Stockholm, Feb.01 (SANA) The use of artificial intelligence in breast cancer screening reduced the rate of cancer diagnoses in the years following screening by 12% and increased early detection, according to a Swedish study described as the first randomized trial of its kind.
Researchers said the study, the largest to date examining AI use in cancer screening, involved about 100,000 women in Sweden who underwent routine mammography.
Participants were randomly assigned to either AI-supported screening or standard screening read independently by two radiologists, according to the Guardian.
The AI system analyzed mammograms, assigning low-risk cases to a single radiologist reading and high-risk cases to double reading by radiologists, while flagging suspicious findings to support clinical review.
Mammography supported by AI resulted in fewer cancers diagnosed after a screening appointment, the researchers reported. The rate was 1.55 cancers per 1,000 women in the AI-supported group, compared with 1.76 per 1,000 in the control group.
Early detection also improved. More than four in five cancers (81%) in the AI-supported group were identified at the screening stage, compared with about three-quarters (74%) in the control group. The AI group also recorded nearly a third fewer aggressive sub-type cancers, a reduction of 27% versus standard screening.
Dr. Kristina Lång of Lund University, the study’s lead author, said AI-supported mammography could help detect cancers earlier but cautioned against rapid, unmonitored adoption.
“However, introducing AI in healthcare must be done cautiously, using tested AI tools and with continuous monitoring in place to ensure we have good data on how AI influences different regional and national screening programs and how that might vary over time,” Lång said.
Researchers said broader use of AI-supported screening could ease workload pressures on radiologists while improving detection of early-stage and aggressive cancers, but stressed that AI does not replace specialist oversight.
