AI offers potential as diagnostic tool for acute myeloid leukemia
In the largest metastudy to date on acute myeloid leukemia, German researchers contend that they have demonstrated that artificial intelligence can detect this common and deadly form of blood cancer.
In the largest metastudy to date on acute myeloid leukemia, German researchers contend that they have demonstrated that artificial intelligence can detect this common and deadly form of blood cancer.
Results of their proof-of-concept study, published in the journal iScience, are based on the analysis of the gene activity of cells found in blood using 12,029 samples from 105 different studies.
“Our results support the notion that transcriptomics combined with machine learning could be used as part of an integrated -omics approach where risk prediction, differential diagnosis and subclassification of AML is achieved by genomics while diagnosis could be assisted by transcriptomic-based machine learning,” state the study’s authors.
Researchers from the German Center for Neurodegenerative Diseases (DZNE) and the University of Bonn leveraged the enormous amount of study data on the gene activity of blood cells, while focusing on the transcriptome—the set of all RNA molecules in one cell or a population of cells.
“The transcriptome holds important information about the condition of cells,” says 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. “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.”
These algorithms searched the transcriptome for disease-specific patterns in what investigators contend is the largest dataset leveraged to date for a metastudy on AML.
While the diagnosis of AML will continue to require expert physician input in the future, Schultze notes that the aim of the research was to provide clinicians with a tool that supports them in making their diagnoses.
"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,” he adds. “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.”
Although researchers have not yet developed such a test, they believe they have demonstrated that their approach works in principle and that the groundwork has been laid for developing such a test.
Results of their proof-of-concept study, published in the journal iScience, are based on the analysis of the gene activity of cells found in blood using 12,029 samples from 105 different studies.
“Our results support the notion that transcriptomics combined with machine learning could be used as part of an integrated -omics approach where risk prediction, differential diagnosis and subclassification of AML is achieved by genomics while diagnosis could be assisted by transcriptomic-based machine learning,” state the study’s authors.
Researchers from the German Center for Neurodegenerative Diseases (DZNE) and the University of Bonn leveraged the enormous amount of study data on the gene activity of blood cells, while focusing on the transcriptome—the set of all RNA molecules in one cell or a population of cells.
“The transcriptome holds important information about the condition of cells,” says 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. “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.”
These algorithms searched the transcriptome for disease-specific patterns in what investigators contend is the largest dataset leveraged to date for a metastudy on AML.
While the diagnosis of AML will continue to require expert physician input in the future, Schultze notes that the aim of the research was to provide clinicians with a tool that supports them in making their diagnoses.
"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,” he adds. “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.”
Although researchers have not yet developed such a test, they believe they have demonstrated that their approach works in principle and that the groundwork has been laid for developing such a test.
More for you
Loading data for hdm_tax_topic #better-outcomes...