A new study reveals that AI can boost breast cancer detection rates by nearly 18% in Germany’s Mammography Screening Program without increasing false positives. This advancement could transform global health care.
A new study conducted in Germany has revealed that artificial intelligence can enhance breast cancer detection rates by nearly 18% within Germany’s Mammography Screening Program (MSP). This improvement comes without an increase in false positives or unnecessary follow-up examinations, marking a significant milestone in medical technology.
The study, published in the journal Nature Medicine, emphasize the potential of AI to reduce radiologists’ workload while maintaining high diagnostic quality. This breakthrough could lead to substantial improvements in early breast cancer detection and patient outcomes worldwide.
The study, termed PRAIM, analyzed data from over 460,000 women participating in the MSP between 2021 and 2023 across 12 German screening sites. Approximately half of the mammograms were reviewed using AI technology, while the remaining half underwent traditional double reading by radiologists.
“Our initial aim was to demonstrate that AI-based evaluations are equivalent to human assessments,” co-corresponding author Alexander Katalinic, the director of the Institute of Social Medicine and Epidemiology at the University of Luebeck and UKSH, said in a news release. “However, the findings exceeded our expectations: AI significantly improves breast cancer detection rates.”
The study found that AI detected 6.7 cases of breast cancer per 1,000 women screened, compared to the 5.7 cases per 1,000 identified through traditional methods, translating to one additional cancer case detected per 1,000 women screened.
Crucially, the rate of women referred for further testing remained stable — 37.4 per 1,000 for AI assessments versus 38.3 per 1,000 for traditional readings.
“The PRAIM study highlights the immense potential of AI to enhance screening programs worldwide. This evidence will elevate discussions about integrating AI into healthcare systems to a new level,” added co-corresponding author Stefan Bunk, chief technology officer of Vara, a technology company.
Another key finding from the study is the potential of AI to streamline breast cancer screenings. Simulations indicated that if all cases flagged as normal by AI were not reviewed by human readers, the breast cancer detection rate would still be 16.7% higher and unnecessary recalls could be reduced by 15%.
Given that radiologists in Germany currently analyze 24 million individual images annually, the implementation of AI could significantly reduce their workload.
“We hope that the higher detection rates enabled by AI will improve outcomes for women with breast cancer. This will be the focus of future investigations,” Katalinic added.
Breast cancer is the most common cancer affecting women in Germany, with 78,000 new cases annually. The MSP, designed for early detection, screens over 3 million women aged 50 to 75 each year. Despite the high accuracy of double readings, some cancer cases remain undetected.
AI-based systems could address this diagnostic gap, enhancing accuracy and reducing the burden on radiologists.
The study marks a significant advancement in integrating AI into clinical practice. Its findings illustrate the transformative potential of AI in cancer detection, efficiency improvement and overall patient outcomes.
Future research will aim to understand the long-term impacts of AI on patient prognosis and its seamless integration into clinical workflows.