Электронный каталог

Статья

Shchetinin, Eu.Yu.
Methods for Developing and Implementing Large Languagemodels in Healthcare: Challenges and Prospects in Russia / Eu.Yu.Shchetinin, L.A.Sevastianov, [a.o.]. – Text : electronic // Discrete and Continuous Models and Applied Computational Science. – 2025. – Vol. 33, No. 3. – P. 327-344. – URL: https://doi.org/10.22363/2658-4670-2025-33-3-327-344. – Bibliogr.: 37.

Large language models (LLMs) are transforming healthcare by enabling the analysis of clinical texts,supporting diagnostics, and facilitating decision-making. This systematic review examines the evolution of LLMsfrom recurrent neural networks (RNNs) to transformer-based and multimodal architectures (e.g., BioBERT, Med-PaLM), with a focus on their application in medical practice and challenges in Russia. Based on 40 peer-reviewedarticles from Scopus, PubMed, and other reliable sources (2019–2025), LLMs demonstrate high performance (e.g.,Med-PaLM: F1-score 0.88 for binary pneumonia classification on MIMIC-CXR; Flamingo-CXR: 77.7% preferencefor in/outpatient X-ray re-ports). However, limitations include data scarcity, interpretability challenges, andprivacy concerns. An adaptation of the Mixture of Experts (MoE) architecture for rare disease diagnostics andautomated radiology report generation achieved promising results on synthetic datasets. Challenges in Russiainclude limited annotated data and compliance with Federal Law No. 152-FZ. LLMs enhance clinical workflowsby automating routine tasks, such as report generation and patient triage, with advanced models like KARGENimproving radiology report quality. Russia’s focus on AI-driven healthcare aligns with global trends, yet linguisticand infrastructural barriers necessitate tailored solutions. Developing robust validation frameworks for LLMswill ensure their reliability in diverse clinical scenarios. Collaborative efforts with international AI researchcommunities could accelerate Russia’s adoption of advanced medical AI technologies, particularly in radiologyautomation. Prospects involve integrating LLMs with healthcare systems and developing specialized models forRussian medical contexts. This study provides a foundation for advancing AI-driven healthcare in Russia



Спец.(статьи,препринты) = Ц 849 - Искусственный интеллект. Теория и практика
Спец.(статьи,препринты) = С 325.1а - Нейронные сети и клеточные автоматы
ОИЯИ = ОИЯИ (JINR)2025