Artificial intelligence has always been a hot topic of discussion in the medical sciences with a whirlwind of applications. However, know the latest curiosity is if AI can detect leukemia?
The answer is yes! Specifically, it can detect acute myeloid leukemia—a fatal disease and one of the most common forms of blood cancer.
Learn more about acute myeloid leukemia (AML):
Researchers at the German Center for Neurodegenerative Diseases (DZNE) and the University of Bonn were able to demonstrate that their AI approach can provide high reliability diagnostics and accelerate the early use of treatments. The method was based on analysis of gene activity in blood cells.
"We aimed to investigate the potential on the basis of a specific example," explains Prof. Joachim Schultze, 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. "Because this requires large amounts of data, we evaluated data on the gene activity of blood cells. Numerous studies have been carried out on this topic and the results are available through databases. Thus, there is an enormous data pool. We have collected virtually everything that is currently available."
Learn more about gene regulation:
In the study, researchers focused their approach on something called a “transcriptome” or the ‘fingerprint of gene activity’ that can determine what genes are currently active and those that are sleeping.
"The transcriptome holds important information about the condition of cells. However, classical diagnostics is based on different data. We therefore wanted to find out what an analysis of the transcriptome can achieve using artificial intelligence, that is to say trainable algorithms," said Schultze, who is member of the Bonn-based "ImmunoSensation" cluster of excellence. "In the long term, we intend to apply this approach to further topics, in particular in the field of dementia."
AML is a blood cancer that can alter bone marrow cells and evenatually enter the bloodstream—allowing both helath and tumor cells to mix freely providing a deadly hub. In the study, data retrieved from 12,000 blood samples taken from 105 different allowed researchers to determine that cells have particular gene activity patterns. Researchers were then able to add their algorithms and allow for machine learning to categorize samples as AML or no AML.
"The algorithms then searched the transcriptome for disease-specific patterns. This is a largely automated process. It's called machine learning," said Schultze. "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. 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."
Findings were published in the journal iScience and is based on the largest dataset to date for a metastudy on AML.
Source: Science Daily
