close
close

Mondor Festival

News with a Local Lens

AI detects more cases of breast cancer, study finds
minsta

AI detects more cases of breast cancer, study finds

Would you pay extra to improve your medical exam with artificial intelligence? In a recent study, more than 30% of women opted for AI-enhanced mammograms – and the results are there.

Researchers at this year’s Radiological Society of North America (RSNA) Annual Meeting revealed that cancer was 21% more likely to be detected in women who paid extra for a breast cancer screening program. AI-enhanced breast. Their conclusions, presented at the annual meeting and detailed in an RSNA statementaffirm the potential of AI as a “second pair of eyes” for radiologists.

“This is the first report of the results of a program that provides an enhanced AI-powered exam that patients can choose to enroll in,” said Bryan Haslam, chief product officer at DeepHealth who led the study, in the press release.

The study examined 10 clinical practices offering patients an AI-powered, paid, FDA-compliant screening mammography program. The X-rays of the women who participated in the program were reviewed by a breast radiologist and then by the AI ​​software. If the exams were not consistent with each other, a second radiologist would perform a third exam.

“The enhanced AI-driven exam program leverages AI in a new workflow to ensure women with suspicious findings receive expert-level care that could help detect many more breast cancers early” , added Haslam. “The number of women choosing this program now stands at 36% and growing, and the cancer detection rate continues to be significantly higher for these women. »

In fact, of the 747,604 women who had mammograms over the course of a year, the cancer detection rate was about 43% higher for those enrolled in the program than for those who were not. The researchers noted a higher rate in the 10 practices in the study. Although they attributed 22% of this increase to the fact that women at higher risk of cancer were more likely to enroll in the program, the remaining 21% of the increase in detection came from AI.

As a result, enrolled women were recalled for additional screening at a 21% higher rate than non-enrolled women, and their positive cancer predictive value (the chances that positive cancer results Really indicates cancer) was also 15% higher, “indicating that each booster resulted in more cancer diagnoses in the enrolled population,” the researchers wrote. In other words, reminders triggered with the help of AI were more accurate.

“These data indicate that many women are eager to use AI to improve their mammogram screening, and when AI is combined with a review of protective measures, more cancers are detected,” said Gregory Sorensen, also from DeepHealth and lead author of the study. Next, scientists hope to further research and eliminate bias resulting from self-selection through randomized controlled trials.

These results highlight the potential of AI-enhanced radiology. Although some clinics offer this improvement at an additional cost, the fact that insurance companies are not currently willing to cover this cost could slow its integration, according to the researchers.

It remains to be seen whether further research will pave the way for more widespread and potentially revolutionary use of AI in diagnostics, and whether insurance companies will buy into the program.