A research team led by the University of Strathclyde in the UK has developed an artificial intelligence (AI)-based blood test for the diagnosis of brain cancer.
The test uses infrared light to generate a ‘bio-signature’ of a blood sample and then applies AI to identify any signs of cancer.
Strathclyde researchers developed the technology in collaboration with researchers at the University of Liverpool, the Walton NHS Foundation Trust in Liverpool and the Western General Hospital in Edinburgh.
The researchers had their work published in the journal Nature Communications.
According to the publication, the blood test demonstrated favourable sensitivity and specificity in distinguishing cancer and control patients in a clinical validation study.
The university spin-out company ClinSpec Diagnostics is commercialising the blood test to allow quick diagnosis and treatment.
University of Strathclyde pure and applied chemistry department reader Matthew Baker said: “This is the first publication of data from our clinical feasibility study and it is the first demonstration that our blood test works in the clinic.
“Earlier detection of brain tumours in the diagnostic pathway brings the potential to significantly improve patient quality of life and survival, whilst also providing savings to the health services.”
Brain cancer patients often have non-specific symptoms and the final diagnosis can be time-consuming.
When the team examined samples from a 104-patient prospective cohort, the blood test was able to correctly differentiate brain cancer patients from healthy people in 87% of the cases.
Based on the findings, researchers concluded that the test could help doctors prioritise individuals who require brain scans for tumour diagnosis.
The test does not provide the final diagnosis but can aid the diagnostic process as a triage tool.