TY - JOUR
T1 - The diagnostic value of nasal microbiota and clinical parameters in a multi-parametric prediction model to differentiate bacterial versus viral infections in lower respiratory tract infections
AU - Li, Yunlei
AU - Van Houten, Chantal B.
AU - Boers, Stefan A.
AU - Jansen, Ruud
AU - Cohen, Asi
AU - Engelhard, Dan
AU - Kraaij, Robert
AU - Hiltemann, Saskia D.
AU - Ju, Jie
AU - Fernandez, David
AU - Mankoc, Cristian
AU - Gonzalez, Eva
AU - De Waal, Wouter J.
AU - De Winter-De Groot, Karin M.
AU - Wolfs, Tom F.W.
AU - Meijers, Pieter
AU - Luijk, Bart
AU - Oosterheert, Jan Jelrik
AU - Sankatsing, Sanjay U.C.
AU - Bossink, Aik W.J.
AU - Stein, Michal
AU - Klein, Adi
AU - Ashkar, Jalal
AU - Bamberger, Ellen
AU - Srugo, Isaac
AU - Odeh, Majed
AU - Dotan, Yaniv
AU - Boico, Olga
AU - Etshtein, Liat
AU - Paz, Meital
AU - Navon, Roy
AU - Friedman, Tom
AU - Simon, Einav
AU - Gottlieb, Tanya M.
AU - Pri-Or, Ester
AU - Kronenfeld, Gali
AU - Oved, Kfir
AU - Eden, Eran
AU - Stubbs, Andrew P.
AU - Bont, Louis J.
AU - Hays, John P.
N1 - Publisher Copyright:
© 2022 Li et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
PY - 2022/4/18
Y1 - 2022/4/18
N2 - Background The ability to accurately distinguish bacterial from viral infection would help clinicians better target antimicrobial therapy during suspected lower respiratory tract infections (LRTI). Although technological developments make it feasible to rapidly generate patient-specific microbiota profiles, evidence is required to show the clinical value of using microbiota data for infection diagnosis. In this study, we investigated whether adding nasal cavity microbiota profiles to readily available clinical information could improve machine learning classifiers to distinguish bacterial from viral infection in patients with LRTI. Results Various multi-parametric Random Forests classifiers were evaluated on the clinical and microbiota data of 293 LRTI patients for their prediction accuracies to differentiate bacterial from viral infection. The most predictive variable was C-reactive protein (CRP). We observed a marginal prediction improvement when 7 most prevalent nasal microbiota genera were added to the CRP model. In contrast, adding three clinical variables, absolute neutrophil count, consolidation on X-ray, and age group to the CRP model significantly improved the prediction. The best model correctly predicted 85% of the 'bacterial' patients and 82% of the 'viral' patients using 13 clinical and 3 nasal cavity microbiota genera (Staphylococcus, Moraxella, and Streptococcus). Conclusions We developed high-accuracy multi-parametric machine learning classifiers to differentiate bacterial from viral infections in LRTI patients of various ages. We demonstrated the predictive value of four easy-to-collect clinical variables which facilitate personalized and accurate clinical decision-making. We observed that nasal cavity microbiota correlate with the clinical variables and thus may not add significant value to diagnostic algorithms that aim to differentiate bacterial from viral infections.
AB - Background The ability to accurately distinguish bacterial from viral infection would help clinicians better target antimicrobial therapy during suspected lower respiratory tract infections (LRTI). Although technological developments make it feasible to rapidly generate patient-specific microbiota profiles, evidence is required to show the clinical value of using microbiota data for infection diagnosis. In this study, we investigated whether adding nasal cavity microbiota profiles to readily available clinical information could improve machine learning classifiers to distinguish bacterial from viral infection in patients with LRTI. Results Various multi-parametric Random Forests classifiers were evaluated on the clinical and microbiota data of 293 LRTI patients for their prediction accuracies to differentiate bacterial from viral infection. The most predictive variable was C-reactive protein (CRP). We observed a marginal prediction improvement when 7 most prevalent nasal microbiota genera were added to the CRP model. In contrast, adding three clinical variables, absolute neutrophil count, consolidation on X-ray, and age group to the CRP model significantly improved the prediction. The best model correctly predicted 85% of the 'bacterial' patients and 82% of the 'viral' patients using 13 clinical and 3 nasal cavity microbiota genera (Staphylococcus, Moraxella, and Streptococcus). Conclusions We developed high-accuracy multi-parametric machine learning classifiers to differentiate bacterial from viral infections in LRTI patients of various ages. We demonstrated the predictive value of four easy-to-collect clinical variables which facilitate personalized and accurate clinical decision-making. We observed that nasal cavity microbiota correlate with the clinical variables and thus may not add significant value to diagnostic algorithms that aim to differentiate bacterial from viral infections.
KW - Bacterial Infections/drug therapy
KW - C-Reactive Protein/metabolism
KW - Humans
KW - Microbiota
KW - Nose/microbiology
KW - Respiratory Tract Infections/drug therapy
KW - Virus Diseases/diagnosis
UR - http://www.scopus.com/inward/record.url?scp=85128477528&partnerID=8YFLogxK
U2 - 10.1371/journal.pone.0267140
DO - 10.1371/journal.pone.0267140
M3 - Article
C2 - 35436301
AN - SCOPUS:85128477528
SN - 1932-6203
VL - 17
SP - 1
EP - 20
JO - PLoS ONE
JF - PLoS ONE
IS - 4
M1 - e0267140
ER -