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 learn...

Full description

Saved in:

Bibliographic Details
Published in:	Nature communications Vol. 13; no. 1; pp. 915 - 13
Main Authors:	Mueller, Yvonne M., Schrama, Thijs J., Ruijten, Rik, Schreurs, Marco W. J., Grashof, Dwin G. B., van de Werken, Harmen J. G., Lasinio, Giovanna Jona, Álvarez-Sierra, Daniel, Kiernan, Caoimhe H., Castro Eiro, Melisa D., van Meurs, Marjan, Brouwers-Haspels, Inge, Zhao, Manzhi, Li, Ling, de Wit, Harm, Ouzounis, Christos A., Wilmsen, Merel E. P., Alofs, Tessa M., Laport, Danique A., van Wees, Tamara, Kraker, Geoffrey, Jaimes, Maria C., Van Bockstael, Sebastiaan, Hernández-González, Manuel, Rokx, Casper, Rijnders, Bart J. A., Pujol-Borrell, Ricardo, Katsikis, Peter D.
Format:	Journal Article
Language:	English
Published:	London Nature Publishing Group UK 17-02-2022 Nature Publishing Group Nature Portfolio
Subjects:	631/250/24 631/553/2695 692/53/2423 692/699/255/2514 Aged Antibodies Antibodies, Viral - blood Antiviral agents Cluster analysis Clustering Coronavirus Nucleocapsid Proteins - immunology Coronaviruses COVID-19 COVID-19 - pathology Cytokines Cytokines - blood Disease Progression Electrical impedance Female Health risks Hospitalization Humanities and Social Sciences Humans Identification methods Immune response Immune system Immunoglobulin A - blood Immunoglobulin G - blood Immunoglobulin M - blood Immunology Immunophenotyping - methods Inflammation Learning algorithms Longitudinal studies Machine Learning Male Middle Aged multidisciplinary Patients Phenotypes Phenotyping Phosphoproteins - immunology SARS-CoV-2 - immunology Science Science (multidisciplinary) Severe acute respiratory syndrome Severe acute respiratory syndrome coronavirus 2 Severity of Illness Index Viral diseases
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	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.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	2041-1723 2041-1723
DOI:	10.1038/s41467-022-28621-0