An AI model cut breast cancer diagnostic timelines from several weeks to about an hour, according to a study published May 18 in NPJ Digital Medicine.
Researchers from University of California San Francisco and UC Berkeley developed and trained the model, called Mirai, on more than 114,000 mammograms linked to patient outcomes before integrating the model into mammography screening at the Zuckerberg San Francisco General Hospital and Trauma Center.
Here are three things to know from the study:
- Of 4,100 mammograms, the model identified 525 patients at high risk of developing breast cancer.
- Once identified by the model, the diagnostic evaluation waiting period for high-risk patients fell from several weeks to about an hour. The average biopsy waiting period fell from two months to less than 10 days among patients ultimately diagnosed with breast cancer.
- Researchers hope “AI will foster a more tailored approach to breast cancer screening that is personalized to each patient’s breast cancer risk,” according to a June 11 news release from the University of California.
Read the full study here.
At the Becker's Perioperative Summit, taking place September 14–15 in Chicago, perioperative leaders and healthcare executives will focus on improving operating room efficiency, enhancing patient safety, optimizing staffing and driving innovation across surgical services. Apply for complimentary registration now.
