Abstract
In this chapter, the authors present an appropriate use of prompt engineering in ChatGPT in developing a hypothetical case study for students in understanding basic medical science. In artificial intelligence, particularly in natural language processing, the idea of prompt engineering is used. In prompt engineering, the task description that the AI is expected to complete is incorporated into the input, for example, as a question. Students and teachers can develop hypothetical case studies for their learning of the subjects such as pathology, pharmacology, Western medical diagnostic, and internal medicine. The chapter provided the structure of composing the prompt with a hypothetical case study of peptic ulcer disease of a 45 year of women that underwent endoscopy for H. pylori detection.
TopBackground
Prompt engineering (PE) is an increasingly important skill set needed to converse effectively with large language models (LLMs) (White et al., 2023). Language models have a history dating back to the 1950s; however, it was not until the emergence of the BERT and GPT models in 2018 that language models truly gained widespread acceptance and became the dominant approach in the field (Wang et al., 2023). It is known as prompt engineering, prompt design, or prompt programming.
PE used to design, enhance, and optimizing input prompts in order to effectively convey the user's purpose to a language model like ChatGPT is known as prompt engineering. To get the model to respond in a way that is accurate, pertinent, and cohesive, this practice is necessary. Proper prompt engineering is now a crucial skill for users who want to fully utilize ChatGPT and obtain the best results in a variety of applications as language models continue to improve.
Table 1. The iterative process of composing prompts
| Purpose | Prompt |
| Subject | Subject terms
Keywords |
| Modifier | Question Refinement
Alternative Approaches
Cognitive Verifier
Refusal Breaker |
| Solidifier | Pattern recognition
Error analysis
Fine-tuning
Citation/Reference |
| Variation | Alternative terms
Synonyms |
| Weightage | Priority terms
Exclusion terms
Mixing inclusion and exclusion terms |
Figure 1. Visualization of items for prompt engineering in developing the hypothetical case study