EUVIMEDEUVIMED entdecken
Scoping Review

Dependability of Large Language Models in Cardiovascular Medicine: A Scoping Review

Ying Ying Jia, Lin Yan Pang, Ming Ming Bi, Xiang Lu Yang, Jian Ping Song

Journal of Cardiothoracic and Vascular Anesthesia · 2025

DOI: 10.1053/j.jvca.2025.07.026 ↗

Kurz gefasst

Scoping Review in der Zeitschrift Journal of Cardiothoracic and Vascular Anesthesia, 2025. Verfasst von Ying Ying Jia und 4 weiteren Autor:innen. Beteiligte Einrichtung: Nursing Department, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China; School of Medicine, Zhejiang Universit…. Hauptthemen laut MEDLINE: Cardiology, Cardiovascular Diseases, Language. Die Arbeit nennt 49 Literaturangaben. Gefördert von: Zhejiang Provincial Health Commission.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: The adoption of large language models (LLMs) in both clinical and consumer healthcare settings has surged exponentially. However, there remains limited evidence on their reliability and impact in cardiovascular practice. OBJECTIVES: This scoping review was designed to consolidate the existing biomedical literature on applicability, reliability, and quality improvement strategies for the integration of LLMs into the cardiovascular domain. Following Cochrane methodology and Preferred Reporting Items for Systematic Reviews and Meta-analyses guidelines, three electronic databases (PubMed, Web of Science, and Embase) were systematically searched to identify pertinent studies published between August 2020 and February 2025. Articles addressing the development, implementation, and assessment of LLMs in cardiovascular medicine were selected for comprehensive analysis. RESULTS: Twenty-five eligible publications evaluated the performance of LLMs in responding to cardiology-related questions, encompassing parameters such as accuracy, response latency, indirectness, completeness, and so on. The assessment methodology varied considerably across studies. LLMs demonstrated potential utility in cardiovascular decision-making, myocarditis management, cardiac arrest diagnosis and treatment, and image differentiation. CONCLUSIONS: Although some LLM-generated responses to cardiovascular-related questions exhibit acceptable levels of quality, significant drawbacks persist. These include verbosity, inaccuracies, occasional misinformation, inconsistent outputs to identical questions, bias, and poor reproducibility. Overall, this work highlights the urgent need for continued refinement and validation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CardiologyCardiovascular DiseasesLanguageHumansLarge Language Models

Stichwörter der Autor:innen

ChatGPTcardiovasculargenerative artificial intelligencelarge language modelsreliabilitytrustworthiness

Autor:innen und Institutionen

  • Nursing Department, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China; School of Medicine, Zhejiang University, Hangzhou, China; West China School of Medicine, Chengdu, China.
  • School of Nursing, Lan Zhou University, Lanzhou, China.
  • Nursing Department, Jiaxing University Affiliated Xin'an International Hospital, Jiaxing, China.
  • Nursing Department, Zhejiang University of Traditional Chinese Medicine, Hangzhou, China.
  • Nursing Department, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China. Electronic address: zrxwk1@zju.edu.cn.

Förderung

  • Zhejiang Provincial Health Commission

Zitieren

APA

Jia, Y. Y., Pang, L. Y., Bi, M. M., Yang, X. L., & Song, J. P. (2025). Dependability of Large Language Models in Cardiovascular Medicine: A Scoping Review. Journal of Cardiothoracic and Vascular Anesthesia. https://doi.org/10.1053/j.jvca.2025.07.026

Vancouver

Jia YY, Pang LY, Bi MM, Yang XL, Song JP. Dependability of Large Language Models in Cardiovascular Medicine: A Scoping Review. Journal of Cardiothoracic and Vascular Anesthesia. 2025. doi:10.1053/j.jvca.2025.07.026

BibTeX
@article{Jia2025,
  author = {Jia, Ying Ying and Pang, Lin Yan and Bi, Ming Ming and Yang, Xiang Lu and Song, Jian Ping},
  title = {Dependability of Large Language Models in Cardiovascular Medicine: A Scoping Review},
  journal = {Journal of Cardiothoracic and Vascular Anesthesia},
  year = {2025},
  doi = {10.1053/j.jvca.2025.07.026}
}
Kostenlos starten →