Daijiworld Media Network - Stockholm
Stockholm, Feb 1: Artificial intelligence has helped doctors detect more cases of breast cancer during routine screenings, according to the results of a world-first randomised controlled trial published on Friday.
The study, published in The Lancet, found that AI-supported screening identified nine per cent more cancer cases compared to standard screening methods, suggesting that countries could consider wider adoption of AI to support overburdened radiology services.
The trial, led by Swedish researchers, involved more than 100,000 women who underwent routine breast cancer screening across Sweden in 2021 and 2022. Participants were randomly divided into two groups — one in which scans were read by a single radiologist assisted by an AI system, and another following the standard European practice of having two radiologists independently read each scan.
Researchers found that the AI-assisted group not only detected more cancers but also recorded a 12 per cent lower rate of so-called interval cancers — cases diagnosed between regular screening rounds — over the following two years. Interval cancers are often more aggressive and harder to treat.
The improvement in detection was consistent across different age groups and levels of breast density, both known risk factors. Importantly, the rate of false positives was similar in both groups.
Senior study author Kristina Lang of Lund University said that rolling out AI-supported mammography programmes could ease workload pressures on radiologists while improving early cancer detection. However, she cautioned that such deployment should be done carefully and accompanied by continuous monitoring.
Experts also stressed that AI should complement, not replace, human expertise. Jean-Philippe Masson, head of the French National Federation of Radiologists, said a radiologist’s experience remains crucial, as AI systems can sometimes flag tissue changes that are not cancer. He noted that the use of AI in France remains limited due to high costs and the risk of overdiagnosis.
Stephen Duffy, emeritus professor of cancer screening at Queen Mary University of London, who was not involved in the study, said the findings further support the safety of AI-assisted screening. However, he pointed out that the reduction in interval cancers was not statistically significant and called for longer follow-up to see if similar trends emerge in the control group.
Earlier interim results from the trial, published in 2023, showed that AI nearly halved the time radiologists spent reading scans. The AI model used in the study, Transpara, was trained on more than 200,000 previous examinations from 10 countries.
According to the World Health Organization, more than 2.3 million women were diagnosed with breast cancer globally in 2022, with around 670,000 deaths attributed to the disease.