European guidelines on breast cancer screening and diagnosis

This recommendation has been updated during the latest Guidelines Development Group meeting, considering available evidence until July 2023. 

Should single reading supported by artificial intelligence vs. double reading without artificial intelligence support be used to read mammograms using digital mammography (2DFFDM) or digital breast tomosynthesis for early detection of breast cancer in mammography screening programmes?

The GDG agreed that the undesirable effects probably outweigh the desirable effects of single reading supported by artificial intelligence (AI) compared to double reading. The overall certainty of the evidence is very low because of uncertainty of the accuracy of the readings, and the absence of data for the downstream impact on breast cancer and mortality. None of the studies evaluated the use of the readings in a screening programme or followed individuals over time.

The evidence shows that when using single reading supported by AI, there may be moderately more false positives than double reading. Although AI is probably feasible to implement, there is still uncertainty on whether the use of AI as a replacement for the second reader would reduce reading times or would come with costs or savings. 

The GDG noted that, compared to previous/older computer-aided detection systems, the accuracy of AI has improved over the last few years and is expected to improve. The GDG will carefully monitor the evolution of this field and consider this question again in future.

A careful evaluation of the legal context would be needed before future implementation of AI technology as a support for the reader. Implementation might depend on the availability and experience of radiologists.

Quality indicators should be used to monitor and evaluate.

The GDG noted that, compared to previous/older computer-aided detection systems, the accuracy of AI has improved over the last few years and is expected to improve further. The GDG agreed that they should carefully monitor the evolution of this field to keep the recommendation up-to-date.

Prospectively conducted studies are needed which also measure patient important outcomes, such as breast cancer and mortality. Information about how and when to use AI for most benefit is needed and should be evaluated in studies.