EUVIMEDSkopri EUVIMED
Scoping ReviewOpen access

Prompt Engineering Paradigms for Medical Applications: Scoping Review

Jamil Zaghir iD, Marco Naguib iD, Mina Bjelogrlic iD, Aurélie Névéol iD, Xavier Tannier iD, Christian Lovis iD

Journal of Medical Internet Research · 2024-09-10 · 26 · e60501

DOI: 10.2196/60501 ↗

At a glance

Scoping Review in Journal of Medical Internet Research, published online on 2024-09-10. Written by Jamil Zaghir and 5 co-authors. Institution: Division of Medical Information Sciences, Geneva University Hospitals, Geneva, Switzerland. Major MEDLINE topics: Natural Language Processing. Cited 152 times so far (Crossref); 127 references. The full text is freely available in PubMed Central.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Prompt engineering, focusing on crafting effective prompts to large language models (LLMs), has garnered attention for its capabilities at harnessing the potential of LLMs. This is even more crucial in the medical domain due to its specialized terminology and language technicity. Clinical natural language processing applications must navigate complex language and ensure privacy compliance. Prompt engineering offers a novel approach by designing tailored prompts to guide models in exploiting clinically relevant information from complex medical texts. Despite its promise, the efficacy of prompt engineering in the medical domain remains to be fully explored.

Objective

The aim of the study is to review research efforts and technical approaches in prompt engineering for medical applications as well as provide an overview of opportunities and challenges for clinical practice.

Methods

Databases indexing the fields of medicine, computer science, and medical informatics were queried in order to identify relevant published papers. Since prompt engineering is an emerging field, preprint databases were also considered. Multiple data were extracted, such as the prompt paradigm, the involved LLMs, the languages of the study, the domain of the topic, the baselines, and several learning, design, and architecture strategies specific to prompt engineering. We include studies that apply prompt engineering–based methods to the medical domain, published between 2022 and 2024, and covering multiple prompt paradigms such as prompt learning (PL), prompt tuning (PT), and prompt design (PD).

Results

We included 114 recent prompt engineering studies. Among the 3 prompt paradigms, we have observed that PD is the most prevalent (78 papers). In 12 papers, PD, PL, and PT terms were used interchangeably. While ChatGPT is the most commonly used LLM, we have identified 7 studies using this LLM on a sensitive clinical data set. Chain-of-thought, present in 17 studies, emerges as the most frequent PD technique. While PL and PT papers typically provide a baseline for evaluating prompt-based approaches, 61% (48/78) of the PD studies do not report any nonprompt-related baseline. Finally, we individually examine each of the key prompt engineering–specific information reported across papers and find that many studies neglect to explicitly mention them, posing a challenge for advancing prompt engineering research.

Conclusions

In addition to reporting on trends and the scientific landscape of prompt engineering, we provide reporting guidelines for future studies to help advance research in the medical field. We also disclose tables and figures summarizing medical prompt engineering papers available and hope that future contributions will leverage these existing works to better advance the field.

Subjects

MeSH terms (MEDLINE)

Natural Language ProcessingHumansMedical Informatics

Author keywords

LLMsNLPclinical natural language processingclinical practicecomputer sciencelarge language modelsmedical applicationmedical applicationsmedical informaticsmedical textsmedicinenatural language processingprivacyprompt designprompt engineering

Authors and institutions

  • Division of Medical Information Sciences, Geneva University Hospitals, Geneva, Switzerland.
  • Department of Radiology and Medical Informatics, University of Geneva, Geneva, Switzerland.
  • Université Paris-Saclay, CNRS, Laboratoire Interdisciplinaire des Sciences du Numérique, Orsay, France.
  • Sorbonne Université, INSERM, Université Sorbonne Paris-Nord, Laboratoire d'Informatique Médicale et d'Ingénierie des Connaissances en eSanté, LIMICS, Paris, France.

ORCID profiles: Jamil Zaghir, Marco Naguib, Mina Bjelogrlic, Aurélie Névéol, Xavier Tannier, Christian Lovis

Cite

APA

Zaghir, J., Naguib, M., Bjelogrlic, M., Névéol, A., Tannier, X., & Lovis, C. (2024). Prompt Engineering Paradigms for Medical Applications: Scoping Review. Journal of Medical Internet Research, 26, e60501. https://doi.org/10.2196/60501

Vancouver

Zaghir J, Naguib M, Bjelogrlic M, Névéol A, Tannier X, Lovis C. Prompt Engineering Paradigms for Medical Applications: Scoping Review. Journal of Medical Internet Research. 2024;26:e60501. doi:10.2196/60501

BibTeX
@article{Zaghir2024,
  author = {Zaghir, Jamil and Naguib, Marco and Bjelogrlic, Mina and Névéol, Aurélie and Tannier, Xavier and Lovis, Christian},
  title = {Prompt Engineering Paradigms for Medical Applications: Scoping Review},
  journal = {Journal of Medical Internet Research},
  year = {2024},
  volume = {26},
  pages = {e60501},
  doi = {10.2196/60501}
}
Start for free →