Longitudinally monitored immune biomarkers predict the timing of COVID-19 outcomes.
The clinical outcome of SARS-CoV-2 infection varies widely between individuals. Machine learning models can support decision making in healthcare by assessing fatality risk in patients that do not yet show severe signs of COVID-19. Most predictive models rely on static demographic features and clini...
Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2022-01-01
|
Series: | PLoS Computational Biology |
Online Access: | https://doi.org/10.1371/journal.pcbi.1009778 |
_version_ | 1811256574083072000 |
---|---|
author | Gorka Lasso Saad Khan Stephanie A Allen Margarette Mariano Catalina Florez Erika P Orner Jose A Quiroz Gregory Quevedo Aldo Massimi Aditi Hegde Ariel S Wirchnianski Robert H Bortz Ryan J Malonis George I Georgiev Karen Tong Natalia G Herrera Nicholas C Morano Scott J Garforth Avinash Malaviya Ahmed Khokhar Ethan Laudermilch M Eugenia Dieterle J Maximilian Fels Denise Haslwanter Rohit K Jangra Jason Barnhill Steven C Almo Kartik Chandran Jonathan R Lai Libusha Kelly Johanna P Daily Olivia Vergnolle |
author_facet | Gorka Lasso Saad Khan Stephanie A Allen Margarette Mariano Catalina Florez Erika P Orner Jose A Quiroz Gregory Quevedo Aldo Massimi Aditi Hegde Ariel S Wirchnianski Robert H Bortz Ryan J Malonis George I Georgiev Karen Tong Natalia G Herrera Nicholas C Morano Scott J Garforth Avinash Malaviya Ahmed Khokhar Ethan Laudermilch M Eugenia Dieterle J Maximilian Fels Denise Haslwanter Rohit K Jangra Jason Barnhill Steven C Almo Kartik Chandran Jonathan R Lai Libusha Kelly Johanna P Daily Olivia Vergnolle |
author_sort | Gorka Lasso |
collection | DOAJ |
description | The clinical outcome of SARS-CoV-2 infection varies widely between individuals. Machine learning models can support decision making in healthcare by assessing fatality risk in patients that do not yet show severe signs of COVID-19. Most predictive models rely on static demographic features and clinical values obtained upon hospitalization. However, time-dependent biomarkers associated with COVID-19 severity, such as antibody titers, can substantially contribute to the development of more accurate outcome models. Here we show that models trained on immune biomarkers, longitudinally monitored throughout hospitalization, predicted mortality and were more accurate than models based on demographic and clinical data upon hospital admission. Our best-performing predictive models were based on the temporal analysis of anti-SARS-CoV-2 Spike IgG titers, white blood cell (WBC), neutrophil and lymphocyte counts. These biomarkers, together with C-reactive protein and blood urea nitrogen levels, were found to correlate with severity of disease and mortality in a time-dependent manner. Shapley additive explanations of our model revealed the higher predictive value of day post-symptom onset (PSO) as hospitalization progresses and showed how immune biomarkers contribute to predict mortality. In sum, we demonstrate that the kinetics of immune biomarkers can inform clinical models to serve as a powerful monitoring tool for predicting fatality risk in hospitalized COVID-19 patients, underscoring the importance of contextualizing clinical parameters according to their time post-symptom onset. |
first_indexed | 2024-04-12T17:42:20Z |
format | Article |
id | doaj.art-6e20ef620826496397e91cdbc58ba169 |
institution | Directory Open Access Journal |
issn | 1553-734X 1553-7358 |
language | English |
last_indexed | 2024-04-12T17:42:20Z |
publishDate | 2022-01-01 |
publisher | Public Library of Science (PLoS) |
record_format | Article |
series | PLoS Computational Biology |
spelling | doaj.art-6e20ef620826496397e91cdbc58ba1692022-12-22T03:22:45ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582022-01-01181e100977810.1371/journal.pcbi.1009778Longitudinally monitored immune biomarkers predict the timing of COVID-19 outcomes.Gorka LassoSaad KhanStephanie A AllenMargarette MarianoCatalina FlorezErika P OrnerJose A QuirozGregory QuevedoAldo MassimiAditi HegdeAriel S WirchnianskiRobert H BortzRyan J MalonisGeorge I GeorgievKaren TongNatalia G HerreraNicholas C MoranoScott J GarforthAvinash MalaviyaAhmed KhokharEthan LaudermilchM Eugenia DieterleJ Maximilian FelsDenise HaslwanterRohit K JangraJason BarnhillSteven C AlmoKartik ChandranJonathan R LaiLibusha KellyJohanna P DailyOlivia VergnolleThe clinical outcome of SARS-CoV-2 infection varies widely between individuals. Machine learning models can support decision making in healthcare by assessing fatality risk in patients that do not yet show severe signs of COVID-19. Most predictive models rely on static demographic features and clinical values obtained upon hospitalization. However, time-dependent biomarkers associated with COVID-19 severity, such as antibody titers, can substantially contribute to the development of more accurate outcome models. Here we show that models trained on immune biomarkers, longitudinally monitored throughout hospitalization, predicted mortality and were more accurate than models based on demographic and clinical data upon hospital admission. Our best-performing predictive models were based on the temporal analysis of anti-SARS-CoV-2 Spike IgG titers, white blood cell (WBC), neutrophil and lymphocyte counts. These biomarkers, together with C-reactive protein and blood urea nitrogen levels, were found to correlate with severity of disease and mortality in a time-dependent manner. Shapley additive explanations of our model revealed the higher predictive value of day post-symptom onset (PSO) as hospitalization progresses and showed how immune biomarkers contribute to predict mortality. In sum, we demonstrate that the kinetics of immune biomarkers can inform clinical models to serve as a powerful monitoring tool for predicting fatality risk in hospitalized COVID-19 patients, underscoring the importance of contextualizing clinical parameters according to their time post-symptom onset.https://doi.org/10.1371/journal.pcbi.1009778 |
spellingShingle | Gorka Lasso Saad Khan Stephanie A Allen Margarette Mariano Catalina Florez Erika P Orner Jose A Quiroz Gregory Quevedo Aldo Massimi Aditi Hegde Ariel S Wirchnianski Robert H Bortz Ryan J Malonis George I Georgiev Karen Tong Natalia G Herrera Nicholas C Morano Scott J Garforth Avinash Malaviya Ahmed Khokhar Ethan Laudermilch M Eugenia Dieterle J Maximilian Fels Denise Haslwanter Rohit K Jangra Jason Barnhill Steven C Almo Kartik Chandran Jonathan R Lai Libusha Kelly Johanna P Daily Olivia Vergnolle Longitudinally monitored immune biomarkers predict the timing of COVID-19 outcomes. PLoS Computational Biology |
title | Longitudinally monitored immune biomarkers predict the timing of COVID-19 outcomes. |
title_full | Longitudinally monitored immune biomarkers predict the timing of COVID-19 outcomes. |
title_fullStr | Longitudinally monitored immune biomarkers predict the timing of COVID-19 outcomes. |
title_full_unstemmed | Longitudinally monitored immune biomarkers predict the timing of COVID-19 outcomes. |
title_short | Longitudinally monitored immune biomarkers predict the timing of COVID-19 outcomes. |
title_sort | longitudinally monitored immune biomarkers predict the timing of covid 19 outcomes |
url | https://doi.org/10.1371/journal.pcbi.1009778 |
work_keys_str_mv | AT gorkalasso longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT saadkhan longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT stephanieaallen longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT margarettemariano longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT catalinaflorez longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT erikaporner longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT joseaquiroz longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT gregoryquevedo longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT aldomassimi longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT aditihegde longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT arielswirchnianski longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT roberthbortz longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT ryanjmalonis longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT georgeigeorgiev longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT karentong longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT nataliagherrera longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT nicholascmorano longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT scottjgarforth longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT avinashmalaviya longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT ahmedkhokhar longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT ethanlaudermilch longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT meugeniadieterle longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT jmaximilianfels longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT denisehaslwanter longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT rohitkjangra longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT jasonbarnhill longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT stevencalmo longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT kartikchandran longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT jonathanrlai longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT libushakelly longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT johannapdaily longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes AT oliviavergnolle longitudinallymonitoredimmunebiomarkerspredictthetimingofcovid19outcomes |