CoChat

A pilot study on the efficacy of GPT-4 in providing orthopedic treatment recommendations from MRI reports

Open access

The DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.

Abstract

Large language models (LLMs) have shown potential in various applications, including clinical practice. However, their accuracy and utility in providing treatment recommendations for orthopedic conditions remain to be investigated. Thus, this pilot study aims to evaluate the validity of treatment recommendations generated by GPT-4 for common knee and shoulder orthopedic conditions using anonymized clinical MRI reports. A retrospective analysis was conducted using 20 anonymized clinical MRI reports, with varying severity and complexity. Treatment recommendations were elicited from GPT-4 and evaluated by two board-certified specialty-trained senior orthopedic surgeons. Their evaluation focused on semiquantitative gradings of accuracy and clinical utility and potential limitations of the LLM-generated recommendations. GPT-4 provided treatment recommendations for 20 patients (mean age, 50 years ± 19 [standard deviation]; 12 men) with acute and chronic knee and shoulder conditions. The LLM produced largely accurate and clinically useful recommendations. However, limited awareness of a patient’s overall situation, a tendency to incorrectly appreciate treatment urgency, and largely schematic and unspecific treatment recommendations were observed and may reduce its clinical usefulness. In conclusion, LLM-based treatment recommendations are largely adequate and not prone to ‘hallucinations’, yet inadequate in particular situations. Critical guidance by healthcare professionals is obligatory, and independent use by patients is discouraged, given the dependency on precise data input.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-023-47500-2

Cites

29 of 29 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Workflow of the Artificial Intelligence-powered MRI-to-treatment recommendation pipeline. GPT-4, denoted as the AI icon, was prompted three times to translate the MRI report, provide general treatment recommendations, and prioritize its recommendations. Two experienced orthopedic surgeons rated the patient-specific treatment recommendations.
Figure 1 Workflow of the Artificial Intelligence-powered MRI-to-treatment recommendation pipeline. GPT-4, denoted as the AI icon, was prompted three times to translate the MRI report, provide general treatment recommendations, and prioritize its recommendations. Two experienced orthopedic surgeons rated the patient-specific treatment recommendations.CC BY · PubMed Central
Figure 2 Multidimensional ratings of the treatment recommendations provided by GPT-4. In a consensus meeting, two experienced orthopedic surgeons evaluated the treatment recommendations for various knee and shoulder conditions derived from clinical MRI reports. Ratings were based on five-item Likert scales, and counts were provided only for selected answers.
Figure 2 Multidimensional ratings of the treatment recommendations provided by GPT-4. In a consensus meeting, two experienced orthopedic surgeons evaluated the treatment recommendations for various knee and shoulder conditions derived from clinical MRI reports. Ratings were based on five-item Likert scales, and counts were provided only for selected answers.CC BY · PubMed Central
Figure 3 Representative knee joint MR images of a patient with a joint infection, key MRI report findings, and specific treatment recommendations by GPT-4. Axial proton density-weighted fat-saturated image above the patella (upper image) and sagittal post-contrast T1-weighted fat-saturated image through the central femur diaphysis (lower image). Of all 20 MRI studies/reports and associated treatment recommendations, these treatment recommendations were rated lowest.
Figure 3 Representative knee joint MR images of a patient with a joint infection, key MRI report findings, and specific treatment recommendations by GPT-4. Axial proton density-weighted fat-saturated image above the patella (upper image) and sagittal post-contrast T1-weighted fat-saturated image through the central femur diaphysis (lower image). Of all 20 MRI studies/reports and associated treatment recommendations, these treatment recommendations were rated lowest.CC BY · PubMed Central
Figure 4 Representative shoulder joint MR images of a patient after re-dislocation, key MRI report findings, and specific treatment recommendations by GPT-4. Axial and parasagittal proton density-weighted fat-saturated images through the humeral head and glenoid, respectively.
Figure 4 Representative shoulder joint MR images of a patient after re-dislocation, key MRI report findings, and specific treatment recommendations by GPT-4. Axial and parasagittal proton density-weighted fat-saturated images through the humeral head and glenoid, respectively.CC BY · PubMed Central

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Show all 29 references

Research works printed but not linked: 1

  1. Jiao, W., Wang, W., Huang, J., Wang, X. & Tu, Z. Is ChatGPT a good translator? Yes with GPT-4 as the engine. http://arxiv.org/abs/2301.08745 (2023) · arXiv

Cited by

See all 75

Metadata

Authors
Truhn, D., Weber, C. D., Braun, B. J., Bressem, K., Kather, J. N., Kuhl, C., & Nebelung, S.
Affiliations
  • Universitätsklinikum Aachen (DE)
  • University of Tübingen (DE)
  • Humboldt-Universität zu Berlin (DE)
  • University Hospital Heidelberg (DE)
Corresponding author
Nebelung, Sven
Venue
Scientific Reports
Published
2023-11-17
Volume
13
Issue
1
Pages
20159-20159
ISSN
2045-2322 (ISSN-L)
OpenAlex
W4388775426
Cited by
71
References
27
Citations by year
2026: 14 · 2025: 29 · 2024: 27 · 2023: 1
FWCI
2.84
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RWTH Publications (RWTH Aachen) (publishedVersion, other-oa)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • RWTH Publications (RWTH Aachen)
Funders
  • European Union’s Horizon Europe programme (ODELIA, 101057091, COMFORT, 101079894)
  • Deutsche Forschungsgemeinschaft (TR 1700/7-1, NE 2136/3-1)
  • Bundesministerium für Gesundheit (DEEP LIVER, ZMVI1-2520DAT111)
  • Max-Eder-Programme of the German Cancer Aid (#70113864)
  • German Federal Ministry of Education and Research (PEARL, 01KD2104C, CAMINO, 01EO2101, SWAG, 01KD2215A, TRANSFORM LIVER, 031L0312A, TANGERINE, 01KT2302 through ERA-NET Transcan)
  • Deutscher Akademischer Austauschdienst (SECAI, 57616814)
  • German Federal Joint Committee (Transplant.KI, 01VSF21048)
  • European Union’s Horizon Europe and innovation programme (ODELIA, 101057091, GENIAL, 101096312)
  • National Institute for Health and Care Research (NIHR, NIHR213331)
  • RWTH Aachen University
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
Keywords
GPT-4, large language models, shoulder disorders, MRI reports, clinical decision support, hallucinations, treatment urgency, clinical implementation of AI
MeSH terms
Humans, Language, Magnetic Resonance Imaging, Male, Medicine, Middle Aged, Musculoskeletal Diseases, Pilot Projects, Retrospective Studies

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: A pilot study on the efficacy of GPT-4 in providing orthopedic treatment recommendations from MRI reports. https://app.cochat.ai/papers/10.1038/s41598-023-47500-2
The paper
Truhn, D., Weber, C. D., Braun, B. J., Bressem, K., Kather, J. N., Kuhl, C., & Nebelung, S. (2023). A pilot study on the efficacy of GPT-4 in providing orthopedic treatment recommendations from MRI reports. Scientific Reports. https://doi.org/10.1038/s41598-023-47500-2

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.