The use of artificial intelligence (AI) in breast cancer screening has shown promise in a groundbreaking trial, reducing radiologist workload by almost 50%. With breast cancer affecting millions of women worldwide, early detection through screening is crucial for improving prognosis and reducing mortality rates.
The trial, published in the Lancet Oncology journal, involved over 80,000 women in Sweden and compared AI-supported screening with standard care. The interim safety analysis revealed that AI screening performed on par with two radiologists working together, without increasing false positives. In fact, AI detected 41 additional cancers, including invasive and in situ cancers, with a consistent false-positive rate compared to standard care.
The most significant finding was that AI significantly reduced radiologists’ workload by 44%. The AI group required 36,886 fewer screen readings, highlighting the potential of AI to alleviate the burden on healthcare professionals and improve efficiency in breast cancer screening.
However, the final results, which will assess AI’s impact on interval cancers and cost-effectiveness, are yet to be released. Researchers plan to investigate whether combining AI with radiologists’ expertise can identify interval cancers that may be missed during traditional screening.
While these findings show promise, concerns have been raised about the potential overdiagnosis of harmless lesions. For instance, ductal carcinoma in situ, a non-invasive type of breast cancer, may be detected more frequently with AI screening. As the final results are pending, it is important to address urgent issues in breast screening programs, such as outdated IT systems.
Overall, this study encourages further trials and evaluations to address the shortage of radiologists in many countries and explore the potential benefits of integrating AI in mammography screening. AI has the potential to improve early detection, reduce waiting times for patients, and allow radiologists to focus on more advanced diagnostics. The National Health Service (NHS) in England is already exploring how AI can speed up diagnosis and enhance breast cancer detection and outcomes.
By harnessing the power of AI, breast cancer screening can become more efficient and effective. However, it is crucial to strike a balance between the benefits of early detection and the potential risks of overdiagnosis. Continued research and advancements in AI technology will help shape the future of breast cancer screening, ultimately saving more lives.
