AI better than radiologists at diagnosing lung cancer
pharmafile | May 21, 2019 | News story | Manufacturing and Production | AI, artificial intelligence, cancer screening, lung cancer, pharma ML
An artificial intelligence (AI) is better than specialist doctors at diagnosing lung cancer, according to a study from researchers at Google and Northwestern University in Illinois.
While not yet ready for clinical use, it is hoped that the technology will boost the effectiveness of cancer screening in the future.
The study, published in the journal Nature Medicine, outlines a deep learning algorithm that is able to predict a patient’s risk of lung cancer.
Current screening methods have high rates of false-positives and high false-negatives. However the AI beat out radiologists in showing it was able to reduce the number of false-positives by 11% and the number of false negatives by 5%.
The AI was able to outperform six radiologists when prior computed tomography (CT) imaging was not available. The algorithm was however on par with radiologists when the doctors had access to prior CT scans.
The AI presents an “opportunity to optimize the screening process via computer assistance and automation,” the study says.
“While the vast majority of patients remain unscreened, we show the potential for deep learning models to increase the accuracy, consistency and adoption of lung cancer screening worldwide.”
Rebecca Campbell, from Cancer Research UK, commented: “It’s encouraging to see new technological innovations that could one day help us to detect lung cancer early. Similarly to how we learn from experience, deep learning algorithms perform a task repeatedly, each time tweaking it a little to improve accuracy.
“Detecting cancer early, when treatment is more likely to be successful, is one of the most powerful ways of improving survival, and developing inexpensive technology which isn’t invasive could play an important role.
“The next steps will be to test this technology further to see whether it can be applied accurately to large numbers of people.”
Louis Goss
Related Content
Practical AI toolkit launched to help manufacturers cut through complexity
A new guide from Made Smarter is helping manufacturers cut through the noise around AI …
Bramacare launches new AI platform to improve eating disorder care
Bramacare has launched an AI-enabled platform designed to aid eating disorder and rehabilitation services, the …
Roche adds 2,176 NVIDIA Blackwell GPUs to its hybrid-cloud AI factory
Roche has expanded its global AI infrastructure with a NVIDIA AI factory, adding 2,176 high-performance …
