Abstract
Introduction. Generative Artificial Intelligence (AI), specifically through Large Language Models (LLMs), is progressively reshaping clinical documentation, decision support, patient education, and research synthesis in healthcare. Despite significant benefits, these models pose challenges such as inaccuracies (hallucinations) and inherent biases. This paper highlights prompt engineering as an emerging and critical skill for healthcare professionals and demonstrates how structured prompting techniques can improve the reliability, clinical relevance, and ethical compliance of AI-driven applications.
Methods. A systematic review of recent literature was conducted to present structured prompt engineering methodologies specifically tailored to healthcare settings. Advanced prompting techniques, including chain-of-thought reasoning, zero-shot and few-shot prompting, and self-consistency strategies, were examined.
Results. The proposed structured approach encompasses clear objective definition, precise contextualization, integration of domain-specific knowledge, iterative refinement, and ethical risk mitigation. Practical guidelines are provided for designing prompts suitable for clinical scenarios, such as diagnostic decisions, patient-specific therapeutic protocols, and administrative tasks. Notably, advanced techniques such as chain-of-thought reasoning and self-consistency effectively reduce inaccuracies and enhance clinical decision-making.
Discussion and Conclusion. The structured integration of prompt engineering optimizes clinical decision-making and supports adherence to evidence-based practices. Incorporating prompt engineering into healthcare educational programs and fostering interdisciplinary collaboration are crucial for the responsible implementation of generative AI. These advancements have far-reaching implications for improving clinical effectiveness, enhancing patient care quality, and elevating the standards of healthcare education and professional practice.
References
Shah K, Xu AY, Sharma Y, et al. Large language model prompting techniques for advancement in clinical medicine. J Clin Med. 2024;13(17):5101. doi:10.3390/jcm13175101
Patil R, Heston TF, Bhuse V. Prompt engineering in healthcare. Electronics. 2024;13:2961. doi:10.3390/electronics13152961
Meskó B. Prompt engineering as an important emerging skill for medical professionals: Tutorial. J Med Internet Res. 2023;25:e50638. doi:10.2196/50638
Nazi ZA, Peng W. Large language models in healthcare and medical domain: A review. Informatics. 2024;11:57. doi:10.3390/informatics11030057
Habib MM, Hoodbhoy Z, Siddiqui MAR. Knowledge, attitudes, and perceptions of healthcare students and professionals on the use of artificial intelligence in healthcare in Pakistan. PLoS Digit Health. 2024;3(5):e0000443. doi:10.1371/journal.pdig.0000443
Hendawi S, Kanan T, Elbes M, Mughaid A, AlZu’bi S. Automated prompt engineering pipelines: Fine-tuning LLMs for enhanced response accuracy [Preprint]. SSRN. Published 2024. doi:10.2139/ssrn.5004054
Chen CJ, Liao CT, Tung YC, Liu CF. Enhancing healthcare efficiency: integrating ChatGPT in nursing documentation. Stud Health Technol Inform. 2024;316:851-852. doi:10.3233/SHTI240545
Abhari S, Fatahi S, Saragadam A, Chumachenko D, Pelegrini Morita P. A road map of prompt engineering for ChatGPT in healthcare: A perspective study. Stud Health Technol Inform. 2024;316:998-1002. doi:10.3233/SHTI240578
Cai CJ, Wang H, Wang M, Agrawal RK, Bero N. Prompting is all you need: LLMs for systematic review screening. MedRxiv. Preprint. Published 2024. doi:10.1101/2024.06.01.24308323
Zaghir J, Naguib M, Bjelogrlic M, et al. Prompt engineering paradigms for medical applications: Scoping review. J Med Internet Res. 2024;26:e60501. doi:10.2196/60501
Huang M, Sangi-Haghpeykar H. Prompt engineering in medical education. Int Med Educ. 2023;2(3):198-205. doi:10.3390/ime2030019
Garante per la protezione dei dati personali. Decalogo per la realizzazione di servizi sanitari nazionali attraverso sistemi di Intelligenza Artificiale. October 10, 2023.
Hsieh CJ, Si S, Yu F, Dhillon IS. Automatic engineering of long prompts. In: Findings of the Association for Computational Linguistics: ACL 2024. Bangkok, Thailand: Association for Computational Linguistics; 2024:10672-1085.
Atil B, Chittams A, Fu L, Ture F, Xu L, Baldwin B. LLM stability: a detailed analysis with some surprises. arXiv preprint arXiv:2408.04667. Published 2024.
Zhuo J, Zhang S, Fang X, et al. ProSA: Assessing and understanding the prompt sensitivity of LLMs. In: Findings of the Association for Computational Linguistics: EMNLP 2024. Miami, Florida, USA: Association for Computational Linguistics; 2024:1950-1976.
Ho CN, Tian T, Ayers AT, et al. Qualitative metrics from the biomedical literature for evaluating large language models in clinical decision-making: a narrative review. BMC Med Inform Decis Mak. 2024;24:357. doi:10.1186/s12911-024-02757-z
Tam TYC, Sivarajkumar S, Kapoor S, et al. A literature review and framework for human evaluation of generative large language models in healthcare. arXiv preprint arXiv:2405.02559. Published 2024.
Zhang W, Shen Y, Wu L, et al. Self-Contrast: Better reflection through inconsistent solving perspectives. arXiv preprint arXiv:2401.02009. Published 2024.
Puerto H, Chubakov T, Zhu X, Tayyar Madabushi H, Gurevych I. Fine-tuning with divergent chains of thought boosts reasoning through self-correction in language models. OpenReview. Published September 24, 2024. Updated December 5, 2024. https://openreview.net/forum?id=u4whlT6xKO
Huang S, Ma Z, Du J, et al. Mirror-consistency: Harnessing inconsistency in majority voting. arXiv preprint arXiv:2410.10857. Published 2024.
Google Research. NotebookLM: AI-powered research and writing tool [Internet]. Google; 2023. Accessed February 7, 2025. https://notebooklm.google
OpenAI. ChatGPT: AI language model with custom knowledge retrieval [Internet]. OpenAI; 2023. Accessed February 7, 2025. https://openai.com/chatgpt
World Health Organization. Regulatory considerations on artificial intelligence for health. Geneva: WHO; 2023:26-31. https://iris.who.int/handle/10665/373421
Neha F, Bhati D, Shukla DK, Amiruzzaman M. ChatGPT: Transforming healthcare with AI. AI. 2024;5(4):2618-2650. doi:10.3390/ai5040126

This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2025 Antonio Alemanno, Michele Carmone, Leonardo Priore
