06 January 2020

German scientists have used artificial intelligence to diagnose acute myeloid leukaemia (AML) via gene activity of cells in blood samples, in the largest study of its kind to date.

The team from the University of Bonn, Germany, examined the transcriptome, which they describe as a ‘fingerprint’ of gene activity, showing which genes are switched on in a cell.

In their study, they analysed the transcriptome relating to thousands of genes in cells from more than 12,000 blood samples. Around 4,100 of these samples were from AML patients, and the rest from people with other leukaemias and healthy controls.

Team leader, Dr Joachim Schultze, explains: “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.

“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.”

The team trained algorithms to search the transcriptome for disease-specific patterns which could be used to diagnose AML. Dr Schultze adds that the ‘hit rate’ was above 99% for some of the applied methods.

This proof-of-concept study was published in the journal iScience in December last year. The authors believe that this approach could add to conventional diagnostic methods and perhaps help doctors begin treatment faster.

Dr Schultze says: “In principle, a blood sample taken by the family doctor and sent to a laboratory for analysis could suffice. I guess that the cost would be less than 50 euros.

“However, we have not yet developed a workable test. We have only shown that the approach works in principle. So we have laid the groundwork for developing a test.

“In the long term, we intend to apply this approach to further topics, in particular in the field of dementia.”

 


 

Source: Warnat-Herresthal S, Perrakis K, Taschler B, Becker M, Baßler K, Beyer M, Günther P, Schulte-Schrepping J, Seep L, Klee K, Ulas T, Haferlach T, Mukherjee S, Schultze JL (2019) “Scalable prediction of acute myeloid leukemia using high-dimensional machine learning and blood transcriptomics”, iScience, doi: 10.1016/j.isci.2019.100780

 

Disclaimer: The news stories shared on this site are used as a way to inform our members and followers of updates and relevant information happening in Haematology. The BSH does not endorse the content of news items from external sources, and is not in a position to verify the findings, accuracy or the source of any studies mentioned. Any medical or drugs information is provided as an information resource only, and is not to be relied on for any diagnostic or treatment purposes.

News service provided by Englemed News http://www.englemed.co.uk/