New York City-based NYU Langone Health's Perlmutter Cancer Center and the University of Glasgow in Scotland developed an artificial intelligence-powered tool that was 99% accurate in distinguishing between two lung cancers.
The tool was tested on adenocarcinoma and squamous cell cancers, and the results were published June 11 in Nature Communications.
It was also 72% accurate in predicting the timing of a cancer's possible return after undergoing treatments or therapies.
"Lung tissue samples can now be analyzed in minutes by our computer program to provide fairly accurate predictions of whether their cancer will return, predictions that are better than current standards of care for making a prognosis in lung adenocarcinoma," Aristotelis Tsirigos, PhD, co-senior investigator of the study and a professor at the NYU Grossman School of Medicine, said in a June 11 news release.
The AI tool works by using a model of machine learning known as histomorphological phenotype learning, an algorithm the team trained using lung adenocarcinoma tissue slides from the Cancer Genome Atlas. From the slides, the researchers identified 46 key characteristics they can group into phenotype clusters from both normal and diseased tissues. The tool learns from that information, looks at a patient's results and assigns a score based on their likelihood for tumor recurrence five years out.