Researchers developed several artificial intelligence algorithms using a vast collection of transcriptome data — more than 12,000 blood samples collected in 105 previous studies, with nearly one-third collected from AML patients — which denotes blood cells’ gene activity.
Once trained on the data, the machine learning algorithms searched transcriptome data for patterns specific to AML, tasked with retroactively identifying those blood samples diagnosed with the disease.
“Of course, we knew the classification as it was listed in the original data, but the software did not. We then checked the hit rate. It was above 99 percent for some of the applied methods,” lead investigator Joachim Schultze, MD, head of the genomics and immunoregulation department at the University of Bonn in Germany, said in a news release.
Dr. Schultze concluded, “The aim is to provide the experts with a tool that supports them in their diagnosis. In addition, many patients go through a real odyssey until they finally end up with a specialist and get a diagnosis. … With a blood test, as it seems possible on the basis of our study, it is conceivable that the family doctor would already clarify a suspicion of AML. And when the suspicion is confirmed, the patient is referred to a specialist. Possibly, the diagnosis would then happen earlier than it does now and therapy could start earlier.”
More articles on AI:
Rushing unregulated AI into healthcare raises patient risks: ‘I don’t think we want to fail fast’
8 healthcare companies among the top 25 highest-funded AI startups of 2019
NAM report: The success of healthcare AI depends on building consensus
