Named the benefits of artificial intelligence in the fight against cancer

While the pros and cons of AI are being debated, a new study has shown that artificial intelligence is as good at breast cancer screening as two radiologists. Preliminary results from a major trial show that the use of AI technology can nearly halve human workloads.

The use of artificial intelligence in breast cancer screening is safe and could almost halve the workload of radiologists, according to the world’s largest study of its kind.

According to the World Health Organization, breast cancer is the most common type of cancer worldwide, with more than 2.3 million women developing the disease each year.

Screening can improve prognosis and reduce mortality by detecting breast cancer at an earlier, treatable stage. Preliminary results from a large study show that AI-assisted screening is as good as two radiologists working together without increasing false positives and nearly halving the workload.

Interim results from a safety analysis of the first randomized controlled trial of its kind involving more than 80,000 women have been published in the Lancet oncology journal.

Previous studies examining whether artificial intelligence can accurately diagnose breast cancer on mammograms were conducted retrospectively, evaluating images that were reviewed by clinicians.

But according to The Guardian, the latest study, which involved Swedish women with a median age of 54, compared AI-assisted screening directly with standard care.

Half of the images were evaluated by two radiologists, while the other half were evaluated by AI-assisted screening followed by interpretation by one or two radiologists.

A total of 244 women (28%) recalled after AI screening were found to have cancer compared to 203 women (25%) recalled after standard screening. This led to the fact that, with the support of artificial intelligence, 41 more types of cancer were identified.

The use of artificial intelligence has not resulted in more false positives when scans are misdiagnosed as abnormal. The false positive rate was 1.5% in both groups, notes The Guardian.

In the AI ​​group, radiologists took 36,886 fewer screen shots compared to the standard treatment group, according to the authors of the study, resulting in a 44% reduction in radiologist workload.

The final results on whether artificial intelligence can reduce the number of cancers detected between screenings, which usually have a worse prognosis, and whether the use of artificial intelligence in screening is justified, are not expected until a few years later.

But an interim analysis concludes: “AI-enabled mammography screening resulted in a similar cancer detection rate compared to standard dual readout with significantly less screen read load, indicating that AI is safe to use in mammography screening.”

Lead author Dr Christina Long from Lund University in Sweden says: “These promising interim safety results should be used to inform new trials and programmatic evaluations to address the acute shortage of radiologists in many countries, but are not sufficient on their own to confirm that the AI ​​is ready to use. implemented in mammography screening. We still need to understand the implications for patient outcomes, especially whether combining the expertise of radiologists with artificial intelligence can help identify interval cancers that are often missed by traditional screening, as well as the cost-effectiveness of the technology. The biggest potential of artificial intelligence right now is that it could allow radiologists to be less burdened by excessive data readouts. While our AI-enabled screening system requires at least one radiologist responsible for detection, it has the potential to eliminate the need for double-reading most mammograms, reducing the burden on the work environment and allowing radiologists to focus on more advanced diagnostics. reducing patient waiting times.”

Stephen Duffy, professor of cancer screening at Queen Mary University of London, who was not involved in the study, welcomed the study’s “high quality” but warned that there could be concerns that artificial intelligence’s increase in breast cancer detection could include over-detection of relatively harmless defeats.

Dr. Kotrina Temchinaite, head of science communications for the charity Breast Cancer Now, says the final results of the trials will ultimately determine whether artificial intelligence can help improve breast cancer screening.

In the meantime, she said, “pressing issues” in breast screening programs need to be addressed, such as outdated IT systems that take up valuable staff time and delay improvements.

An NHS spokesman described the study as “very encouraging” and said it was already exploring how artificial intelligence could help speed up diagnosis in women, catch cancer earlier and save more lives.

Dr Katherine Holliday, President of the Royal College of Radiologists, said: “Artificial intelligence holds enormous promise and can save clinicians time by maximizing our efficiency, supporting decision-making and helping to identify and prioritize the most urgent cases.”