"How does AI spot long COVID in blood samples?"
"David Putrino and his team divided participants into three groups: those with no prior COVID infection, those who fully recovered, and those with long COVID symptoms for at least four months after infection."
"A machine learning algorithm was applied to determine which biomarkers best identified long COVID." "The algorithm differentiated between those with and without long COVID with 96 percent accuracy, detecting unique features in long COVID patients' blood. The biggest differences involved abnormal immune cell activity, reactivated dormant herpes viruses like Epstein-Barr, and reduced cortisol levels."
The article is paywalled, but we get some clues from the abstract.
"Marked differences were noted in circulating myeloid and lymphocyte populations relative to matched controls, as well as evidence of exaggerated humoral responses directed against SARS-CoV-2 among participants with long COVID."
"Myeloid" cells are bone marrow cells.
"Lymphocytes" are a type of white blood cell.
"Humoral" means "relating to the body fluids, especially with regard to immune responses involving antibodies in body fluids as distinct from cells."
"Further, higher antibody responses directed against non-SARS-CoV-2 viral pathogens were observed among individuals with long COVID, particularly Epstein-Barr virus. Levels of soluble immune mediators and hormones varied among groups, with cortisol levels being lower among participants with long COVID."
Long COVID might be diagnosed with nearly 100% accuracy: study | ZeroHedge
