Metabolomics and machine learning used to identify COVID-19 biomarkers

One of the many mysteries that still surrounds COVID-19 is why some people get only mild, flu-like symptoms, while others suffer from life-threatening respiratory problems, viral deficiency and thin damage.

Now, researchers report in ACS ‘ Analytical chemistry has used a combination of metabolism and machine learning to identify biomarkers that may help detect COVID-19 and assess the risk of developing a serious illness.

While some previous illnesses, such as diabetes or obesity, may increase the risk of hospitalization and death from COVID-19, some otherwise healthy people also have severe symptoms. get. With the majority of the world’s population waiting for a vaccine, it could simultaneously test a patient’s ability and estimate his or her risk level to make better medical decisions, such as how closely to monitor a particular patient or where resources are allocated.

So Anderson Rocha, Rodrigo Ramos Catharino and colleagues wanted to use mass spectrametry in conjunction with an artificial intelligence device called machine learning to identify a panel of metabolites that could do just that.

The cross-sectional study included 442 patients who had different types of COVID-19 markers and tested positive by a transversease-polymerase chain reaction (RT-PCR) test, 350 controls performed a negative test for COVID-19 and 23 people suspected of having the virus despite a negative RT-PCR test.

The researchers analyzed blood plasma samples from the participants with mass spectrametry and machine learning algorithms, identifying 19 potential biomarkers for the diagnosis of COVID-19 and 26 biomarkers that were inter- contrasts between mild and severe illnesses. Of the patients with suspected COVID-19, 78.3% tested positive with the new procedure, possibly indicating that they had a false negative RT-PCR.

Although the biomarkers named, which included metabolites involved in viral recognition, inflammation, lipid remodeling and cholesterol homeostasis, need to be further tested, they may the emergence of new advertisements on how SARS-CoV-2 affects the body and causes serious illness, the researchers say. .