Image: © okrasiuk/Stock.adobe.com
Based on a trial involving more than 80,000 women in Sweden, a new study has found that AI can reduce the workload of radiologists by up to 44pc.
A new study has found that experienced doctors can use the help of AI to greatly improve their chances of accurate breast cancer detection during routine mammogram screenings.
Published yesterday (1 August) in the journal The Lancet Oncology, the study is based on a randomised trial involving more than 80,000 women in Sweden, which compared results from AI-assisted breast cancer detection with those detected by humans alone.
Half of the women were placed in a group where AI read mammogram results before it was analysed by radiologists, while the other half had their mammogram screening results analysed by two experienced radiologists without the use of artificial intelligence.
The study found that the first group had a 20pc higher breast cancer detection rate than the second, paving the way for AI to be deployed safely in the industry. The number of false positives – when cancer is wrongly detected – was also not higher than those made by doctors.
Overall, the study concludes that the use of AI in breast cancer detection can reduce doctor workloads by up to 44pc. This is especially important in the context of a shortage of radiologists on both sides of the pond.
“The greatest potential of AI right now is that it could allow radiologists to be less burdened by the excessive amount of reading,” co-author Dr Kristina Lång, an associate professor of radiology diagnostics from Lund University in Sweden, told CNN.
According to the World Economic Forum, healthcare accounts for 11pc of global GDP or $9trn annually. This presents a significant opportunity for AI to aid in research and development of everything from drugs and vaccines to better medical diagnostics and treatment.
The technology is already being used in healthcare extensively, from helping reduce false positives in colorectal cancer to searching for novel antibiotics. And as AI gets more advanced, this trend is only set to increase.
“We’ve had this real spike in the last couple of decades,” Aaron Quigley told SiliconRepublic.com recently. He is the science director and deputy director of CSIRO’s Data 61, the digital specialist arm of Australia’s national science agency.
“It’s a human capital solution as much as a research, innovation solution, there’s just a lot of people who have the skills now to do this kind of advanced AI research.”
10 things you need to know direct to your inbox every weekday. Sign up for the Daily Brief, Silicon Republic’s digest of essential sci-tech news.
