Artificial Intelligence (AI) has been found to be more effective than doctors at detecting breast cancer, according to a new study published in the journal The Lancet Oncology. The study, which is believed to be the first randomized control trial comparing AI-assisted breast cancer detection to human detection, found that AI not only detected more cancers but also reduced doctors’ mammogram reading workload by almost half.
The study analyzed scans from over 80,000 women in Sweden who underwent a mammogram between April 2021 and July 2022. Half of the women’s scans were read by a radiologist along with AI assistance, while the other half were read by two radiologists without AI. The group that used AI detected 20% more cancers than the group without AI, resulting in a cancer detection rate of 6 per 1,000 screened women compared to 5 per 1,000 for the standard approach.
Furthermore, the AI did not increase the number of false positives, meaning it did not incorrectly diagnose abnormalities as cancer. In addition to its superior detection abilities, the AI also reduced the reading workload of radiologists by 44%.
Although the study highlights the potential of AI in breast cancer detection, researchers emphasize that further research is necessary before AI can be used as a sole determiner of cancer. The European guidelines currently recommend that two radiologists screen a mammogram, while the US does not have the same standard. However, both countries are facing a shortage of radiologists as the global population ages and requires more imaging.
Many radiologists see AI as a welcome tool that can enhance their accuracy and efficiency. Dr. Stamatia Destounis, a radiologist specializing in breast imaging, describes anything that improves accuracy as a “wonderful thing.” AI has the potential to make a significant difference in breast cancer screening, as breast cancer incidence has been increasing by 0.5% per year.
While AI may help with pattern recognition, radiologists emphasize that their job involves much more than that. They believe that AI algorithms work best when paired with highly trained radiologists who make the final call on mammogram readings. AI can be seen as a tool that enhances a radiologist’s abilities, similar to a stethoscope for a cardiologist.
AI is an emerging technology that is capturing the imagination of scientists. It has shown promise in various fields, including drug discovery, communication with patients, and even medical licensing exams. Several AI programs are currently under development to assist doctors in cancer detection. These programs have the potential to significantly improve early detection rates and ultimately save more lives.
While AI still requires further research and validation, it has the potential to revolutionize breast cancer detection and improve the accuracy and efficiency of radiologists. As the demand for radiologists increases with the aging population, AI could help ease staffing problems and lead to better patient outcomes.