As the COVID-19 pandemic rages on, people from all walks of life are being exposed to the virus. Yet, even with the wealth of knowledge at our disposal, scientists still cannot figure out the answer to the golden question: why do some people get fatally ill from COVID-19, and others don’t even realise they have it?
A large machine-learning project called Blue Brain believes they have the answer, and it lies within our blood glucose levels.
Using machine-learning models to scour through swathes of COVID-19 research papers, Blue Brain analyzed 240,000 articles and uncovered that glucose levels are the single most referenced biological variable throughout.
Their findings were published in the journal Frontiers in Public Health.
The research drew on a huge database of accessible COVID-19 research pieces, called the COVID-19 Open Research Database (CORD-19). With all the research available to scientists, those behind CORD-19 set a challenge to AI developers to process the endless data and generate new lines of inquiry into COVID-19 pathogenesis, and that’s exactly what Blue Brain did.
“With access to the CORD-19 dataset, Blue Brain quickly assembled an AI tool and targeted it to try and find out why some get sick and others not. Is it enough to just say that older people are more vulnerable? We must find out why. Why do some apparently healthy people die from COVID-19? Why do so many people die in the ICU? To answer these questions, we directed our AI to trace every step of the viral infection from the moment the virus enters the lungs until the time when the virus breaks out of the cells in the lungs and spreads throughout the body to infect the organs,” said Professor Henry Markram, corresponding author of the paper, in a statement.
“We also built the virus at an atomistic level and developed a computational model of the infection so we could try to test what was coming out of the literature. I think we did find the most likely reason why some people get sicker than others.”
The researchers strongly believe that elevated glucose levels are the most likely candidate for higher disease severity, and so they tested it on infection models. Through this, they found that high glucose levels provide the ideal conditions for the virus to bypass the initial defense of the body, in which the virus enters the respiratory system and battles the immune system in the lungs. If it can win and gain access to the alveolar cells, it can begin replicating rapidly and cause far more damage than if it falls at the first hurdle.
Elevated glucose levels were implicated in a wide array of ways that help the virus gain entry to the lung cells, alongside almost all the other stages of infection. Higher glucose resulted in the destruction of antiviral defenses in the lungs, while it also downregulates the immune system and causes a cytokine storm, which floods the infection site with immune cells. Once past these initial defenses, glucose even facilitates the entry of SARS-CoV-2 into cells via the ACE2 receptor, and results in far more serious disease, including multi-organ failure.
While not necessarily proven, the article illuminates the huge effect high glucose levels in the body may play during the pandemic and the possibility of using it as a biomarker for disease severity. Alongside the evidence against glucose, it also highlights a powerful approach to reviewing not just COVID-19 literature, but other biological topics too, which the researchers hope to further refine to limit human involvement.