[en] 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.
Disciplines :
Cardiovascular & respiratory systems
Author, co-author :
Bobak, Carly A; Thayer School of Engineering, Dartmouth College, Hanover, NH, USA ; Geisel School of Medicine, Dartmouth College, Hanover, NH, USA
Kang, Lili; Thayer School of Engineering, Dartmouth College, Hanover, NH, USA
Workman, Lesley; Department of Pediatrics and Child Health, MRC Unit on Child and Adolescent Health, University of Cape Town and Red Cross War Memorial Children's Hospital, Cape Town, South Africa
Bateman, Lindy; Department of Pediatrics and Child Health, MRC Unit on Child and Adolescent Health, University of Cape Town and Red Cross War Memorial Children's Hospital, Cape Town, South Africa
Khan, Mohammad S; Thayer School of Engineering, Dartmouth College, Hanover, NH, USA
Prins, Margaretha; Department of Pediatrics and Child Health, MRC Unit on Child and Adolescent Health, University of Cape Town and Red Cross War Memorial Children's Hospital, Cape Town, South Africa
May, Lloyd; Thayer School of Engineering, Dartmouth College, Hanover, NH, USA
Franchina, Flavio ; Université de Liège - ULiège > Département de chimie (sciences) > Chimie analytique, organique et biologique ; Thayer School of Engineering, Dartmouth College, Hanover, NH, USA
Baard, Cynthia; Department of Pediatrics and Child Health, MRC Unit on Child and Adolescent Health, University of Cape Town and Red Cross War Memorial Children's Hospital, Cape Town, South Africa
Nicol, Mark P; Division of Medical Microbiology and Institute for Infectious Diseases and Molecular Medicine, University of Cape Town, Cape Town, South Africa ; School of Biomedical Sciences, University of Western Australia, Perth, Australia
Zar, Heather J; Department of Pediatrics and Child Health, MRC Unit on Child and Adolescent Health, University of Cape Town and Red Cross War Memorial Children's Hospital, Cape Town, South Africa
Hill, Jane E; Thayer School of Engineering, Dartmouth College, Hanover, NH, USA. jane.hill@ubc.ca
Language :
English
Title :
Breath can discriminate tuberculosis from other lower respiratory illness in children.
BWF - Burroughs Wellcome Fund [US-NC] [US-NC] SAMRC - South African Medical Research Council [ZA] BMGF - Bill and Melinda Gates Foundation [US-WA] [US-WA] NIH - National Institutes of Health [US-MD] [US-MD] CFF - Cystic Fibrosis Foundation [US-MD] [US-MD] NHMRC - National Health and Medical Research Council [AU]
Funding text :
The authors thank the children who participated in the study, the children’s carers, and the staff at Red Cross War Memorial Children’s Hospital for their support. C.A.B. was supported by the Burroughs Wellcome Fund institutional program grant unifying population and laboratory based sciences to Dartmouth College (Grant#1014106). This study was also supported by the Bill and Melinda Gates Foundation (to J.E.H.). HZ is supported by the SA MRC. Funding for the TB diagnostic study is from the NIH. J.E.H is supported by the US NIH, the US Cystic Fibrosis Foundation, and the Australian MRC.
Martinez, L. & Zar, H. J. Tuberculin conversion and tuberculosis disease in infants and young children from the Drakenstein Child Health Study: A call to action. S. Afr. Med. J. 108, 247 (2018). DOI: 10.7196/SAMJ.2018.v108i4.13169
Dodd, P. J., Gardiner, E., Coghlan, R. & Seddon, J. A. Burden of childhood tuberculosis in 22 high-burden countries: A mathematical modelling study. Lancet Glob. Heal. 2, e453–e459 (2014). DOI: 10.1016/S2214-109X(14)70245-1
WHO Global tuberculosis report 2018. WHO (World Health Organization, Geneva, 2019).
Zar, H. J. et al. Tuberculosis diagnosis in children using Xpert ultra on different respiratory specimens. Am. J. Respir. Crit. Care Med. 10.1164/rccm.201904-0772OC (2019). DOI: 10.1164/rccm.201904-0772OC
Connell, T. G., Zar, H. J. & Nicol, M. P. Advances in the diagnosis of pulmonary tuberculosis in HIV-infected and HIV-uninfected children. J. Infect. Dis. 204(Suppl 4), S1151-8 (2011). DOI: 10.1093/infdis/jir413
Fry, S. H., Barnabas, S. & Cotton, M. F. Tuberculosis and HIV—An update on the ‘cursed duet’ in children. Front. Pediatr. 7, 159 (2019). DOI: 10.3389/fped.2019.00159
Seong, G. M., Lee, J., Lee, J. H., Kim, J. H. & Kim, M. Usefulness of sputum induction with hypertonic saline in a real clinical practice for bacteriological yields of active pulmonary tuberculosis. Tuberc. Respir. Dis. 76, 163 (2014). DOI: 10.4046/trd.2014.76.4.163
Sakashita, K. et al. Efficiency of the Lung Flute for sputum induction in patients with presumed pulmonary tuberculosis. Clin. Respir. J. 12, 1503–1509 (2018). DOI: 10.1111/crj.12697
Graham, S. M. et al. Clinical case definitions for classification of intrathoracic tuberculosis in children: An update. Clin. Infect. Dis. 61, S179–S187 (2015). DOI: 10.1093/cid/civ581
Nicol, M. P. et al. Microbiological diagnosis of pulmonary tuberculosis in children by oral swab polymerase chain reaction. Sci. Rep. 9, 10789 (2019). DOI: 10.1038/s41598-019-47302-5
Beccaria, M. et al. Preliminary investigation of human exhaled breath for tuberculosis diagnosis by multidimensional gas chromatography—Time of flight mass spectrometry and machine learning. J. Chromatogr. B 1074–1075, 46–50 (2018). DOI: 10.1016/j.jchromb.2018.01.004
Beccaria, M. et al. Exhaled human breath analysis in active pulmonary tuberculosis diagnostics by comprehensive gas chromatography-mass spectrometry and chemometric techniques. J. Breath Res. 13, 016005 (2018). DOI: 10.1088/1752-7163/aae80e
Maiga, M. et al. Stool microbiome reveals diverse bacterial ureases as confounders of oral urea breath testing for Helicobacter pylori and Mycobacterium tuberculosis in Bamako, Mali. J. Breath Res. 10, 036012 (2016). DOI: 10.1088/1752-7155/10/3/036012
Morozov, V. N. et al. Non-invasive approach to diagnosis of pulmonary tuberculosis using microdroplets collected from exhaled air. J. Breath Res. 12, 036010 (2018). DOI: 10.1088/1752-7163/aab3f2
Phillips, M. et al. Point-of-care breath test for biomarkers of active pulmonary tuberculosis. Tuberculosis 92, 314–320 (2012). DOI: 10.1016/j.tube.2012.04.002
Phillips, M. et al. Breath biomarkers of active pulmonary tuberculosis. Tuberculosis 90, 145–51 (2010). DOI: 10.1016/j.tube.2010.01.003
Phillips, M. et al. Volatile biomarkers of pulmonary tuberculosis in the breath. Tuberculosis 87, 44–52 (2007). DOI: 10.1016/j.tube.2006.03.004
Sahota, A. S. et al. A simple breath test for tuberculosis using ion mobility: A pilot study. Tuberculosis 99, 143–146 (2016). DOI: 10.1016/j.tube.2016.05.005
Saktiawati, A. M. I., Putera, D. D., Setyawan, A., Mahendradhata, Y. & van der Werf, T. S. Diagnosis of tuberculosis through breath test: A systematic review. EBioMedicine 46, 202–214 (2019). DOI: 10.1016/j.ebiom.2019.07.056
Bruins, M. et al. Diagnosis of active tuberculosis by e-nose analysis of exhaled air. Tuberculosis 93, 232–238 (2013). DOI: 10.1016/j.tube.2012.10.002
Kolk, A. H. J. et al. Breath analysis as a potential diagnostic tool for tuberculosis. Int. J. Tuberc. Lung Dis. 16, 777–782 (2012). DOI: 10.5588/ijtld.11.0576
Nakhleh, M. K. et al. Detecting active pulmonary tuberculosis with a breath test using nanomaterial-based sensors. Eur. Respir. J. 43, 1522–1525 (2014). DOI: 10.1183/09031936.00019114
Mohamed, E. I. et al. Qualitative analysis of biological tuberculosis samples by an electronic nose-based artificial neural network. Int. J. Tuberc. Lung Dis. 21, 810–817 (2017). DOI: 10.5588/ijtld.16.0677
Zetola, N. M. et al. Diagnosis of pulmonary tuberculosis and assessment of treatment response through analyses of volatile compound patterns in exhaled breath samples. J. Infect. 74, 367 (2017). DOI: 10.1016/j.jinf.2016.12.006
Coronel Teixeira, R. et al. The potential of a portable, point-of-care electronic nose to diagnose tuberculosis. J. Infect. 75, 441–447 (2017). DOI: 10.1016/j.jinf.2017.08.003
McNerney, R. et al. Field test of a novel detection device for Mycobacterium tuberculosis antigen in cough. BMC Infect. Dis. 10, 161 (2010). DOI: 10.1186/1471-2334-10-161
Van Beek, S. C. et al. Measurement of exhaled nitric oxide as a potential screening tool for pulmonary tuberculosis. Int. J. Tuberc. Lung Dis. 15, 66 (2011).
Mgode, G. F., Cox, C. L., Mwimanzi, S. & Mulder, C. Pediatric tuberculosis detection using trained African giant pouched rats. Pediatr. Res. 84, 99–103 (2018). DOI: 10.1038/pr.2018.40
Mgode, G. F. et al. Mycobacterium tuberculosis volatiles for diagnosis of tuberculosis by Cricetomys rats. Tuberculosis 92, 535–542 (2012). DOI: 10.1016/j.tube.2012.07.006
Weetjens, B. J. et al. African pouched rats for the detection of pulmonary tuberculosis in sputum samples. Int. J. Tuberc. Lung Dis. 13, 66 (2009).
Mahoney, A. et al. Using giant African pouched rats to detect tuberculosis in human sputum samples: 2010 findings. Pan Afr. Med. J. 9, 66 (2011). DOI: 10.4314/pamj.v9i1.71204
Poling, A. et al. Tuberculosis detection by giant African pouched rats. Behav. Anal. 34, 47–54 (2011). DOI: 10.1007/BF03392234
Poling, A. et al. Active tuberculosis detection by pouched rats in 2014: More than 2,000 new patients found in two countries. J. Appl. Behav. Anal. 50, 165–169 (2017). DOI: 10.1002/jaba.356
Mulder, C. et al. Accuracy of giant African pouched rats for diagnosing tuberculosis: Comparison with culture and Xpert MTB/RIF. Int. J. Tuberc. Lung Dis. 21, 1127–1133 (2017). DOI: 10.5588/ijtld.17.0139
Mgode, G. F. et al. Mycobacterium genotypes in pulmonary tuberculosis infections and their detection by trained African giant pouched rats. Curr. Microbiol. 70, 212–218 (2015). DOI: 10.1007/s00284-014-0705-6
Ellis, H., Mulder, C., Valverde, E., Poling, A. & Edwards, T. Reproducibility of African giant pouched rats detecting Mycobacterium tuberculosis. BMC Infect. Dis. 17, 298 (2017). DOI: 10.1186/s12879-017-2347-3
Poling, A. et al. Using giant african pouched rats to detect human tuberculosis: A review. Pan Afr. Med. J. 21, 66 (2015). DOI: 10.11604/pamj.2015.21.333.2977
Mgode, G. F. et al. Diagnosis of tuberculosis by trained African giant pouched rats and confounding impact of pathogens and microflora of the respiratory tract. J. Clin. Microbiol. 50, 274–280 (2012). DOI: 10.1128/JCM.01199-11
Reither, K. et al. Evaluation of giant African pouched rats for detection of pulmonary tuberculosis in patients from a high-endemic setting. PLoS ONE 10, e0135877 (2015). DOI: 10.1371/journal.pone.0135877
Mahoney, A. et al. Giant African pouched rats (Cricetomys gambianus) as detectors of tuberculosis in human sputum: Two operational improvements. Psychol. Rec. 63, 583–594 (2013). DOI: 10.11133/j.tpr.2013.63.3.012
Poling, A. et al. Using giant African pouched rats to detect tuberculosis in human sputum samples: 2009 Findings. Am. J. Trop. Med. Hyg. 83, 1308–1310 (2010). DOI: 10.4269/ajtmh.2010.10-0180
Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001). DOI: 10.1023/A:1010933404324
Suykens, J. A. K. & Vandewalle, J. Least squares support vector machine classifiers. Neural Process. Lett. 9, 293–300 (1999). DOI: 10.1023/A:1018628609742
Van Der Linden, D. et al. Xpert MTB/RIF ultra for tuberculosis testing in children: A mini-review and commentary. Front. Pediatr. 7, 34 (2016).
van’t Hoog, A. H. et al. Optimal triage test characteristics to improve the cost-effectiveness of the Xpert MTB/RIF assay for TB diagnosis: A decision analysis. PLoS ONE 8, e82786 (2013).
Loots, D. T. An altered Mycobacterium tuberculosis metabolome induced by katG mutations resulting in isoniazid resistance. Antimicrob. Agents Chemother. 58, 2144–9 (2014). DOI: 10.1128/AAC.02344-13
Chen, X. et al. Association of smoking with metabolic volatile organic compounds in exhaled breath. Int. J. Mol. Sci. 18, 66 (2017).
Caldeira, M. et al. Profiling allergic asthma volatile metabolic patterns using a headspace-solid phase microextraction/gas chromatography based methodology. J. Chromatogr. A 1218, 3771–80 (2011). DOI: 10.1016/j.chroma.2011.04.026
Van Berkel, J. J. B. N. et al. A profile of volatile organic compounds in breath discriminates COPD patients from controls. Respir. Med. 104, 557–563 (2010). DOI: 10.1016/j.rmed.2009.10.018
Dent, A. G., Sutedja, T. G. & Zimmerman, P. V. Exhaled breath analysis for lung cancer. J. Thorac. Dis. 5(Suppl 5), S540-50 (2013).
Cazzola, M. et al. Analysis of exhaled breath fingerprints and volatile organic compounds in COPD. COPD Res. Pract. 1, 7 (2015). DOI: 10.1186/s40749-015-0010-1
Caldeira, M. et al. Allergic asthma exhaled breath metabolome: A challenge for comprehensive two-dimensional gas chromatography. J. Chromatogr. A 1254, 87–97 (2012). DOI: 10.1016/j.chroma.2012.07.023
Cristescu, S. M. et al. Screening for emphysema via exhaled volatile organic compounds. J. Breath Res. 5, 046009 (2011). DOI: 10.1088/1752-7155/5/4/046009
Kushch, I. et al. Compounds enhanced in a mass spectrometric profile of smokers’ exhaled breath versus non-smokers as determined in a pilot study using PTR-MS. J. Breath Res. 2, 026002 (2008). DOI: 10.1088/1752-7155/2/2/026002
Naz, S. et al. Identification of new benzamide inhibitor against α-subunit of tryptophan synthase from Mycobacterium tuberculosis through structure-based virtual screening, anti-tuberculosis activity and molecular dynamics simulations. J. Biomol. Struct. Dyn. 37, 1043–1053 (2019). DOI: 10.1080/07391102.2018.1448303
Joshi, S. D. et al. Pharmacophore mapping, molecular docking, chemical synthesis of some novel pyrrolyl benzamide derivatives and evaluation of their inhibitory activity against enoyl-ACP reductase (InhA) and Mycobacterium tuberculosis. Bioorg. Chem. 81, 440–453 (2018). DOI: 10.1016/j.bioorg.2018.08.035
Queralto, N. et al. Detecting cancer by breath volatile organic compound analysis: A review of array-based sensors. J. Breath Res. 8, 027112 (2014). DOI: 10.1088/1752-7155/8/2/027112
Dunn, J. J., Starke, J. R. & Revell, P. A. Laboratory diagnosis of Mycobacterium tuberculosis infection and disease in children. J. Clin. Microbiol. 54, 1434–1441 (2016). DOI: 10.1128/JCM.03043-15
Thekedar, B., Oeh, U., Szymczak, W., Hoeschen, C. & Paretzke, H. G. Influences of mixed expiratory sampling parameters on exhaled volatile organic compound concentrations. J. Breath Res. 5, 66 (2011). DOI: 10.1088/1752-7155/5/1/016001
Boshier, P. R., Priest, O. H., Hanna, G. B. & Marczin, N. Influence of respiratory variables on the on-line detection of exhaled trace gases by PTR-MS. Thorax 66, 919–920 (2011). DOI: 10.1136/thx.2011.161208
Bikov, A. et al. Standardised exhaled breath collection for the measurement of exhaled volatile organic compounds by proton transfer reaction mass spectrometry. BMC Pulm. Med. 13, 43 (2013). DOI: 10.1186/1471-2466-13-43
Lärstad, M. A. E., Torén, K., Bake, B. & Olin, A. C. Determination of ethane, pentane and isoprene in exhaled air—Effects of breath-holding, flow rate and purified air. Acta Physiol. 189, 87–98 (2007). DOI: 10.1111/j.1748-1716.2006.01624.x
Dragonieri, S. et al. An electronic nose in the discrimination of patients with asthma and controls. J. Allergy Clin. Immunol. 120, 856–862 (2007). DOI: 10.1016/j.jaci.2007.05.043
Montuschi, P. et al. Diagnostic performance of an electronic nose, fractional exhaled nitric oxide, and lung function testing in asthma. Chest 137, 790–796 (2010). DOI: 10.1378/chest.09-1836
Horváth, I. et al. A European respiratory society technical standard: Exhaled biomarkers in lung disease. Eur. Respir. J. 49, 66 (2017). DOI: 10.1183/13993003.00965-2016
Van Der Schee, M. P. et al. Effect of transportation and storage using sorbent tubes of exhaled breath samples on diagnostic accuracy of electronic nose analysis. J. Breath Res. 7, 016002 (2013). DOI: 10.1088/1752-7155/7/1/016002
Peters, R. J. B. & Bakkeren, H. A. Sorbents in sampling Stability and breakthrough measurements. Analyst 119, 71–74 (1994). DOI: 10.1039/an9941900071
Brown, V. M., Crump, D. R., Plant, N. T. & Pengelly, I. Evaluation of the stability of a mixture of volatile organic compounds on sorbents for the determination of emissions from indoor materials and products using thermal desorption/gas chromatography/mass spectrometry. J. Chromatogr. A 1350, 1–9 (2014). DOI: 10.1016/j.chroma.2014.05.011
Patil, S. F. & Lonkar, S. T. Evaluation of Tenax TA for the determination of chlorobenzene and chloronitrobenzenes in air using capillary gas chromatography and thermal desorption. J. Chromatogr. A 684, 133–142 (1994). DOI: 10.1016/S0021-9673(94)89139-7
Gjølstad, M., Bergemalm-Rynell, K., Ljungkvist, G., Thorud, S. & Molander, P. Comparison of sampling efficiency and storage stability on different sorbents for determination of solvents in occupational air. J. Sep. Sci. 27, 1531–1539 (2004). DOI: 10.1002/jssc.200401887
Harshman, S. W. et al. Storage stability of exhaled breath on Tenax TA. J. Breath Res. 10, 046008 (2016). DOI: 10.1088/1752-7155/10/4/046008
Tabe-Bordbar, S., Emad, A., Zhao, S. D. & Sinha, S. A closer look at cross-validation for assessing the accuracy of gene regulatory networks and models. Sci. Rep. 8, 6620 (2018). DOI: 10.1038/s41598-018-24937-4
R Core Team. R: A Language and Environment for Statistical Computing (2019).
Pantanowitz, A. & Marwala, T. Missing Data Imputation Through the Use of the Random Forest Algorithm, in 53–62 (Springer, Berlin, 2009). https://doi.org/10.1007/978-3-642-03156-4_6
McKnight, P. E. & Najab, J. Mann–Whitney U Test, in The Corsini Encyclopedia of Psychology 1–1 (Wiley, New York, 2010). https://doi.org/10.1002/9780470479216.corpsy0524
Benjamini, Y. & Hochberg, Y. Controlling the false discovery rate: A practical and powerful approach to multiple testing. J. R. Stat. Soc. Ser. B 57, 289–300 (1995).
Kursa, M. B., Jankowski, A. & Rudnicki, W. R. Boruta—A system for feature selection. Fundam. Inform. 101, 271–285 (2010). DOI: 10.3233/FI-2010-288
Kursa, M. B. & Rudnicki, W. R. Feature selection with the Boruta package. J. Stat. Softw. 36, 1–13 (2010). DOI: 10.18637/jss.v036.i11
Lee, E. C., Whitehead, A. L., Jacques, R. M. & Julious, S. A. The statistical interpretation of pilot trials: Should significance thresholds be reconsidered?. BMC Med. Res. Methodol. 14, 41 (2014). DOI: 10.1186/1471-2288-14-41
Althouse, A. D. Adjust for multiple comparisons? It’s not that simple. Ann. Thorac. Surg. 101, 1644–1645 (2016). DOI: 10.1016/j.athoracsur.2015.11.024
Kuhn, M. et al. caret: Classification and Regression Training (2018).
Kohavi, R. A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection (1995).
Hastie, T., Tibshirani, R. & Friedman, J. Random Forests, in 587–604 (2009). https://doi.org/10.1007/978-0-387-84858-7_15
Wickham, H. ggplot2: Elegant Graphics for Data Analysis (Springer, New York, 2016). DOI: 10.1007/978-3-319-24277-4
Kassambara, H. ggpubr: ‘ggplot2’ Based Publication Ready Plots (2020).
Gu, Z., Eils, R. & Schlesner, M. Complex heatmaps reveal patterns and correlations in multidimensional genomic data. Bioinformatics 32, 2847–2849 (2016). DOI: 10.1093/bioinformatics/btw313
