Application of machine learning algorithms to identify serological predictors of COVID-19 severity and outcomes

Abstract Background Critically ill hospitalized patients with COVID-19 have greater antibody titers than those with mild to moderate illness, but their association with recovery or death from COVID-19 has not been characterized. Methods In a cohort study of 178 COVID-19 patients, 73 non-hospitalized...

Full description

Saved in:
Bibliographic Details
Main Authors: Santosh Dhakal, Anna Yin, Marta Escarra-Senmarti, Zoe O. Demko, Nora Pisanic, Trevor S. Johnston, Maria Isabel Trejo-Zambrano, Kate Kruczynski, John S. Lee, Justin P. Hardick, Patrick Shea, Janna R. Shapiro, Han-Sol Park, Maclaine A. Parish, Christopher Caputo, Abhinaya Ganesan, Sarika K. Mullapudi, Stephen J. Gould, Michael J. Betenbaugh, Andrew Pekosz, Christopher D. Heaney, Annukka A. R. Antar, Yukari C. Manabe, Andrea L. Cox, Andrew H. Karaba, Felipe Andrade, Scott L. Zeger, Sabra L. Klein
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Communications Medicine
Online Access:https://doi.org/10.1038/s43856-024-00658-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846147552244662272
author Santosh Dhakal
Anna Yin
Marta Escarra-Senmarti
Zoe O. Demko
Nora Pisanic
Trevor S. Johnston
Maria Isabel Trejo-Zambrano
Kate Kruczynski
John S. Lee
Justin P. Hardick
Patrick Shea
Janna R. Shapiro
Han-Sol Park
Maclaine A. Parish
Christopher Caputo
Abhinaya Ganesan
Sarika K. Mullapudi
Stephen J. Gould
Michael J. Betenbaugh
Andrew Pekosz
Christopher D. Heaney
Annukka A. R. Antar
Yukari C. Manabe
Andrea L. Cox
Andrew H. Karaba
Felipe Andrade
Scott L. Zeger
Sabra L. Klein
author_facet Santosh Dhakal
Anna Yin
Marta Escarra-Senmarti
Zoe O. Demko
Nora Pisanic
Trevor S. Johnston
Maria Isabel Trejo-Zambrano
Kate Kruczynski
John S. Lee
Justin P. Hardick
Patrick Shea
Janna R. Shapiro
Han-Sol Park
Maclaine A. Parish
Christopher Caputo
Abhinaya Ganesan
Sarika K. Mullapudi
Stephen J. Gould
Michael J. Betenbaugh
Andrew Pekosz
Christopher D. Heaney
Annukka A. R. Antar
Yukari C. Manabe
Andrea L. Cox
Andrew H. Karaba
Felipe Andrade
Scott L. Zeger
Sabra L. Klein
author_sort Santosh Dhakal
collection DOAJ
description Abstract Background Critically ill hospitalized patients with COVID-19 have greater antibody titers than those with mild to moderate illness, but their association with recovery or death from COVID-19 has not been characterized. Methods In a cohort study of 178 COVID-19 patients, 73 non-hospitalized and 105 hospitalized patients, mucosal swabs and plasma samples were collected at hospital enrollment and up to 3 months post-enrollment (MPE) to measure virus RNA, cytokines/chemokines, binding antibodies, ACE2 binding inhibition, and Fc effector antibody responses against SARS-CoV-2. The association of demographic variables and more than 20 serological antibody measures with intubation or death due to COVID-19 was determined using machine learning algorithms. Results Predictive models reveal that IgG binding and ACE2 binding inhibition responses at 1 MPE are positively and anti-Spike antibody-mediated complement activation at enrollment is negatively associated with an increased probability of intubation or death from COVID-19 within 3 MPE. Conclusions At enrollment, serological antibody measures are more predictive than demographic variables of subsequent intubation or death among hospitalized COVID-19 patients.
format Article
id doaj-art-f7ea6c1555904c5aa73e7df2ef8983ac
institution Kabale University
issn 2730-664X
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Communications Medicine
spelling doaj-art-f7ea6c1555904c5aa73e7df2ef8983ac2024-12-01T12:42:04ZengNature PortfolioCommunications Medicine2730-664X2024-11-014111510.1038/s43856-024-00658-wApplication of machine learning algorithms to identify serological predictors of COVID-19 severity and outcomesSantosh Dhakal0Anna Yin1Marta Escarra-Senmarti2Zoe O. Demko3Nora Pisanic4Trevor S. Johnston5Maria Isabel Trejo-Zambrano6Kate Kruczynski7John S. Lee8Justin P. Hardick9Patrick Shea10Janna R. Shapiro11Han-Sol Park12Maclaine A. Parish13Christopher Caputo14Abhinaya Ganesan15Sarika K. Mullapudi16Stephen J. Gould17Michael J. Betenbaugh18Andrew Pekosz19Christopher D. Heaney20Annukka A. R. Antar21Yukari C. Manabe22Andrea L. Cox23Andrew H. Karaba24Felipe Andrade25Scott L. Zeger26Sabra L. Klein27W. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Bloomberg School of Public HealthW. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Bloomberg School of Public HealthDivision of Rheumatology, Johns Hopkins School of MedicineDepartment of Medicine, Johns Hopkins School of MedicineDepartment of Environmental Health and Engineering, Johns Hopkins Bloomberg School of Public HealthDepartment of Environmental Health and Engineering, Johns Hopkins Bloomberg School of Public HealthDivision of Rheumatology, Johns Hopkins School of MedicineDepartment of Environmental Health and Engineering, Johns Hopkins Bloomberg School of Public HealthW. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Bloomberg School of Public HealthDivision of Infectious Diseases, Department of Medicine, Johns Hopkins School of MedicineW. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Bloomberg School of Public HealthW. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Bloomberg School of Public HealthW. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Bloomberg School of Public HealthW. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Bloomberg School of Public HealthW. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Bloomberg School of Public HealthW. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Bloomberg School of Public HealthDepartment of Medicine, Johns Hopkins School of MedicineDepartment of Biological Chemistry, Johns Hopkins School of MedicineDepartment of Chemical and Biomolecular Engineering, Advanced Mammalian Biomanufacturing Innovation Center, Johns Hopkins UniversityW. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Bloomberg School of Public HealthDepartment of Environmental Health and Engineering, Johns Hopkins Bloomberg School of Public HealthDepartment of Medicine, Johns Hopkins School of MedicineW. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Bloomberg School of Public HealthW. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Bloomberg School of Public HealthDepartment of Medicine, Johns Hopkins School of MedicineDivision of Rheumatology, Johns Hopkins School of MedicineDepartment of Biostatistics, Johns Hopkins Bloomberg School of Public HealthW. Harry Feinstone Department of Molecular Microbiology and Immunology, Johns Hopkins Bloomberg School of Public HealthAbstract Background Critically ill hospitalized patients with COVID-19 have greater antibody titers than those with mild to moderate illness, but their association with recovery or death from COVID-19 has not been characterized. Methods In a cohort study of 178 COVID-19 patients, 73 non-hospitalized and 105 hospitalized patients, mucosal swabs and plasma samples were collected at hospital enrollment and up to 3 months post-enrollment (MPE) to measure virus RNA, cytokines/chemokines, binding antibodies, ACE2 binding inhibition, and Fc effector antibody responses against SARS-CoV-2. The association of demographic variables and more than 20 serological antibody measures with intubation or death due to COVID-19 was determined using machine learning algorithms. Results Predictive models reveal that IgG binding and ACE2 binding inhibition responses at 1 MPE are positively and anti-Spike antibody-mediated complement activation at enrollment is negatively associated with an increased probability of intubation or death from COVID-19 within 3 MPE. Conclusions At enrollment, serological antibody measures are more predictive than demographic variables of subsequent intubation or death among hospitalized COVID-19 patients.https://doi.org/10.1038/s43856-024-00658-w
spellingShingle Santosh Dhakal
Anna Yin
Marta Escarra-Senmarti
Zoe O. Demko
Nora Pisanic
Trevor S. Johnston
Maria Isabel Trejo-Zambrano
Kate Kruczynski
John S. Lee
Justin P. Hardick
Patrick Shea
Janna R. Shapiro
Han-Sol Park
Maclaine A. Parish
Christopher Caputo
Abhinaya Ganesan
Sarika K. Mullapudi
Stephen J. Gould
Michael J. Betenbaugh
Andrew Pekosz
Christopher D. Heaney
Annukka A. R. Antar
Yukari C. Manabe
Andrea L. Cox
Andrew H. Karaba
Felipe Andrade
Scott L. Zeger
Sabra L. Klein
Application of machine learning algorithms to identify serological predictors of COVID-19 severity and outcomes
Communications Medicine
title Application of machine learning algorithms to identify serological predictors of COVID-19 severity and outcomes
title_full Application of machine learning algorithms to identify serological predictors of COVID-19 severity and outcomes
title_fullStr Application of machine learning algorithms to identify serological predictors of COVID-19 severity and outcomes
title_full_unstemmed Application of machine learning algorithms to identify serological predictors of COVID-19 severity and outcomes
title_short Application of machine learning algorithms to identify serological predictors of COVID-19 severity and outcomes
title_sort application of machine learning algorithms to identify serological predictors of covid 19 severity and outcomes
url https://doi.org/10.1038/s43856-024-00658-w
work_keys_str_mv AT santoshdhakal applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT annayin applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT martaescarrasenmarti applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT zoeodemko applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT norapisanic applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT trevorsjohnston applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT mariaisabeltrejozambrano applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT katekruczynski applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT johnslee applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT justinphardick applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT patrickshea applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT jannarshapiro applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT hansolpark applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT maclaineaparish applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT christophercaputo applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT abhinayaganesan applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT sarikakmullapudi applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT stephenjgould applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT michaeljbetenbaugh applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT andrewpekosz applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT christopherdheaney applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT annukkaarantar applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT yukaricmanabe applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT andrealcox applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT andrewhkaraba applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT felipeandrade applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT scottlzeger applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes
AT sabralklein applicationofmachinelearningalgorithmstoidentifyserologicalpredictorsofcovid19severityandoutcomes