Exclusive analysis of biotech, pharma, and the life sciences
In-depth analysis of biotech, pharma, and the life sciences
from some of the nation's most trusted and well-connected reporters in the industry
with STAT+ reporters and leading industry experts in our STAT+ Conversations series
hosted by STAT+, plus early-bird access and discounts to industry events around the country
get delivered to your inbox to brief you on the most important industry news of the day
like our CRISPR Trackr and Drug Pricing Policy Tracker
In-depth analysis of biotech, pharma, and the life sciences
from some of the nation's most trusted and well-connected reporters in the industry
with STAT+ reporters and leading industry experts in our STAT+ Conversations series
hosted by STAT+, plus early-bird access and discounts to industry events around the country
get delivered to your inbox to brief you on the most important industry news of the day
like our CRISPR Trackr and Drug Pricing Policy Tracker
A s more machine learning tools reach patients, developers are starting to get smart about the potential for bias to seep in. But a growing body of research aims to emphasize that even carefully trained models — ones built to ignore race — can breed inequity in care.
Researchers at the Massachusetts Institute of Technology and IBM Research recently showed that algorithms based on clinical notes — the free-form text providers jot down during patient visits — could predict the self-identified race of a patient, even when the data had been stripped of explicit mentions of race. It’s a clear sign of a big problem: Race is so deeply embedded in clinical information that straightforward approaches like race redaction won’t cut it when it comes to making sure algorithms aren’t biased.
Unlock this article by subscribing to STAT+ and enjoy your first 30 days free!
Katie Palmer is a health tech correspondent at STAT.
This name will appear with your comment
There was an error saving your display name. Please check and try again.
Reporting from the frontiers of health and medicine
Subscribe to STAT+ for $15 per month lorem ipsum. Subscribe now
Join our community of lorem ipsum dolor sit amet sed do magna lorem ipsum.