By tracing the evolutionary trajectories of these methodologies, this scoping review provides a mechanism-centered framework to inform responsible model development and deployment in medical settings, tailored to task complexity, data characteristics, and resource constraints.
Abstract
Generative large language models (LLMs) are rapidly transforming medicine, demonstrating unprecedented capability across a broad spectrum of clinical and biomedical tasks. While prior literature has extensively investigated their applications, the methodological foundation underpinning these models remains comparatively underexamined. In this review, we provide a mechanically grounded analysis of recent methodological advances shaping the development and deployment of generative LLMs in healthcare. We categorize the technical landscape into three principal pillars: pretraining, fine-tuning, and prompt engineering, and examine their key architectures, subtypes, and adaptation strategies based on literature published between 2023 and 2025. We further discuss the emerging directions, including efficient model infrastructures and LLMs-powered multi-agent systems, alongside critical challenges related to bias, generalization, and evaluation. By tracing the evolutionary trajectories of these methodologies, this scoping review provides a mechanism-centered framework to inform responsible model development and deployment in medical settings, tailored to task complexity, data characteristics, and resource constraints.
Current evidence suggests a limited role for cautious, clinician-supervised use of generative LLMs in selected text-heavy epilepsy tasks, particularly extraction, summarization, documentation support, and patient education, but falls short of justifying independent or routine clinical deployment.
A comprehensive framework for transforming LLMs into trustworthy medical specialists is presented, and the evolution toward agentic AI systems that orchestrate them for autonomous, collaborative clinical decision-making is explored.
Kiduk Kim, Jeong Min Song, Dong Yeong Kim et al.· Cell Reports Medicine· 0 citations
This review is the first to integrate Orem’s Self-Care Theory into a 3D evaluative framework for large language models in chronic care, thereby moving beyond fragmented, technology-centric assessments toward a structured, nursing-informed, and theory-driven synthesis.
Ling-Hui Zhang, P. Huai, Rui Xu et al.· Journal of Medical Internet...· 0 citations
Large language models (LLMs) are generative artificial intelligence (AI) models that are rapidly reshaping the practice of biomedical science. Their ability to synthesize literature, generate analytical code, and interface with multimodal data offers a new framework for accelerating discovery. Yet their integration int...
Kaleigh F. Roberts, Srinivas Koutarapu, Justin Melendez et al.· npj Dementia· 0 citations
This article aims to provide a pragmatic basis for designing and executing rigorous evaluations of healthcare LLMs by describing underlying concepts and potential pitfalls, while emphasizing the importance of aligning evaluation methods with the research question.
S. E. McKinney, Phuc Vu, Samuel A. Justice et al.· arXiv.org· 0 citations
This review highlights the promise of LLMs in enhancing decision support, workflow efficiency, research productivity, and patient communication in spine care, while emphasizing the need for interdisciplinary collaboration, robust evaluation metrics, and governance frameworks that prioritize patient safety and equity.
Fabio Galbusera, Andrea Cina· European spine journal· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
Senior Research Scientist Jim Glass discusses how his MIT-IBM Computing Research Lab collaboration connects perception and language, and addresses the shortcoming of current models.
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
Enforcing physics-based constraints prevents AI models from generating unreliable predictions for complex nonlinear systems in weather, climate, and turbulent flows.
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.