Large language models for clinical artificial intelligence in healthcare a systematic review
Большие языковые модели для клинического искусственного интеллекта в здравоохранении: систематический обзор
2026-01-28
SCID: 54.1/trdrynf9
Discuss with AI
clinical artificial intelligencehealthcarelarge language modelsmultimodal large language modelsretrieval-augmented generation
Figures from the paper
Abstract (AI)
Abstract Large Language Models (LLMs) have demonstrated the capacity to process, reason, and generate extensive volumes of data, providing a novel paradigm for integrating generative artificial intelligence (GenAI) into the medical field. Multimodal LLMs (MLLMs) extend these capabilities by incorporating diverse data modalities into unified representations, including genomics, medical imaging, and clinical text. This systematic review synthesizes advancements from 246 records identified between January 2020 and September 2025, of which 90 studies were included after full-text screening, to address critical gaps in understanding the clinical role of LLM and MLLM in healthcare. We trace the evolution from classical natural language processing (NLP) approaches to modern transformer-based architectures, summarize their technical foundations, and examine their construction, evaluation, and deployment in medical workflows. Key contributions include highlighting multimodal integration (e.g., imaging-genomics-text fusion), ethical governance frameworks, and validated domain-specific fine-tuning in clinical settings. We also highlight advances in Prompting, Retrieval-Augmented Generation (RAG), and Multi-Agent (agentic) workflows, providing a critical assessment of their benefits and limitations. In addition, we analyze challenges such as hallucinations, bias, and privacy risks, while providing actionable guidelines for clinicians, developers, and policymakers to improve regulatory compliance. By consolidating the nomenclature and systematically evaluating GenAI in medicine, this review offers evidence-based recommendations and directions for the safe and effective integration of generative AI into healthcare. The findings are intended as an authoritative guide for researchers and practitioners, bridge principles, clinical applications, and policy considerations for LLM and MLLM.
Key Findings
1
Clinical deployment advances include domain-specific fine-tuning, prompting, Retrieval-Augmented Generation, and multi-agent workflows, alongside validated evaluation approaches.
2
Evidence-based recommendations emphasize ethical governance and coordinated guidance for clinicians, developers, and policymakers to support safe, effective healthcare integration.
3
Multimodal LLMs extend clinical AI by jointly representing genomics, medical imaging, and clinical text for integrated healthcare applications.
4
The review identifies hallucinations, bias, privacy risks, and regulatory compliance as central barriers to safe clinical adoption of LLMs and MLLMs.
5
The systematic review analyzed 246 records published between January 2020 and September 2025, including 90 studies after full-text screening.
Research Object
Large language models (LLMs) and multimodal large language models (MLLMs) in healthcare
Research Subject
Their clinical capabilities, construction, evaluation, deployment, multimodal integration, ethical governance, risks, and safe-use requirements
Publication Details
Publication Date
2026-01-28
Journal
Publisher
ISSN
Cited by
12
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai11
The PRISMA 2020 statement: an updated guideline for reporting systematic reviews2021
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
LLaMA: Open and Efficient Foundation Language Models2023
Sequence to Sequence Learning with Neural Networks2014
Neural Machine Translation by Jointly Learning to Align and Translate2014
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation2016
GPT-4 Technical Report2023
Flamingo: a Visual Language Model for Few-Shot Learning2022
MM-LLMs: Recent Advances in MultiModal Large Language Models2024
A framework for human evaluation of large language models in healthcare derived from literature review2024
Privacy-preserving large language models for structured medical information retrieval2024