Beyond the Hype: Transformative Impact of Large Language Models on Clinical Decision-Making and Healthcare Delivery Systems
DOI:
https://doi.org/10.69996/jsihs.2025007Keywords:
Large language models, Healthcare implementation, Clinical decision support, AI governance, Implementation scienceAbstract
Large language models (LLMs) are rapidly transforming healthcare delivery through unprecedented capabilities in clinical text processing and knowledge synthesis. This research examines the multifaceted impact of LLMs across healthcare settings through a systematic mixed-methods
investigation. We analyzed 218 peer-reviewed studies published between 2022-2025 utilizing a framework analysis approach supplemented by expert consensus development via modified Delphi technique. Our findings reveal differentiated adoption patterns across healthcare domains, with
administrative applications (documentation, coding) showing 72% greater implementation than direct clinical decision support. Performance metrics demonstrate 31-47% efficiency improvements in documentation workflows, 26% reduction in clinician cognitive load, and 18-29% enhancement in
diagnostic accuracy across multiple specialties when used as augmentation tools. However, significant implementation barriers persist, including data privacy concerns, workflow integration challenges, and algorithmic bias. This research establishes an evidence-based framework for healthcare organizations navigating LLM integration while highlighting critical governance mechanisms necessary to balance innovation with patient safety. The findings suggest targeted application areas offering maximum clinical value while minimizing risks in this rapidly evolving technological landscape.
References
[1] K. Vaishali, “Health Education Reimagined Virtual Reality for Immersive WellnessLearning,” J. Comput. Educ. Sport. Heal., vol. 1, no. 1, pp. 55–66, 2024.
[2] D. B. Olawade, A. C. David-Olawade, O. Z. Wada, A. J. Asaolu, T. Adereni, and J. Ling, “Artificial intelligence in healthcare delivery: Prospects and pitfalls,” J. Med. Surgery, Public Heal., p. 100108, 2024.
[3] L. Petersson et al., “Challenges to implementing artificial intelligence in healthcare: a qualitative interview study with healthcare leaders in Sweden,” BMC Health Serv. Res., vol. 22, no. 1, p. 850, 2022.
[4] B. Saha, “Generative AI for Text Generation: Advances and Applications in Natural Language Processing,” J. Comput. Allied Intell. (JCAI, ISSN 2584-2676), vol. 3, no. 1, pp. 77–91, 2025.
[5] P. S. Aravazhi et al., “The integration of artificial intelligence into clinical medicine: trends, challenges, and future directions,” Disease-a-Month, p. 101882, 2025.
[6] K. Cresswell, R. Williams, and A. Sheikh, “Using cloud technology in health care during the COVID-19 pandemic,” Lancet Digit. Heal., vol. 3, no. 1, pp. e4–e5, 2021.
[7] D. Ben-Israel, “The impact of machine learning on patient care: a systematic review,” Artif. Intell. Med., vol. 103, p. 101785, 2020.
[8] Z. Chang, “Application of artificial intelligence in COVID-19 medical area: a systematic review,” J. Thorac. Dis., vol. 13, no. 12, p. 7034, 2021.
[9] U. Kose, O. Deperlioglu, J. Alzubi, and B. Patrut, “Deep learning for medical decision support systems,” 2021.
[10] S. S. Sengar, A. Bin Hasan, S. Kumar, and F. Carroll, “Generative artificial intelligence: a systematic review and applications,” Multimed. Tools Appl., pp. 1–40, 2024.
[11] M. Chen et al., “Evaluating large language models trained on code,” arXiv Prepr. arXiv2107.03374, 2021.
[12] S. Liu, A. B. McCoy, and A. Wright, “Improving large language model applications in biomedicine with retrieval-augmented generation: a systematic review, meta-analysis, and clinical development guidelines,” J. Am. Med. Informatics Assoc., p. ocaf008, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Journal of Sensors, IoT & Health Sciences (JSIHS,ISSN: 2584-2560)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Fringe Global Scientific Press publishes all the papers under a Creative Commons Attribution-Non-Commercial 4.0 International (CC BY-NC 4.0) (https://creativecommons.org/licenses/by-nc/4.0/) license. Authors have the liberty to replicate and distribute their work. Authors have the ability to use either the whole or a portion of their piece in compilations or other publications that include their own work. Please see the licensing terms for more information on reusing the work.
