Abstract

Pediatric tuberculosis (TB) remains a global health crisis. Despite progress, pediatric patients remain difficult to diagnose, with approximately half of all childhood TB patients lacking bacterial confirmation. In this pilot study (n = 31), we identify a 4-compound breathprint and subsequent machine learning model that accurately classifies children with confirmed TB (n = 10) from children with another lower respiratory tract infection (LRTI) (n = 10) with a sensitivity of 80% and specificity of 100% observed across cross validation folds. Importantly, we demonstrate that the breathprint identified an additional nine of eleven patients who had unconfirmed clinical TB and whose symptoms improved while treated for TB. While more work is necessary to validate the utility of using patient breath to diagnose pediatric TB, it shows promise as a triage instrument or paired as part of an aggregate diagnostic scheme.

Details

Title
Breath can discriminate tuberculosis from other lower respiratory illness in children
Author
Bobak, Carly A 1 ; Kang, Lili 2 ; Workman, Lesley 3 ; Bateman Lindy 3 ; Khan, Mohammad S 2 ; Prins Margaretha 3 ; May, Lloyd 2 ; Franchina, Flavio A 4 ; Baard, Cynthia 3 ; Nicol, Mark P 5 ; Zar, Heather J 3 ; Hill, Jane E 2 

 Dartmouth College, Thayer School of Engineering, Hanover, USA (GRID:grid.254880.3) (ISNI:0000 0001 2179 2404); Dartmouth College, Geisel School of Medicine, Hanover, USA (GRID:grid.254880.3) (ISNI:0000 0001 2179 2404) 
 Dartmouth College, Thayer School of Engineering, Hanover, USA (GRID:grid.254880.3) (ISNI:0000 0001 2179 2404) 
 University of Cape Town and Red Cross War Memorial Children’s Hospital, Department of Pediatrics and Child Health, MRC Unit on Child and Adolescent Health, Cape Town, South Africa (GRID:grid.415742.1) (ISNI:0000 0001 2296 3850) 
 Dartmouth College, Thayer School of Engineering, Hanover, USA (GRID:grid.254880.3) (ISNI:0000 0001 2179 2404); University of Liège, Molecular Systems, Organic and Biological Analytical Chemistry Group, Liège, Belgium (GRID:grid.4861.b) (ISNI:0000 0001 0805 7253) 
 University of Cape Town, Division of Medical Microbiology and Institute for Infectious Diseases and Molecular Medicine, Cape Town, South Africa (GRID:grid.7836.a) (ISNI:0000 0004 1937 1151); University of Western Australia, School of Biomedical Sciences, Perth, Australia (GRID:grid.1012.2) (ISNI:0000 0004 1936 7910) 
Publication year
2021
Publication date
2021
Publisher
Nature Publishing Group
e-ISSN
20452322
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2484415033
Copyright
© The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.