Everything you need to understand, replicate, or extend our research.
This study's methodology and analysis plan were specified before data collection began, preventing post-hoc adjustment of methods to achieve desired results.
Protocol version 1.0 — January 2026
All datasets in JSON format for maximum accessibility.
54 name pairs across 6 demographic contrast categories with length matching and category labels.
20 standardized symptom profiles covering cardiovascular, neurological, abdominal, respiratory, pain, mental health, and fatigue categories.
5 clinical reasoning vignettes for pain management scenarios with demographic variants.
5 clinical reasoning vignettes for cardiac scenarios including STEMI, atypical chest pain, and heart failure.
5 clinical reasoning vignettes for psychiatric scenarios including psychosis, depression, and anxiety.
5 clinical reasoning vignettes for emergency scenarios including acute abdomen and mental health crisis.
Foundational research our methodology builds upon.
Dissecting racial bias in an algorithm used to manage the health of populations
Science, 366(6464), 447-453
Racial bias in pain assessment and treatment recommendations, and false beliefs about biological differences between blacks and whites
PNAS, 113(16), 4296-4301
The effect of race and sex on physicians' recommendations for cardiac catheterization
NEJM, 340(8), 618-626
Are Emily and Greg More Employable Than Lakisha and Jamal? A Field Experiment on Labor Market Discrimination
American Economic Review, 94(4), 991-1013
The impact of race on diagnosis and disposition from a psychiatric emergency service
Journal of Clinical Psychiatry, 64(4), 395-401
Healthcare AI Fairness Observatory (2026). Name-Based Discrimination in Consumer Medical AI Symptom Checkers: A Matched-Pair Experimental Study. https://aifairnesslab.org
MIT License
Free to use, modify, and distribute. Include original license and copyright notice.
CC-BY-4.0
Free to share and adapt. Attribution required.
CC-BY-4.0
Free to share and adapt. Attribution required.
If you have questions about the research, data, or resources, please reach out.