Cutting-edge artificial intelligence (AI) technology proves its proficiency in drastically lowering missed early-stage breast cancer cases, revealing a game-changing potential to improve and accelerate medical diagnosis. Current non-AI screening approaches are anticipated to miss 20% or more breast cancer cases; nevertheless, a study shows that AI analysis discovered up to 13% more instances than human doctors.
The research, which was published on Thursday in Nature Medicine, clarifies how machine learning, which can identify mistakes and subtle symptoms that may go unnoticed by humans, is an essential weapon in the battle against deadly illnesses.
Ben Glocker, an Imperial College London professor and co-author of the study, highlights, “Our study shows that using AI can act as an effective safety net — a tool to prevent subtler signs of cancer falling through the cracks.”
The UK-based Kheiron Medical Technologies, a leader in AI medical diagnostics, created the Mia AI tool, which was used in the study. Compared to routine readings by at least two radiologists, the research showed excellent outcomes in three phases, with improvements in cancer detection rates of 5%, 10%, and a significant 13%. The study examined a cohort of 25,000 women who were screened for breast cancer in Hungary between 2021 and 2023.
Most of the newly identified cases of cancer were invasive, indicating they had the potential to spread to other bodily areas. This study adds important evidence to the body of knowledge indicating AI can speed up diagnosis while improving the accuracy of identifying cancerous tissues.
The Royal College of Radiologists’ President, Dr. Katharine Halliday, praises the work, calling it “a promising example of how we can utilize AI to speed up diagnosis and treatment” inside the National Health Service (NHS). She highlights the benefits that both radiologists and artificial intelligence (AI) can contribute to the table and the collaborative future that they both see.
AI not only increases accuracy but also has the potential to speed up analysis. According to the Hungarian study, Mia might be able to reduce the amount of time needed for breast cancer scan readings by up to 45%. According to Kheiron, Mia is being gradually introduced in the US after being tested in 16 hospitals in the UK.
The work represents a major advancement in the use of AI for cancer detection, but the researchers stress the need to broaden the field of investigation. To pave the path for an all-encompassing and cooperative future in cancer care, they support incorporating data from other nations, investigating alternative AI systems, and closely observing newly discovered cancer cases inside the research group.
