EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Pre‐Imaging Clinical Factors Associated With Cardiac MR Image Quality Using Large Language Model‐Enabled Data Extraction

Hong Yu iD, Masha Bondarenko iD, Ali Nowroozi iD, Yoo Jin Lee iD, Adrian Serapio iD, Punita Kaveti iD, Jae Ho Sohn iD

Journal of Magnetic Resonance Imaging · 2026-08 · 64 (2) · 565-578

DOI: 10.1002/jmri.70336 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, online erschienen am 19.04.2026. Verfasst von Hong Yu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou, China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Heart, Image Interpretation, Computer-Assisted, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NHLBI NIH HHS, NCATS NIH HHS, National Heart, Lung, and Blood Institute (NHLBI), NIH.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Poor cardiac MR image quality can prompt repeat examinations and hinder clinical decision‐making.

Purpose

To evaluate whether pre‐imaging clinical information, extracted using a large language model (LLM), is independently associated with cardiac MR image quality. Study Type Retrospective. Population 1006 adults undergoing clinical cardiac MR examinations. Field Strength/Sequence 1.5 T and 3 T scanners with cine, black blood, MR angiogram, or late gadolinium enhancement protocols. Assessment Image quality was categorized per study as excellent, slightly limited, severely limited, or nondiagnostic using institutional reporting conventions finalized by radiologists and cardiologists. A HIPAA‐compliant LLM assigned image quality labels based on radiology reports through an iteratively refined prompt, with reliability confirmed by two radiologists. Labels were binarized as Good (excellent and slightly limited) versus Poor (severely limited and nondiagnostic). A repeat‐imaging‐adjusted image quality label was used in a sensitivity analysis. Pre‐imaging clinical and patient variables were extracted from electronic health records. Associations between variables and image quality labels were investigated. Statistical Tests Cohen's kappa (κ) for label agreement. Chi‐square and t‐tests for univariate analysis. Variance inflation factor (VIF) and multivariable logistic regression. Significance level: p < 0.05.

Results

Binarized image quality labels showed substantial agreement with interpreters' assessments for both the primary dataset (κ = 0.689) and the repeat‐adjusted dataset (κ = 0.879). There was no significant multicollinearity (VIF = 1.01–1.39). Cognitive and communication impairment (OR 1.81, 95% CI [1.30–2.54], p < 0.001) and respiratory issues (1.57 [1.14–2.17], p = 0.006) were independently associated with poor image quality. These associations remained significant in the repeat‐adjusted sensitivity analysis (cognitive and communication impairment (OR 1.75, 95% CI [1.27–2.44], p < 0.001) and respiratory compromise (OR 1.37, 95% CI [1.04–1.82], p = 0.027)). Other clinical variables were not independently associated after adjustment. Data Conclusion Cognitive/communication impairment and respiratory compromise were independently associated with poor cardiac MR image quality. Level of Evidence 3. Technical Efficacy Stage 2.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingHeartImage Interpretation, Computer-AssistedImage Processing, Computer-AssistedHumansLarge Language ModelsFemaleReproducibility of ResultsMaleRetrospective StudiesMiddle AgedAgedAdultSensitivity and SpecificityGadoliniumMagnetic Resonance Imaging, Cine

Stichwörter der Autor:innen

artificial intelligencecardiac MRimage qualitylarge language model

Substanzen

Gadolinium

Autor:innen und Institutionen

  • Department of Radiology, Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou, China.
  • Department of Radiology and Biomedical Imaging, University of California, San Francisco, California, USA.
  • Division of Cardiology and Department of Medicine, University of California, San Francisco, San Francisco, California, USA.

ORCID-Profile: Hong Yu, Masha Bondarenko, Ali Nowroozi, Yoo Jin Lee, Adrian Serapio, Punita Kaveti, Jae Ho Sohn

Förderung

  • NHLBI NIH HHS
  • NCATS NIH HHS
  • National Heart, Lung, and Blood Institute (NHLBI), NIH
  • National Center for Advancing Translational Sciences
  • National Heart, Lung, and Blood Institute

Zitieren

APA

Yu, H., Bondarenko, M., Nowroozi, A., Lee, Y. J., Serapio, A., Kaveti, P., & Sohn, J. H. (2026). Pre‐Imaging Clinical Factors Associated With Cardiac MR Image Quality Using Large Language Model‐Enabled Data Extraction. Journal of Magnetic Resonance Imaging, 64(2), 565-578. https://doi.org/10.1002/jmri.70336

Vancouver

Yu H, Bondarenko M, Nowroozi A, Lee YJ, Serapio A, Kaveti P, et al. Pre‐Imaging Clinical Factors Associated With Cardiac MR Image Quality Using Large Language Model‐Enabled Data Extraction. Journal of Magnetic Resonance Imaging. 2026;64(2):565-578. doi:10.1002/jmri.70336

BibTeX
@article{Yu2026,
  author = {Yu, Hong and Bondarenko, Masha and Nowroozi, Ali and Lee, Yoo Jin and Serapio, Adrian and Kaveti, Punita and Sohn, Jae Ho},
  title = {Pre‐Imaging Clinical Factors Associated With Cardiac MR Image Quality Using Large Language Model‐Enabled Data Extraction},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2026},
  volume = {64},
  number = {2},
  pages = {565--578},
  doi = {10.1002/jmri.70336}
}
Kostenlos starten →