New research from published in Nature puts AI to the test in the largest study examining effectiveness in mammogram screenings. The study was conducted by the University of Lubeck in collaboration with the company Vara. It included 460,000 women, 119 radiologists, 5 different machine vendors and 12 screening sites across Germany. Half of the patients were examined using AI-screening methods, while the other half received a traditional double reading by radiologists. The results show AI improved breast cancer detection rates by 17.6 percent.
“Our initial aim was to demonstrate that AI-based evaluations are equivalent to human assessments,” explained Prof. Dr. Alexander Katalinic, principal investigator and Director of the Institute of Social Medicine and Epidemiology at the University of Luebeck and UKSH, Campus Luebeck. “However, the findings exceeded our expectations: AI significantly improves breast cancer detection rates.”
Previous studies have indicated that women are also ready to welcome these AI-enhanced screenings to their mammograms.
Women Are Ready to Welcome AI in Mammogram Screenings
Recent research presented at the Radiological Society of North America (RSNA) shows that the majority of patients welcome AI-driven breast cancer screenings. The study looked at how women felt about AI in mammograms. The majority of respondents were familiar with AI in medicine. Of those, nearly nine in 10 were optimistic about the technology.
The study was presented by radiology resident Ottavia Battaglia, MD, of the Istituto Europeo di Oncologia (IEO) in Milan, Italy. She noted that most women believe radiologists still needed to be involved in the process.
“Our findings suggest that social attitudes to the use of AI to support diagnosis are positive, but women still want human involvement,” Battaglia said. “Specifically, women want to be fully informed about the use of AI in healthcare and they want to retain human interaction in the diagnostic process.”
Why is AI involved in breast cancer screenings?
The National Cancer Institute reports that mammograms correctly identify about 87% of breast cancers during screening. Researchers see AI as a way to potentially improve accuracy, supplementing a radiologist’s reading of a mammogram. AI uses hyper-sensitive algorithms, which scan mammogram images and look for discrepancies. A study published in Radiology: Artificial Intelligence noted that when used alongside a radiologist, AI can identify low-risk mammograms.
“False positives are when you call a patient back for additional testing, and it turns out to be benign,” explained senior author Richard L. Wahl, MD, a professor of radiation oncology and a professor of radiology at Washington University’s Mallinckrodt Institute of Radiology (MIR). “That causes a lot of unnecessary anxiety for patients and consumes medical resources. This simulation study showed that very low-risk mammograms can be reliably identified by AI to reduce false positives and improve workflows.”
The same team previously worked on an AI program to gauge breast density and identify patients who would benefit from additional screening.
