Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.

Large Language Models Are Poor Medical Coders — Benchmarking of Medical Code Querying

Open access

Abstract

BACKGROUND Large language models (LLMs) have attracted significant interest for automated clinical coding. However, early data show that LLMs are highly error-prone when mapping medical codes. We sought to quantify and benchmark LLM medical code querying errors across several available LLMs.

Overview

Integrity signals

Registry

Crossref · 10.1056/aidbp2300040

Cites

30 of 30 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 14 references

Research works printed but not linked: 7

  1. American Medical Association. CPT® overview and code approval. 2023 (https://www.ama-assn.org/practice-management/cpt/cpt-overview-and-code-approval).
  2. Open AI. GPT-4 technical report. March 15 2023 (https://arxiv.org/abs/2303.08774). Preprint. · arXiv
  3. Anil R Borgeaud S Wu Y et al. Gemini: a family of highly capable multimodal models. December 19 2023 (https://arxiv.org/abs/2312.11805). Preprint. · arXiv
  4. Zhang T Kishore V Wu F Weinberger KQ Artzi Y. BERTscore: evaluating text generation with BERT. 2019 (https://arxiv.org/abs/1904.09675). Preprint. · arXiv
  5. Nogueira R Jiang Z Lin J. Investigating the limitations of transformers with simple arithmetic tasks. April 12 2021 (https://arxiv.org/abs/2102.13019). Preprint. · arXiv
  6. Yang K Liu J Wu J et al. If LLM is the wizard then code is the wand: a survey on how code empowers large language models to serve as intelligent agents. January 8 2024 (https://arxiv.org/abs/2401.00812). Preprint. · arXiv
  7. Lu P Peng B Cheng H et al. Chameleon: plug-and-play compositional reasoning with large language models. October 31 2023 (https://arxiv.org/abs/2304.09842). Preprint. · arXiv

Cited by

See all 156

Metadata

Authors
Soroush, A., Glicksberg, B. S., Zimlichman, E., Barash, Y., Freeman, R., Charney, A. W., Nadkarni, G. N., & Klang, E.
Affiliations
  • Icahn School of Medicine at Mount Sinai (US)
  • Tel Aviv University (IL)
  • Mount Sinai Health System (US)
Venue
NEJM AI
Published
2024-04-25
Volume
1
Issue
5
Pages
AIdbp2300040-AIdbp2300040
ISSN
2836-9386 (ISSN-L)
OpenAlex
W4394943312
Cited by
137
References
14
Citations by year
2026: 45 · 2025: 64 · 2024: 28
FWCI
41.86
Type
journal article
Language
en
Open access
Locations
  • NEJM AI (publishedVersion)
  • PubMed (publishedVersion)
Funders
  • AGA Research Foundation
  • National Institutes of Health
Topics
  • Health Sciences › Health Professions › Health Information Management › Medical Coding and Health Information
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
large language models, ICD-10-CM, benchmarking, natural language processing

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: Large Language Models Are Poor Medical Coders — Benchmarking of Medical Code Querying. https://app.cochat.ai/papers/10.1056/aidbp2300040
The paper
Soroush, A., Glicksberg, B. S., Zimlichman, E., Barash, Y., Freeman, R., Charney, A. W., Nadkarni, G. N., & Klang, E. (2024). Large Language Models Are Poor Medical Coders — Benchmarking of Medical Code Querying. NEJM AI. https://doi.org/10.1056/aidbp2300040

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.