Amid all the coronavirus gloom and doom, it is a pleasure for us at Stopcancer.health to report some positive news on research unto cancer detection and prevention.
A new AI test that can early detect more than 50 types of cancer shows promise in a clinical study led by the Dana-Faber Cancer Institute and the Mayo Clinic in USA.
The AI test is a liquid biopsy based on DNA shed by tumour lesions into the blood. It not only gives early warning of cancer but also the type of cancer.
The researchers tested their new AI system on 1,264 individuals, about half of whom had cancer. Less than 1% of those without cancer were wrongly identified by the system as having the disease. The Boston researchers also found signs that the AI test could shed light on the type of cancer, including many cancers that are difficult to detect at an early stage. For 96% of samples deemed to show cancer, the test was able to offer a prediction for the tissue in whichthe cancer originated, with 93% of these predictions found to be correct
The test results appear to offer the possibility of a new way to screen for cancers that are otherwise difficult to detect. The efficacy of the test is now being explored in clinical trials.
New techniques such as AI blood tests have promised to be the Holy Grail of cancer research since a research team presented a paper on blood tests, (liquid biopsies), at the 2018 annual conference of the American Society of Clinical Oncologists in Chicago. The Boston research is a further refinement on AI blood test research.
With increased accuracy, AI could open up the prospect of cancer blood tests becoming a universal screening tool in cancer detection and prevention. But more research and clinical trials will be needed to achieve this.
Professor Ian Hampson comments Improved cancer diagnostics being synonymous with higher cure rates is unfortunately not quite so simple.
To quote from Srivastava et al (Natures Reviews Cancer, 2019),
“More sensitive screening methods are detecting smaller and smaller lesions, but this has not been accompanied by a comparable reduction in the
incidence of invasive cancers”.
The reasons for this are that many microscopic, so called, indolent lesions would not progress to become life-threatening. The issue is that, for many cancers, it is difficult to distinguish between indolent and aggressive disease and the ‘treat all’ approach can result in many patients being subjected to unnecessary surgeries and chemotherapy. Thus, although improved cancer diagnosis is generally a good thing, it must be applied with care.
Dana Faber Institute
National Cancer Institute
Opportunities in Cancer Research Artificial Intelligence
Nature Reviews Cancer
Cancer over diagnosis: a biological challenge and clinical dilemma.
Keywords: Coronavirus, cancer, Artificial Intelligence, blood test, liquid biopsy, chemotherapy, tumour, DNA, Ian Hampson, Dana Faber Institute, Caring Cancer Trust.