"Remodeling Education in Pathology and Biomedical Sciences: Prompting Effective Learning and Teaching with AI LLMs"

Area of Science:

• Biomedical Sciences Education
• Health Professions Education
• Medical Education Technology

Background:

• Mastering complex biomedical concepts is crucial for pathology and other medical sciences.
• Generative Artificial Intelligence (GenAI), powered by large language models (LLMs), offers new avenues for improving health sciences education.
• Integrating innovative educational tools is essential for undergraduate medical science programs.

Purpose of the Study:

• To develop and evaluate task-focused prompt-based assistants (PAs) for undergraduate medical science education.
• To explore the application of GenAI LLMs in supporting student self-study and interactive learning.
• To assess the role of GenAI in assessment creation and pedagogical innovation within basic medical science courses.

Main Methods:

• Development of five standardized prompt-based assistants (PAs) tailored for specific learning tasks.
• Application of PAs for self-study modules, interactive learning activities, and assessment generation.
• Focus on utilizing Generative Artificial Intelligence (GenAI) large language models (LLMs) for educational support.

Main Results:

• Prompt-based assistants (PAs) effectively support student self-study and engagement in basic medical sciences.
• GenAI LLMs facilitate the creation of diverse learning materials and assessments.
• The study highlights the potential of PAs to foster active learning and drive curriculum development.

Conclusions:

• GenAI LLMs, through PAs, can significantly enhance the learning experience in undergraduate medical education.
• Task-focused PAs offer a scalable solution for improving pedagogical approaches in biomedical sciences.
• The integration of GenAI represents a transformative step towards innovative and effective health sciences education.