Biases in an artificial intelligence image-generator’s depictions of healthy aging and Alzheimer’s

TL;DR

This study finds that AI image generators like DALL-E 3 and Midjourney often portray older adults and those with dementia in negative or stereotypical ways.

Contribution

The study is one of the first to analyze AI-generated images for biases related to aging and dementia, revealing significant disparities in emotional and contextual portrayals.

Findings

DALL-E 3 and Midjourney frequently depicted dementia-related images with negative emotional states.

DALL-E 3 showed more diversity and some positive affect in dementia-related images compared to Midjourney.

Both models produced biased depictions compared to control images of general older adults.

Abstract

This content analysis study investigates potential biases in image generation by 2 artificial intelligence (AI) tools, DALL-E 3 and Midjourney, in portraying older adults and individuals living with dementia. Despite widespread use of generative AI in various sectors, there is limited research on how these models might perpetuate stereotypes and stigmatization through their images.

1056 images were generated using specified prompts categorized into 3 groups: general older adults, dementia-related, and control. Each prompt began with “photorealistic portrait” followed by specific scene descriptions. Four researchers conducted content analysis on each generated image, focusing on factors, such as portrait style, setting, posture, apparent sex of subjects, and emotional affect. The analysis was executed with blinding and randomization protocols to ensure unbiased assessment. Chi-square tests examined the relationship between prompt categories and variables.

Results revealed significant disparities in depictions of older adults and those with dementia compared with control images. Both models more often portrayed subjects in response to dementia-related prompts with negative affect, in less favorable emotional states. However, DALL-E 3 also generated more personas displaying positive affect in response to these prompts. Variations in depiction styles between the 2 AI models were noted, with DALL-E 3 showing a broader diversity of outputs.

The findings highlight AI's potential to reinforce stigmatizing stereotypes through biased image generation. Recommendations include selecting prompts carefully to avoid negative depictions and advocating for greater AI explainability and inclusivity by design. Future research should explore other AI models, other forms of bias, and strategies to mitigate biases.

Figures