ArticleNPJ digital medicine2025
Demographic inaccuracies and biases in the depiction of patients by artificial intelligence text-to-image generators.
Article in NPJ digital medicine, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. It is linked to trial NCT07626736 (Evaluating the Efficacy and Safety of AI Localization Models in Multidisciplinary Team Care for NSCLC), which is not on this map. Cited by 4 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Evaluating the Efficacy and Safety of AI Localization Models in Multidisciplinary Team Care for NSCLC: a Prospective, Controlled Clinical Trial Protocol
Who cites it
4 citing papers in PubMed.
- How Hospice and Palliative Care Are Portrayed in Artificial Intelligence-Generated Images: A Content Analysis.Journal of palliative medicine · 2026Article
- Patient-Initiated Permanent Deletion of Their Electronic Health Record Data: implications for Artificial Intelligence and Big Data in Healthcare : Clyde T. Matava, MBChB, MMed, MHSc.Journal of medical systems · 2026Article
- Bias, representation, and clinical fidelity in AI-generated images for medical education: a systematic literature review.NPJ digital medicine · 2026Article
- Artificial intelligence in membranous nephropathy: transforming clinical management toward precision medicine.Frontiers in medicine · 2026Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
14 authors.
Funding
Abstract
The wide usage of artificial intelligence (AI) text-to-image generators raises concerns about the role of AI in amplifying misconceptions in healthcare. This study therefore evaluated the demographic accuracy and potential biases in the depiction of patients by four commonly used text-to-image generators. A total of 9060 images of patients with 29 different diseases was generated using Adobe Firefly, Bing Image Generator, Meta Imagine, and Midjourney. Twelve independent raters determined the sex, age, weight, and race and ethnicity of the patients depicted. Comparison to the real-world epidemiology showed that the generated images failed to depict demographical characteristics such as sex, age, and race and ethnicity accurately. In addition, we observed an over-representation of White and normal weight individuals. Inaccuracies and biases may stem from non-representative and non-specific training data as well as insufficient or misdirected bias mitigation strategies. In consequence, new strategies to counteract such inaccuracies and biases are needed.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.