Can AI/LLM-Enhanced Active Learning Transform Microbiology Education in Low-Cost Settings? Insights from a Pilot Case Study and an initial guide for educators.

2. Abstract This pilot case study investigates the potential of artificial intelligence (AI)-enhanced active learning to transform microbiology education, particularly in low-resource settings. By integrating traditional lectures with interactive learning sessions using freely available large language model (LLM) tools (Ex; NotebookLM), the study aimed to assess improvements in student engagement and knowledge retention. Nineteen undergraduate Biomedical Science students participated, exploring microbiological topics through curated digital resources and interactive AI platforms, with comprehension assessed via mock and final quizzes. The MCQ questions, student guides, and learning outcomes were all AI-generated, leveraging extensive cohort-specific information, and clearly defined desired outcomes. All AI-generated content was thoroughly vetted and independently confirmed by a second reviewer. Results demonstrated notable improvements in average test scores, rising from 68% to 83.8% after iterative adjustments based on student feedback. Participants reported increased engagement and deeper conceptual understanding compared to conventional methods. Additionally, the integration of AI possibly reduced lecturer preparation and session creation time to only approximately 60 minutes, although this observation requires further formal investigation. Despite encountering challenges such as limited functionality for free AI tool users (In ChatGPT), occasional connectivity issues, and minor inaccuracies in some answers, the approach was widely recommended by students. This study underscores the viability and benefits of low-cost AI tools in enhancing active learning and student outcomes, providing educators with a scalable instructional framework adaptable across various STEM and biomedical contexts.