Marcella La Cioppa Recent research has highlighted that the use of artificial intelligence may be able to diagnose breast cancer earlier, also improving the workload of radiologists.
@Canva
Using artificial intelligence, breast radiologists in Denmark have improved breast cancer screening performance and reduced the rate of false-positive results.
The discovery comes 16 months after a study from the same hospital found that artificial intelligence could diagnose cancer through chest X-rays as effectively as a certified radiologist.
When used to evaluate likely normal screening results or assist in decision support, artificial intelligence can also substantially reduce the radiologist’s workload.
Dr. Andreas Lauritzen, a researcher at Gentofte Hospital in Denmark and the study’s lead author, stated:
“Population-based mammography screening reduces breast cancer mortality but imposes a significant workload on radiologists who must read a large number of mammograms, most of which do not warrant a patient recall.”
The study
Compared to screening without AI, the AI-assisted screening detected a significantly higher number of breast cancers (0.82% versus 0.70%) and had a lower false-positive rate (1.63% versus 2.39%).
In the AI-screened group, the recall rate, referring to the number of times a patient was asked to return for a follow-up examination, decreased by 20.5%, and the radiologists’ reading workload was reduced by 33.4%.
The positive predictive value of AI-assisted screening was also higher than that of non-AI screening (33.5% versus 22.5%). In the AI group, a larger percentage of detected invasive tumors were 0.4 inches or smaller (44.93% versus 36.60%).
Similarly, a Swedish study conducted at Lund University reported a 20% improvement in accurate breast cancer diagnoses, with the AI’s labor-saving capability being even greater than that observed in Dr. Lauritzen’s study.
An accompanying editorial praised AI’s ability to reduce human workload and suggested that, rather than presenting AI as a potential replacement for radiologists, evidence supports the development of AI programs as work tools and labor-saving devices.
