At the NCRI Cancer Conference (3–5 November 2019, Glasgow, UK), researchers have presented data that demonstrates how chemical analysis of blood samples, coupled with an artificial intelligence program, could speed up brain tumor diagnosis.
Due to the ambiguous symptoms presented by individuals with brain tumors, such as headaches or memory problems, brain scans remain the only reliable technique for diagnosis. Finding new ways to efficiently diagnose and treat brain tumors remains an urgent need, particularly as the number of related mortalities is increasing.
In this research, the investigators commented on how their new test could improve brain tumor survival by making diagnosis quicker and more efficient.
“Brain tumors reduce life expectancy by an average of 20 years. That’s the highest of any cancer,” explained Paul Brennan, Senior Clinical Lecturer at the University of Edinburgh (UK). “We know that 62% of patients are diagnosed in the emergency department, even though they may have seen their general practitioner several times beforehand. This is because diagnosing brain tumors is so difficult.”
Brennan added that the difficulty with brain tumor diagnosis is that headaches could be a presenting symptom. As headaches can often be associated with something unrelated, sending lots of people for a brain scan is impractical and the bigger challenge lies with identifying who to prioritize for an urgent scan.
In line with this, Brennan has worked with Matthew Baker, who is the Chief Scientific Officer at ClinSpec Diagnostics Ltd (Glasgow, Scotland), to develop a test that could help clinicians to quickly and efficiently find those patients who are most likely to have a brain tumor.
You might also like:
The test, which relies on infrared spectroscopy to examine the chemical makeup of a person’s blood, was coupled with an artificial intelligence-based program that is able to spot the chemical clues that may indicate the likelihood of a brain tumor.
The researchers examined the new test on blood samples that were taken from 400 patients who had possible signs of a brain tumor. Of these, 40 were subsequently found to have a brain tumor.
In addition to this, the team were able to correctly identify 82% of brain tumors and 84% of individuals who did not have a brain tumor. In the case of identifying glioma, the test was demonstrated to be 92% accurate.
Baker concluded that: “These results are extremely promising because they suggest that our technique can accurately spot who is most likely to have a brain tumor and who probably does not. Because the technique requires just a small blood sample, it offers the potential to test a large number of people with suspicious symptoms and give the best indication of who needs an urgent brain scan. This could ultimately speed up diagnosis, reduce the anxiety of waiting for tests and get patients treated as quickly as possible.”
The next step of their research will include testing 600 more patients who have either been referred for a brain scan via their GP or the hospital emergency department. The team anticipate that a much smaller proportion of these patients will be diagnosed with a tumor.