4. Use of artificial intelligence
4.1 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?
Recommendation
The ECIBC's Guidelines Development Group (GDG) suggests to not use single reading supported by artificial intelligence (AI) to read mammograms from digital mammography (2DFFDM) or digital breast tomosynthesis for early detection of breast cancer in organised population-based screening programmes.
Issued in July 2023.
This recommendation has been updated during the latest Guidelines Development Group meeting, considering available evidence until July 2023.
Justification
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.
Considerations for implementation and policy making
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.
Monitoring and evaluation
Quality indicators should be used to monitor and evaluate.
Research priorities
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.
Supporting material
4.2 Should double reading with support by artificial intelligence vs. double reading without support by artificial intelligence be used to read mammograms using digital mammography (2DFFDM) or digital breast tomosynthesis for early detection of breast cancer in mammography screening programmes?
Recommendation
The ECIBC's Guidelines Development Group (GDG) suggests to use double reading (with consensus or arbitration for discordant readings) supported by artificial intelligence (AI) over double reading (with consensus or arbitration for discordant readings) without AI support to read mammograms from digital mammography (2DFFDM) or digital breast tomosynthesis for early detection of breast cancer in organised population-based screening programmes.
Issued in July 2023.
This recommendation has been updated during the latest Guidelines Development Group meeting, considering available evidence until July 2023.
Justification
The majority of the GDG agreed that the balance of desirable and undesirable effects favours the use of double reading with AI support. 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 double reading supported by AI, there may be slightly more false positives than double reading without support. However, there may be one more breast cancer detected for every 1 000 women screened when double reading is supported by AI, which outweighed the false positives.
Although the addition of AI as a support to double reading is probably feasible and acceptable, it may increase costs, and therefore its adoption should be conditional on sustainability. The GDG also 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 the future.
The majority of the GDG agreed with the recommendation: 6 members voted for a conditional recommendation for double reading with support by artificial intelligence, 2 members voted for a conditional recommendation for either double reading with support by artificial intelligence or double reading without support by artificial intelligence, and 2 members abstained.
Considerations for implementation and policy making
Before acquiring and implementing AI technology, an evaluation of the legal context for its use is needed. In addition, thorough quality control of the AI system should be conducted and might include the assessment of data provided by the vendor (e.g. testing and validation results, ROC curves, and number of images utilised for training the algorithm).
Monitoring and evaluation
Quality assurance and quality improvement of AI technology should be conducted and might require storing of AI and consensus results.
Research priorities
- 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.
- Linkage with cancer registries could assist in connecting the long-term follow-up data to the intervention.
- Further research, including retrospective analyses of existing data, should support identifying which subgroups (e.g. lobular cancers, DCIS) artificial intelligence performs better.
Supporting material