Immune-Based Prediction of COVID-19 Severity and Chronicity Decoded Using Machine Learning

Abstract

Individuals with systemic symptoms long after COVID-19 has cleared represent approximately ~10% of all COVID-19 infected individuals. Here we present a bioinformatics approach to predict and model the phases of COVID so that effective treatment strategies can be devised and monitored. We investigated 144 individuals including normal individuals and patients spanning the COVID-19 disease continuum. We collected plasma and isolated PBMCs from 29 normal individuals, 26 individuals with mild-moderate COVID-19, 25 individuals with severe COVID-19, and 64 individuals with Chronic COVID-19 symptoms. Immune subset profiling and a 14-plex cytokine panel were run on all patients. Data was analyzed using machine learning methods to predict and distinguish the groups from each other.Using a multi-class deep neural network classifier to better fit our prediction model, we recapitulated a 100% precision, 100% recall and F1 score of 1 on the test set. Moreover, a first score specific for the chronic COVID-19 patients was defined as S1 = (IFN-γ + IL-2)/ CCL4-MIP-1β. Second, a score specific for the severe COVID-19 patients was defined as S2 = (10*IL-10 + IL-6) - (IL-2 + IL-8). Severe cases are characterized by excessive inflammation and dysregulated T cell activation, recruitment, and counteracting activities. While chronic patients are characterized by a profile able to induce the activation of effector T cells with pro-inflammatory properties and the capacity of generating an effective immune response to eliminate the virus but without the proper recruitment signals to attract activated T cells.SummaryImmunologic Modeling of Severity and Chronicity of COVID-19

Persistence of SARS CoV-2 S1 Protein in CD16+ Monocytes in Post-Acute Sequelae of COVID-19 (PASC) Up to 15 Months Post-Infection

“…Another important aspect is the permanency of S1-containing cells in the circulation, intermediate monocytes express high levels of CCR5 and extravasation of these cells can occur in response to CCL4 gradients. We showed that PASC individuals have low levels of CCL4 ( 5 ) maintaining these cells in circulation until they turn into nonclassical monocytes. Moreover, IFN-γ induced CX3CL1/Fractalkine production by endothelial cells ( 23 ) creates a gradient within the vascular compartment preserving nonclassical monocytes expressing CX3CR1 in the circulation.…”

“…During pathologic conditions mediated by infectious/inflammatory reactions, the proportions of monocyte subsets vary according to the functionality of each specific subpopulation ( 6,13,15 ). Our previous results show that during early stages of the disease, PASC group have reduced classical monocyte and increased intermediate monocyte percentages compared with healthy controls ( 5 ). We find an increase in nonclassical monocytes in PASC group 6-15 months post infection, and higher percentages of intermediate and nonclassical monocytes at day 0 in severe cases, suggesting augmented classical-intermediate-nonclassical monocyte transition in both groups but with different kinetics.…”

“…It has been shown in both humans and mice that nonclassical monocytes require fractalkine (CX3CL1) and TNF to inhibit apoptosis and promote cell survival ( 22 ). Our previous data show high IFN-γ levels in PASC individuals ( 5 ), which can induce TNF-α production ( 23 ). Further, TNF-α and IFN-γ induce CX3CL1/Fractalkine production by vascular endothelial cells 24 creating the conditions to promote survival of nonclassical monocytes.…”

“…The underlying cause of PASC symptoms has remained a mystery though some data has pointed to tissue reservoirs of persistent SARS-CoV-2 as a potential mechanism ( 3,4 ). We recently reported a machine learning approach that identified the unique immunologic signature of individuals with PASC ( 5 ). In the same report, we also identified characteristic immune cell subset abnormalities that accompanied the unique cytokine/chemokine profile.…”

Post-COVID-19 Syndrome and the Potential Benefits of Exercise

“…• Recently, some studies has suggested that it is possible to identify the immunologic signatures of post-COVID-19 syndrome [60].…”