AI Can Now Diagnose Acute Myeloid Leukemia
Thu, April 22, 2021

AI Can Now Diagnose Acute Myeloid Leukemia

AI can detect acute myeloid leukemia (AML) with high reliability, which is above 99% for some of the applied methods / Credits: Andrey_Popov via Shutterstock

 

Artificial intelligence has played a huge role in both detecting and diagnosing diseases. Recently, a team of researchers from the German Center for Neurodegenerative Diseases (DZNE) and the University of Bonn discovered that AI can detect one of the most common forms of blood cancer, acute myeloid leukemia (AML). Joachim Schultze, Ph.D., a research group leader at the DZNE and head of the department for genomics and immunoregulation at the LIMES Institute of the University of Bonn, stated that they investigated “the potential on the basis of a specific example.”

The study published in the journal iScience used data from more than 12,000 blood samples, which came from 105 different studies. Thus, this research makes the largest dataset to date on AML. Of all these blood samples, 4,100 derived from individuals diagnosed with AML, while the remaining samples were taken from individuals with other diseases or from healthy individuals. All of these data were eventually fed into algorithms, which then searched the transcriptome, a kind of fingerprint of gene activity, for disease-specific patterns. 

According to Science Daily, an American website that aggregates press releases and publishes lightly edited press releases about science, the data was analyzed and classified by the algorithms. Schultze reported that AI detected AML with high reliability, which is above 99% for some of the applied methods. “In fact, we tested various methods from the repertoire of machine learning and artificial intelligence. There was actually one algorithm that was particularly good, but the others were close behind,” he added. 

While this method can support conventional diagnostics and help save costs, Schultze stated that diagnosing AML still requires specialized physicians in the future. This study aims to provide experts with a tool that supports them in their diagnosis and help patients get help immediately. This is because the early stages of the symptoms of AML usually resemble those of a bad cold. “Possibly, the diagnosis would then happen earlier than it does now and therapy could start earlier,” he said.