Welkom! Inholland respecteert je privacy. Deze website maakt gebruik van cookies om je bezoek makkelijker en persoonlijker te maken, de site te verbeteren en om marketingactiviteiten te kunnen doen. Wanneer je op ‘Ja, ik accepteer’ klikt geef je hier toestemming voor.
Using artificial intelligence to create diverse and inclusive medical case vignettes for education
Using artificial intelligence to create diverse and inclusive medical case vignettes for education
Auteurs
Michiel J. Bakkum, Mariëlle G. Hartjes, Joost D. Piët, Erik M. Donker, Robert Likic, Emilio J. Sanz, Fabrizio De Ponti, Petra Verdonk, Milan C. Richir, Michiel A. van Agtmael, Jelle Tichelaar
Abstract
Aims: Medical case vignettes play a crucial role in medical education, yet they often fail to authentically represent diverse patients. Moreover, these vignettes tend to oversimplify the complex relationship between patient characteristics and medical conditions, leading to biased and potentially harmful perspectives among students. Displaying aspects of patient diversity, such as ethnicity, in written cases proves challenging. Additionally, creating these cases places a significant burden on teachers in terms of labour and time. Our objective is to explore the potential of artificial intelligence (AI)-assisted computer-generated clinical cases to expedite case creation and enhance diversity, along with AI-generated patient photographs for more lifelike portrayal.
Methods: In this study, we employed ChatGPT (OpenAI, GPT 3.5) to develop diverse and inclusive medical case vignettes. We evaluated various approaches and identified a set of eight consecutive prompts that can be readily customized to accommodate local contexts and specific assignments. To enhance visual representation, we utilized Adobe Firefly beta for image generation.
Results: Using the described prompts, we consistently generated cases for various assignments, producing sets of 30 cases at a time. We ensured the inclusion of mandatory checks and formatting, completing the process within approximately 60 min per set.
Conclusions: Our approach significantly accelerated case creation and improved diversity, although prioritizing maximum diversity compromised representativeness to some extent. While the optimized prompts are easily reusable, the process itself demands computer skills not all educators possess. To address this, we aim to share all created patients as open educational resources, empowering educators to create cases independently.