Ensuring Appropriate Representation in Artificial Intelligence-Generated Medical Imagery: Protocol for a Methodological Approach to Address Skin Tone Bias.

Background: In medical education, particularly in anatomy and dermatology, generative artificial intelligence (AI) can be used to create customized illustrations. However, the underrepresentation of darker skin tones in medical textbooks and elsewhere, which serve as training data for AI, poses a significant challenge in ensuring diverse and inclusive educational materials.

Objective: This study aims to evaluate the extent of skin tone diversity in AI-generated medical images and to test whether the representation of skin tones can be improved by modifying AI prompts to better reflect the demographic makeup of the US population.

A cost-utility analysis comparing endovascular coiling to neurosurgical clipping in the treatment of aneurysmal subarachnoid haemorrhage.

Endovascular coiling (EC) has been identified in systematic reviews and meta-analyses to produce more favourable clinical outcomes in comparison to neurosurgical clipping (NC) when surgically treating a subarachnoid haemorrhage from a ruptured aneurysm. Cost-effectiveness analyses between both interventions have been done, but no cost-utility analysis has yet been published. This systematic review aims to perform an economic analysis of the relative utility outcomes and costs from both treatments in the UK.