Stratification of hospitalized COVID-19 patients into clinical severity progression groups by immuno-phenotyping and machine learning

Quantitative or qualitative differences in immunity may drive clinical severity in COVID-19. Although longitudinal studies to record the course of immunological changes are ample, they do not necessarily predict clinical progression at the time of hospital admission. Here we show, by a machine learning approach using serum pro-inflammatory, anti-inflammatory and anti-viral cytokine and anti-SARS-CoV-2 antibody measurements as input data, that COVID-19 patients cluster into three distinct immune phenotype groups. These immune-types, determined by unsupervised hierarchical clustering that is agnostic to severity, predict clinical course. The identified immune-types do not associate with disease duration at hospital admittance, but rather reflect variations in the nature and kinetics of individual patient's immune response. Thus, our work provides an immune-type based scheme to stratify COVID-19 patients at hospital admittance into high and low risk clinical categories with distinct cytokine and antibody profiles that may guide personalized therapy. Developing predictive methods to identify patients with high risk of severe COVID-19 disease is of crucial importance. Authors show here that by measuring anti-SARS-CoV-2 antibody and cytokine levels at the time of hospital admission and integrating the data by unsupervised hierarchical clustering/machine learning, it is possible to predict unfavourable outcome.

Automated summary

This study demonstrates that by measuring anti-SARS-CoV-2 antibody and cytokine levels at the time of hospital admission and using unsupervised hierarchical clustering/machine learning, it is possible to predict unfavorable outcomes in COVID-19 patients.