Accuracy, Consistency, and Hallucination of Large Language Models When Analyzing Unstructured Clinical Notes in Electronic Medical Records
Open accessAbstract
Kathryn G. Burford, PhD; Nicole G. Itzkowitz, MSc; Ashley G. Ortega, BSc; Julien O. Teitler, PhD; Andrew G. Rundle, DrPH
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 5 · Cited by 80
Research works printed but not linked: 2
- Agrawal M, Hegselmann S, Lang H, et al. Large language models are few-shot clinical information extractors. arXiv. Preprint posted online May 25, 2022. doi:10.48550/arXiv.2205.12689 · DOI
- Zhang H, Jethani N, Jones S, et al. Evaluating large language models in extracting cognitive exam dates and scores. medRxiv. Preprint posted online February 13, 2024. doi:10.1101/2023.07.10.23292373 · DOI
- Authors
- Shah, S. V.
- Affiliations
- University of Chicago (US)
- Corresponding author
- Shah, Savyasachi V.
- Venue
- JAMA Network Open
- Publisher
- American Medical Association (AMA)
- Published
- 2024-08-13
- Volume
- 7
- Issue
- 8
- Pages
- e2425953
- ISSN
- 2574-3805 (ISSN-L)
- OpenAlex
- W4401542967
- Cited by
- 80
- References
- 5
- Citations by year
- 2026: 46 · 2025: 33 · 2024: 1
- FWCI
- 11.81
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- JAMA Network Open (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Biomedical Text Mining and Ontologies
- Keywords
- large language models, hallucinations, clinical notes, electronic health records, clinical text, natural language processing, clinical text mining, model accuracy, consistency
- MeSH terms
- Humans, Natural Language Processing, Electronic Health Records
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
