Demographic inaccuracies and biases in the depiction of patients by artificial intelligence text-to-image generators
Open Access
- 19 July 2025
- journal article
- Published by Springer Nature in npj Digital Medicine
- Vol. 8 (1) , 459
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.Keywords
All Related Versions
This publication has 86 references indexed in Scilit:
- The increasing global health priority of substance use in young peopleThe Lancet Psychiatry, 2016
- The Chicago face database: A free stimulus set of faces and norming dataBehavior Research Methods, 2015
- Public perceptions of stigma towards people with schizophrenia, depression, and anxietyPsychiatry Research, 2014
- Consequences of Perceived Stigma Among Patients with CirrhosisDigestive Diseases and Sciences, 2013
- Global and regional estimates of preeclampsia and eclampsia: a systematic reviewEuropean Journal of Obstetrics & Gynecology and Reproductive Biology, 2013
- Association of perceived stigma and mood and anxiety disorders: results from the World Mental Health SurveysActa Psychiatrica Scandinavica, 2008
- Differences in depressive symptom profile between males and femalesJournal of Affective Disorders, 2008
- Global Epidemiology of HIV-AIDSInfectious Disease Clinics of North America, 2007
- Comparative stigma of HIV/AIDS, SARS, and Tuberculosis in Hong KongSocial Science & Medicine, 2006
- ObesityThe Lancet, 2005