Missing ancestry data in single-cell atlases threatens fair medicine
Researchers at Mount Sinai have found that single-cell atlases used for medical research and AI training often lack diverse ancestry data. This omission poses a significant risk to the fairness and accuracy of future medical treatments.
Menu Medical Home Life Sciences Home Become a Member Search Medical Home Life Sciences Home About Functional Food News Health A-Z Drugs Medical Devices Interviews White Papers More... MediKnowledge eBooks Posters Podcasts Videos Newsletters Health & Personal Care Contact Meet the Team Advertise Search Become a Member Top Health Categories Coronavirus Disease COVID-19 Diet & Nutrition Artificial Intelligence Allergies Alzheimer's & Dementia Arthritis & Rheumatology Breast Cancer Breastfeeding Cold, Flu & Cough Dermatology Diabetes Eating Disorders Eye Health Gastrointestinal Health Heart Disease Lung Cancer Mental Health Parkinson's Disease Pregnancy Sleep Urology View Health A-Z Top Health Categories Coronavirus Disease COVID-19 Eating Disorders Diet & Nutrition Eye Health Artificial Intelligence Gastrointestinal Health Allergies Heart Disease Alzheimer's & Dementia Lung Cancer Arthritis & Rheumatology Mental Health Breast Cancer Parkinson's Disease Breastfeeding Pregnancy Cold, Flu & Cough Sleep Dermatology Urology Diabetes View Health A-Z Medical Home Life Sciences Home About News Life Sciences A-Z White Papers Lab Equipment Interviews Newsletters Webinars More... eBooks Posters Podcasts Videos Contact Meet the Team Advertise Search Become a Member White Papers MediKnowledge eBooks Posters Podcasts Videos Newsletters Health & Personal Care Contact Meet the Team Advertise Search Become a Member Webinars eBooks Posters Podcasts Videos Contact Meet the Team Advertise Search Become a Member Missing ancestry data in single-cell atlases threatens fair medicine Download PDF Copy Add News Medical on Google as a preferred source Mount Sinai Health System Jul 20 2026 Reviewed The single-cell "atlases" that are increasingly used to map the human body and as training data for artificial intelligence models, may not represent the world's populations fairly, according to a study led by researchers at the Icahn School of Medicine at Mount Sinai. The analysis found that people of European ancestry were consistently overrepresented, while Asian and Latino individuals were underrepresented, and that a large share of samples lacked any record of ancestry at all. The findings were published July 20 in Cell Genomics [10.1016/j.xgen.2026.101300].
Get the full story
Sign up for Headlinne to unlock AI insights, political bias analysis, and your personalized news feed.
Create free accountAlready have an account? Sign in