U.S. breast cancer screening program demonstrates the potential benefits of using artificial intelligence (AI) for mammography screening, with women who paid for AI-enhanced scans 21% more likely to have cancer detected claims.
DeepHealth, an AI company owned by radiology giant RadNet, presented a study at the Radiological Society of North America (RSNA) annual meeting detailing 747,604 women who underwent mammograms over a 12-month period. . Overall cancer detection rates were 43% higher for those enrolled in the program compared to those not enrolled in the program. But some women apply (at their own expense) “U.S. Food and Drug Administration-compliant AI software” to their mammograms, which acts as a “second set of eyes” to help radiologists spot abnormalities in mammography exams. Some people chose to do so.
The findings suggest that 22% of the overall cancer detection increase is due to the fact that high-risk patients are more likely to enroll in the program in the first place (suggesting selection bias). ), whose analysis concluded that the remaining 21% was due to increased use of AI to improve recall in additional image processing.
However, this is far from definitive, and researchers are now trying to “better quantify” the benefits of AI in this situation through randomized controlled trials.