Development of a liver disease–specific large language model chat interface using retrieval-augmented generation
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Background and Aims: Large language models (LLMs) have significant capabilities in clinical information processing tasks. Commercially available LLMs, however, are not optimized for clinical uses and are prone to generating hallucinatory information. Retrieval-augmented generation (RAG) is an enterprise architecture that allows the embedding of customized data into LLMs. This approach “specializes” the LLMs and is thought to reduce hallucinations. Approach and Results: We developed “LiVersa,” a liver disease–specific LLM, by using our institution’s protected health information-complaint text embedding and LLM platform, “Versa.” We conducted RAG on 30 publicly available American Association for the Study of Liver Diseases guidance documents to be incorporated into LiVersa. We evaluated LiVersa’s performance by conducting 2 rounds of testing. First, we compared LiVersa’s outputs versus those of trainees from a previously published knowledge assessment. LiVersa answered all 10 questions correctly. Second, we asked 15 hepatologists to evaluate the outputs of 10 hepatology topic questions generated by LiVersa, OpenAI’s ChatGPT 4, and Meta’s Large Language Model Meta AI 2. LiVersa’s outputs were more accurate but were rated less comprehensive and safe compared to those of ChatGPT 4. Results: We evaluated LiVersa’s performance by conducting 2 rounds of testing. First, we compared LiVersa’s outputs versus those of trainees from a previously published knowledge assessment. LiVersa answered all 10 questions correctly. Second, we asked 15 hepatologists to evaluate the outputs of 10 hepatology topic questions generated by LiVersa, OpenAI’s ChatGPT 4, and Meta’s Large Language Model Meta AI 2. LiVersa’s outputs were more accurate but were rated less comprehensive and safe compared to those of ChatGPT 4. Conclusions: In this demonstration, we built disease-specific and protected health information-compliant LLMs using RAG. While LiVersa demonstrated higher accuracy in answering questions related to hepatology, there were some deficiencies due to limitations set by the number of documents used for RAG. LiVersa will likely require further refinement before potential live deployment. The LiVersa prototype, however, is a proof of concept for utilizing RAG to customize LLMs for clinical use cases.
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
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
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 2×
“[6,7] Despite these limitations, LLMs are thought to have significant potential in biomedical and clinical applications.”
Terrault, N. A., Lok, A. S. F., McMahon, B. J., Chang, K., Hwang, J. P., Jonas, M. M., Brown, R. S., Bzowej, N. H., & Wong, J. B. (2018) · Hepatology · doi:10.1002/hep.29800 · Cited by 4,306
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. (2022) · arXiv · doi:10.48550/arxiv.2212.13138 · Cited by 4,083
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 · cited 1×
“We then sent an anonymous survey to a convenience sample of hepatologists within and outside our institution to rate the outputs on a 1 to 5 Likert Scale (from least to most) by the following dimensions that were previously used for LLM evaluation: [ 25,26 ] 1.”
Rinella, M. E., Neuschwander-Tetri, B. A., Siddiqui, M. S., Abdelmalek, M. F., Caldwell, S., Barb, D., Kleiner, D. E., & Loomba, R. (2023) · Hepatology · doi:10.1097/hep.0000000000000323 · Cited by 2,667
AASLD Practice Guidance on prevention, diagnosis, and treatment of hepatocellular carcinoma
Singal, A. G., Llovet, J. M., Yarchoan, M., Mehta, N., Heimbach, J. K., Dawson, L. A., Jou, J. H., Kulik, L. M., Agopian, V. G., Marrero, J. A., et al. (2023) · Hepatology · doi:10.1097/hep.0000000000000466 · Cited by 2,052 · cited 1×
“[29,30] LiVersa gave the wrong justification for HCC surveillance in this case simply because the 2018 version was not available to it and “ restrictions ” placed by curated RAG data set.”
Large language models are zero-shot reasoners
Kojima, T., Gu, S. (., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1613 · Cited by 2,013
Large Language Models are Zero-Shot Reasoners
Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022) · arXiv · doi:10.48550/arxiv.2205.11916 · Cited by 2,013
Martin, P., DiMartini, A., Feng, S., Brown, R., & Fallon, M. (2014) · Hepatology · doi:10.1002/hep.26972 · Cited by 1,045
Cited by
Ethical and regulatory challenges of large language models in medicine
Ong, J. C. L., Chang, S. Y.-H., William, W., Butte, A. J., Shah, N. H., Chew, L. S. T., Liu, N., Doshi-Velez, F., Lu, W., Savulescu, J., et al. (2024) · The Lancet Digital Health · doi:10.1016/s2589-7500(24)00061-x · Cited by 342
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
Kresevic, S., Giuffrè, M., Ajcevic, M., Accardo, A., Crocè, L. S., & Shung, D. L. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01091-y · Cited by 207
Retrieval-Augmented Generation (RAG) in Healthcare: A Comprehensive Review
Neha, F., Bhati, D., & Shukla, D. K. (2025) · AI · doi:10.3390/ai6090226 · Cited by 117
“Ge et al. developed a liver disease-specific LLM using RAG within a Protected Health Information (PHI)-compliant system [50].”
Ng, K. K. Y., Matsuba, I., & Zhang, P. C. (2025) · NEJM AI · doi:10.1056/aira2400380 · Cited by 107
Metadata
- Authors
- Ge, J., Sun, S., Owens, J., Galvez, V., Gologorskaya, O., Lai, J. C., Pletcher, M. J., & Lai, K.
- Venue
- Hepatology
- Published
- 2024-03-07
- Volume
- 80
- Issue
- 5
- Pages
- 1158-1168
- ISSN
- 0270-9139 (ISSN-L)
- OpenAlex
- W4392544551
- Cited by
- 178
- References
- 23
- FWCI
- 14.27
- Type
- journal article
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Development of a liver disease–specific large language model chat interface using retrieval-augmented generation. https://app.cochat.ai/papers/10.1097/hep.0000000000000834
- The paper
- Ge, J., Sun, S., Owens, J., Galvez, V., Gologorskaya, O., Lai, J. C., Pletcher, M. J., & Lai, K. (2024). Development of a liver disease–specific large language model chat interface using retrieval-augmented generation. Hepatology. https://doi.org/10.1097/hep.0000000000000834
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.