Is AI the future of breast cancer prediction?

hospital room.
(Image credit: gorodenkoff/Istock)

Researchers at the Massachusetts Institute of Technology have developed a new deep learning model that uses mammograms to successfully predict whether a person will be diagnosed with breast cancer in the future, reports Fast Company.

The team tested the artificial intelligence by examining "subtle patterns" in breast tissue from over 60,000 patients, per a report from MIT. The AI approach has a 31 percent success rate in detecting cancer risks among those in the high-risk category, much higher than traditional methods, which identify around 18 percent, reports Fast Company.

The Week

Escape your echo chamber. Get the facts behind the news, plus analysis from multiple perspectives.

SUBSCRIBE & SAVE
https://cdn.mos.cms.futurecdn.net/flexiimages/jacafc5zvs1692883516.jpg

Sign up for The Week's Free Newsletters

From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.

From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.

Sign up

"Rather than taking a one-size fits all approach, we can personalize screening around a woman's risk of developing cancer," MIT professor Regina Barzilay said. "For example, a doctor might recommend supplemental MRI screening for women with high model-assessed risk."

MIT's model is also racially equitable, with the model being equally accurate for both white and black women. Black women are 43 percent more likely to die from the breast cancer than white women, per the MIT report, but traditional cancer detection methods are more effective in evaluating white women.

Explore More
Marianne Dodson

Marianne is The Week’s Social Media Editor. She is a native Tennessean and recent graduate of Ohio University, where she studied journalism and political science. Marianne has previously written for The Daily Beast, The Crime Report, and The Moroccan Times.