Yunlei Li, Chantal B van Houten, Stefan A Boers, Ruud Jansen, Asi Cohen, Dan Engelhard, Robert Kraaij, Saskia D Hiltemann, Jie Ju, David Fernández, Cristian Mankoc, Eva González, Wouter J de Waal, Karin M de Winter-de Groot, Tom F W Wolfs, Pieter Meijers, Bart Luijk, Jan Jelrik Oosterheert, Sanjay U C Sankatsing, Aik W J Bossink, Michal Stein, Adi Klein, Jalal Ashkar, Ellen Bamberger, Isaac Srugo, Majed Odeh, Yaniv Dotan, Olga Boico, Liat Etshtein, Meital Paz, Roy Navon, Tom Friedman, Einav Simon, Tanya M Gottlieb, Ester Pri-Or, Gali Kronenfeld, Kfir Oved, Eran Eden, Andrew P Stubbs, Louis J Bont, John P Hays
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...
2022: PloS One