and rank knowledge paths relevant to a patient’s clinical context. We evaluated DR.KNOWS on 2 real-world EHR datasets from different geographic locations, comparing its performance to baseline models, including QuickUMLS and standard LLMs (Text-to-Text Transfer Transformer and ChatGPT). To assess diagnostic reasoning quality, we designed and implemented a human evaluation framework grounded in clinical safety metrics. Results: DR.KNOWS demonstrated notable improvements over baseline models, showing higher accuracy in extracting diagnostic concepts and enhanced diagnostic prediction metrics. Prompt-based fine-tuning of Text-to-Text Transfer Transformer with DR.KNOWS knowledge paths achieved the highest ROUGE-L (Recall-Oriented Understudy for Gisting Evaluation–Longest Common Subsequence) and concept unique identifier F1-scores, highlighting the benefits of KG integration. Human evaluators found the diagnostic rationales of DR.KNOWS to be aligned strongly with correct clinical reasoning, indicating improved abstraction and reasoning. Recognized limitations include potential biases within the KG data, which we addressed by emphasizing case-specific path selection and proposing future bias-mitigation strategies. Conclusions: DR.KNOWS offers a robust approach for enhancing diagnostic accuracy and reasoning by integrating structured KG knowledge into LLM-based clinical workflows. Although further work is required to address KG biases and extend generalizability, DR.KNOWS represents progress toward trustworthy artificial intelligence–driven clinical decision support, with a human evaluation framework focused on diagnostic safety and alignment with clinical standards.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
GPT-3: Its Nature, Scope, Limits, and Consequences
Floridi, L., & Chiriatti, M. (2020) · Minds and Machines · doi:10.1007/s11023-020-09548-1 · Cited by 2,519
Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
Conneau, A., Kiela, D., Schwenk, H., Barrault, L., & Bordes, A. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1070 · Cited by 2,049
Savova, G. K., Masanz, J. J., Ogren, P. V., Zheng, J., Sohn, S., Kipper-Schuler, K. C., & Chute, C. G. (2010) · Journal of the American Medical Informatics Association · doi:10.1136/jamia.2009.001560 · Cited by 1,967 · cited 1×
“The example patient presents with medical conditions of fever, cough and sepsis, which are the concepts recognized by medical concept extractors (Clinical Text Analysis and Knowledge Extraction System [31] and QuickUMLS [32]) and the starting concepts for multihop reasoning.”
Unifying Large Language Models and Knowledge Graphs: A Roadmap
Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., & Wu, X. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3352100 · Cited by 1,376 · cited 2×
“Our work is motivated not only by the potential in the NLP field of augmenting LLMs with KGs [20] but also by the theoretical exploration in medical education and psychology research, shedding light on the diagnostic decision-making process used by clinicians.”
Educational Strategies to Promote Clinical Diagnostic Reasoning
Bowen, J. L. (2006) · New England Journal of Medicine · doi:10.1056/nejmra054782 · Cited by 931 · cited 1×
“Forming a diagnostic decision requires the examination of patient data, retrieving encapsulated medical knowledge, and the formulation and testing of the diagnostic hypothesis, which is also known as clinical diagnostic reasoning [21,22].”
Patient Safety Issues From Information Overload in Electronic Medical Records
Nijor, S., Rallis, G., Lad, N., & Gokcen, E. (2022) · Journal of Patient Safety · doi:10.1097/pts.0000000000001002 · Cited by 137
Demystifying Prompts in Language Models via Perplexity Estimation
Gonen, H., Iyer, S., Blevins, T., Smith, N., & Zettlemoyer, L. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.679 · Cited by 109
The opportunities and pitfalls of ChatGPT in clinical and translational medicine
Baumgartner, C. (2023) · Clinical and Translational Medicine · doi:10.1002/ctm2.1206 · Cited by 103
Diagnostic Failure: A Cognitive and Affective Approach: (448242006-001)
Croskerry, P. (2005) · PsycEXTRA Dataset · doi:10.1037/e448242006-001 · Cited by 97 · cited 1×
“Physicians often skip sections of lengthy and repetitive notes and rely on decisional shortcuts (ie, decisional heuristics) that can contribute to diagnostic errors [6].”
Length and redundancy of outpatient progress notes across a decade at an academic medical center
Rule, A., Bedrick, S., Chiang, M. F., & Hribar, M. R. (2021) · JAMA Network Open · doi:10.1001/jamanetworkopen.2021.15334 · Cited by 90
Cited by
Large language models in healthcare and medical domain: A review
Nazi, Z. A., & Peng, W. (2024) · Informatics · doi:10.3390/informatics11030057 · Cited by 415
Retrieval augmented generation for large language models in healthcare: A systematic review
Amugongo, L. M., Mascheroni, P., Brooks, S., Doering, S., & Seidel, J. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000877 · Cited by 267
A Survey of Large Language Models in Medicine: Progress, Application, and Challenge
Zhou, H., Liu, F., Gu, B., Zou, X., Huang, J., Wu, J., Li, Y., Chen, S. S., Zhou, P., Liu, J., et al. (2023) · arXiv · doi:10.48550/arxiv.2311.05112 · Cited by 240
Application of large language models in medicine
Liu, F., Zhou, H., Gu, B., Zou, X., Huang, J., Wu, J., Li, Y., Chen, S. S., Hua, Y., Zhou, P., et al. (2025) · Nature Reviews Bioengineering · doi:10.1038/s44222-025-00279-5 · Cited by 94
Lv, J., Xu, Y., Jiang, M., Lv, Y., Sun, J., Lu, J., Wang, L., & Wang, H. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaf109 · Cited by 12
Anbukkarasi, S., Hemalatha, S., Balakrishnan, A., Varadhaganapathy, S., & Easwaramoorthy, S. V. (2026) · Scientific reports · doi:10.1038/s41598-026-47146-w · Cited by 1
“The incorporation of knowledge graph data into large language models has resulted in diagnostic accuracy and clinical prediction tasks improvements, which is a proof of the structured domain knowledge utility in generalization enhancement 14 .”
Metadata
- Authors
- Gao, Y., Li, R., Croxford, E., Caskey, J., Patterson, B. W., Churpek, M., Miller, T., Dligach, D., & Afshar, M.
- Venue
- JMIR AI
- Publisher
- JMIR Publications Inc.
- Published
- 2025-02-24
- Volume
- 4
- Pages
- e58670
- ISSN
- 2817-1705 (ISSN-L)
- OpenAlex
- W4404138521
- Cited by
- 114
- References
- 14
- FWCI
- 16.82
- Type
- journal article
- Language
- en
- Open access
- diamond
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.
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
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.