
Machine learning helps to develop a blood test that can identify 50 different types of cancer
05 May 2022
- Diagnostic tool being piloted by NHS England shows ‘impressive results’ in spotting tumours in early stages
- The test, developed by US-based company Grail, looks for chemical changes in fragments of genetic code – cell-free DNA (cfDNA) – that leak from tumours into the bloodstream
- The test correctly identified when cancer was present in 51.5% of cases, across all stages of the disease, and wrongly detected cancer in only 0.5% of cases
- the overall ability to generate a positive test result in cancers of the blood, such as lymphoma and myeloma, was 55.1%
- The test correctly identified the tissue in which the cancer was located in the body in 88.7% of cases
- “These data suggest that, if used alongside existing screening tests, the multi-cancer detection test could have a profound impact on how cancer is detected and, ultimately, on public health.”
Dr Eric Klein, chairman of the Glickman Urological and Kidney Institute at Cleveland Clinic
Click here to learn more.