eNose breath prints as a surrogate biomarker for classifying patients with asthma by atopy

U-BIOPRED Study Group; Amsterdam UMC Breath Research Group

doi:10.1016/j.jaci.2020.05.038

eNose breath prints as a surrogate biomarker for classifying patients with asthma by atopy

U-BIOPRED Study Group
, Amsterdam UMC Breath Research Group

Research output: Contribution to Journal › Article › Academic › peer-review

Abstract

© 2020 The AuthorsBackground: Electronic noses (eNoses) are emerging point-of-care tools that may help in the subphenotyping of chronic respiratory diseases such as asthma. Objective: We aimed to investigate whether eNoses can classify atopy in pediatric and adult patients with asthma. Methods: Participants with asthma and/or wheezing from 4 independent cohorts were included; BreathCloud participants (n = 429), Unbiased Biomarkers in Prediction of Respiratory Disease Outcomes adults (n = 96), Unbiased Biomarkers in Prediction of Respiratory Disease Outcomes pediatric participants (n = 100), and Pharmacogenetics of Asthma Medication in Children: Medication with Anti-Inflammatory Effects 2 participants (n = 30). Atopy was defined as a positive skin prick test result (≥3 mm) and/or a positive specific IgE level (≥0.35 kU/L) for common allergens. Exhaled breath profiles were measured by using either an integrated eNose platform or the SpiroNose. Data were divided into 2 training and 2 validation sets according to the technology used. Supervised data analysis involved the use of 3 different machine learning algorithms to classify patients with atopic versus nonatopic asthma with reporting of areas under the receiver operating characteristic curves as a measure of model performance. In addition, an unsupervised approach was performed by using a bayesian network to reveal data-driven relationships between eNose volatile organic compound profiles and asthma characteristics. Results: Breath profiles of 655 participants (n = 601 adults and school-aged children with asthma and 54 preschool children with wheezing [68.2% of whom were atopic]) were included in this study. Machine learning models utilizing volatile organic compound profiles discriminated between atopic and nonatopic participants with areas under the receiver operating characteristic curves of at least 0.84 and 0.72 in the training and validation sets, respectively. The unsupervised approach revealed that breath profiles classifying atopy are not confounded by other patient characteristics. Conclusion: eNoses accurately detect atopy in individuals with asthma and wheezing in cohorts with different age groups and could be used in asthma phenotyping.

Original language	English
Pages (from-to)	1045-1055
Journal	Journal of Allergy and Clinical Immunology
Volume	146
Issue number	5
DOIs	https://doi.org/10.1016/j.jaci.2020.05.038
Publication status	Published - 1 Nov 2020
Externally published	Yes

Funding

Disclosure of potential conflict of interest: R. de Vries reports personal fees and grants from Breathomix during the conduct of the study. J. H. Riley is employed by and owns shares in GlaxoSmithKline. K. F. Chung has received honoraria for participating in advisory board meetings of GlaxoSmithKline, AstraZeneca, Novartis, Merck, Boehringer Ingelheim, and TEVA regarding treatments for asthma and chronic obstructive pulmonary disease and has also been remunerated for speaking engagements. R. Djukanovic reports receiving fees for lectures at symposia organized by Novartis, AstraZeneca, and TEVA, as well as consultation fees from TEVA and Novartis for service as a member of advisory boards and participation in a scientific discussion about asthma organized by GlaxoSmithKline; in addition, R. Djukanovic is a cofounder and current consultant of and has shares in Synairgen, a University of Southampton spinout company. L. J. Fleming reports grants from Asthma UK and fees for expert consultation and speakers fees from AstraZeneca, GlaxoSmithKline, Novartis, Teva, Boehringer Ingelheim, Respiri, and Sanofi that were paid directly to her institution and outside of the submitted work. C. Murray reports personal fees and grants from GlaxoSmithKline, personal fees from Novartis and Thermo Fisher, and grants from Boehringer Ingelheim outside the submitted work. U. Frey reports grants from the Swiss National Science Foundation during the conduct of the study. F. Singer reports personal fees from Vertex and Novartis outside the submitted work. G. Roberts reports grants from the European Union Innovative Medicines Initiative during the conduct of the study. S.-E. Dahlén reports personal fees from AstraZeneca, GlaxoSmithKline, Merck & Co, Novartis, Regeneron, Sanofi, and Teva outside the submitted work. S. J. Fowler reports personal fees and nonfinancial support from AstraZeneca; grants and personal fees from Boehringer Ingelheim; and personal fees from Novartis, Teva, and Chiesi outside the submitted work. K. Knipping is an employee of Danone Nutricia Research. P. J. Sterk reports grants from the Public-Private Innovative Medicines Initiative covered by the European Union and the European Federation of Pharmaceutical Industries and Associations during the conduct of the study, as well as grants from being a scientific advisor and having a formally inconsiderable interest in the start-up company Breathomix BV outside the submitted work. A. H. Maitland-van der Zee reports grants and personal fees from Boehringer Ingelheim, grants from Chiesi, personal fees from AstraZeneca, grants from Vertex, and grants and personal fees from GlaxoSmithKline outside the submitted work. The rest of the authors declare that they have no relevant conflicts of interest. U-BIOPRED has received funding from the Innovative Medicines Initiative Joint Undertaking (under grant agreement no. 115010), the resources of which are composed of financial contributions from the European Union's Seventh Framework Programme (FP7/2007-2013) and in-kind contributions of companies belonging to the European Federation of Pharmaceutical Industries and Associations (www.imi.europa.eu). The PACMAN study was funded by an unrestricted GlaxoSmithKline grant. BreathCloud was sponsored by the public charity Dutch Vriendenloterij. The salary of M.I.A. was sponsored by Egyptian Government PhD Research Scholarships. Disclosure of potential conflict of interest: R. de Vries reports personal fees and grants from Breathomix during the conduct of the study. J. H. Riley is employed by and owns shares in GlaxoSmithKline. K. F. Chung has received honoraria for participating in advisory board meetings of GlaxoSmithKline, AstraZeneca, Novartis, Merck, Boehringer Ingelheim, and TEVA regarding treatments for asthma and chronic obstructive pulmonary disease and has also been remunerated for speaking engagements. R. Djukanovic reports receiving fees for lectures at symposia organized by Novartis, AstraZeneca, and TEVA, as well as consultation fees from TEVA and Novartis for service as a member of advisory boards and participation in a scientific discussion about asthma organized by GlaxoSmithKline; in addition, R. Djukanovic is a cofounder and current consultant of and has shares in Synairgen, a University of Southampton spinout company. L. J. Fleming reports grants from Asthma UK and fees for expert consultation and speakers fees from AstraZeneca, GlaxoSmithKline, Novartis, Teva, Boehringer Ingelheim, Respiri, and Sanofi that were paid directly to her institution and outside of the submitted work. C. Murray reports personal fees and grants from GlaxoSmithKline, personal fees from Novartis and Thermo Fisher, and grants from Boehringer Ingelheim outside the submitted work. U. Frey reports grants from the Swiss National Science Foundation during the conduct of the study. F. Singer reports personal fees from Vertex and Novartis outside the submitted work. G. Roberts reports grants from the European Union Innovative Medicines Initiative during the conduct of the study. S.-E. Dahl?n reports personal fees from AstraZeneca, GlaxoSmithKline, Merck & Co, Novartis, Regeneron, Sanofi, and Teva outside the submitted work. S. J. Fowler reports personal fees and nonfinancial support from AstraZeneca; grants and personal fees from Boehringer Ingelheim; and personal fees from Novartis, Teva, and Chiesi outside the submitted work. K. Knipping is an employee of Danone Nutricia Research. P. J. Sterk reports grants from the Public-Private Innovative Medicines Initiative covered by the European Union and the European Federation of Pharmaceutical Industries and Associations during the conduct of the study, as well as grants from being a scientific advisor and having a formally inconsiderable interest in the start-up company Breathomix BV outside the submitted work. A. H. Maitland-van der Zee reports grants and personal fees from Boehringer Ingelheim, grants from Chiesi, personal fees from AstraZeneca, grants from Vertex, and grants and personal fees from GlaxoSmithKline outside the submitted work. The rest of the authors declare that they have no relevant conflicts of interest. U-BIOPRED has received funding from the Innovative Medicines Initiative Joint Undertaking (under grant agreement no. 115010 ), the resources of which are composed of financial contributions from the European Union’s Seventh Framework Programme ( FP7/2007-2013 ) and in-kind contributions of companies belonging to the European Federation of Pharmaceutical Industries and Associations ( www.imi.europa.eu ). The PACMAN study was funded by an unrestricted GlaxoSmithKline grant. BreathCloud was sponsored by the public charity Dutch Vriendenloterij. The salary of M.I.A. was sponsored by Egyptian Government PhD Research Scholarships.

Funders	Funder number
Danone Nutricia Research
FP7/2007
Merck & Co
Public-Private Innovative Medicines Initiative
AstraZeneca
GlaxoSmithKline
Merck
Novartis
Teva Pharmaceutical Industries
Boehringer Ingelheim
Seventh Framework Programme
European Federation of Pharmaceutical Industries and Associations
Asthma UK
University of Southampton
European Commission
Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
Seventh Framework Programme
Innovative Medicines Initiative	115010

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 16 Peace, Justice and Strong Institutions

Access to Document

10.1016/j.jaci.2020.05.038

Persistent URL (handle)

Persistent link

Cite this

@article{305e2af08b8c42f7bcff3bb0766ff823,

title = "eNose breath prints as a surrogate biomarker for classifying patients with asthma by atopy",

abstract = "{\textcopyright} 2020 The AuthorsBackground: Electronic noses (eNoses) are emerging point-of-care tools that may help in the subphenotyping of chronic respiratory diseases such as asthma. Objective: We aimed to investigate whether eNoses can classify atopy in pediatric and adult patients with asthma. Methods: Participants with asthma and/or wheezing from 4 independent cohorts were included; BreathCloud participants (n = 429), Unbiased Biomarkers in Prediction of Respiratory Disease Outcomes adults (n = 96), Unbiased Biomarkers in Prediction of Respiratory Disease Outcomes pediatric participants (n = 100), and Pharmacogenetics of Asthma Medication in Children: Medication with Anti-Inflammatory Effects 2 participants (n = 30). Atopy was defined as a positive skin prick test result (≥3 mm) and/or a positive specific IgE level (≥0.35 kU/L) for common allergens. Exhaled breath profiles were measured by using either an integrated eNose platform or the SpiroNose. Data were divided into 2 training and 2 validation sets according to the technology used. Supervised data analysis involved the use of 3 different machine learning algorithms to classify patients with atopic versus nonatopic asthma with reporting of areas under the receiver operating characteristic curves as a measure of model performance. In addition, an unsupervised approach was performed by using a bayesian network to reveal data-driven relationships between eNose volatile organic compound profiles and asthma characteristics. Results: Breath profiles of 655 participants (n = 601 adults and school-aged children with asthma and 54 preschool children with wheezing [68.2\% of whom were atopic]) were included in this study. Machine learning models utilizing volatile organic compound profiles discriminated between atopic and nonatopic participants with areas under the receiver operating characteristic curves of at least 0.84 and 0.72 in the training and validation sets, respectively. The unsupervised approach revealed that breath profiles classifying atopy are not confounded by other patient characteristics. Conclusion: eNoses accurately detect atopy in individuals with asthma and wheezing in cohorts with different age groups and could be used in asthma phenotyping.",

author = "M.I. Abdel-Aziz and P. Brinkman and S.J.H. Vijverberg and A.H. Neerincx and \{de Vries\}, R. and Y.W.F. Dagelet and J.H. Riley and S. Hashimoto and P. Montuschi and K.F. Chung and R. Djukanovic and L.J. Fleming and C.S. Murray and U. Frey and A. Bush and F. Singer and G. Hedlin and G. Roberts and S.-E. Dahl{\'e}n and I.M. Adcock and S.J. Fowler and K. Knipping and P.J. Sterk and A.D. Kraneveld and \{Maitland-van der Zee\}, A.H. and \{U-BIOPRED Study Group\} and \{Amsterdam UMC Breath Research Group\}",

year = "2020",

month = nov,

day = "1",

doi = "10.1016/j.jaci.2020.05.038",

language = "English",

volume = "146",

pages = "1045--1055",

journal = "Journal of Allergy and Clinical Immunology",

issn = "0091-6749",

publisher = "Elsevier Inc.",

number = "5",

}

TY - JOUR

T1 - eNose breath prints as a surrogate biomarker for classifying patients with asthma by atopy

AU - Abdel-Aziz, M.I.

AU - Brinkman, P.

AU - Vijverberg, S.J.H.

AU - Neerincx, A.H.

AU - de Vries, R.

AU - Dagelet, Y.W.F.

AU - Riley, J.H.

AU - Hashimoto, S.

AU - Montuschi, P.

AU - Chung, K.F.

AU - Djukanovic, R.

AU - Fleming, L.J.

AU - Murray, C.S.

AU - Frey, U.

AU - Bush, A.

AU - Singer, F.

AU - Hedlin, G.

AU - Roberts, G.

AU - Dahlén, S.-E.

AU - Adcock, I.M.

AU - Fowler, S.J.

AU - Knipping, K.

AU - Sterk, P.J.

AU - Kraneveld, A.D.

AU - Maitland-van der Zee, A.H.

AU - U-BIOPRED Study Group

AU - Amsterdam UMC Breath Research Group

PY - 2020/11/1

Y1 - 2020/11/1

N2 - © 2020 The AuthorsBackground: Electronic noses (eNoses) are emerging point-of-care tools that may help in the subphenotyping of chronic respiratory diseases such as asthma. Objective: We aimed to investigate whether eNoses can classify atopy in pediatric and adult patients with asthma. Methods: Participants with asthma and/or wheezing from 4 independent cohorts were included; BreathCloud participants (n = 429), Unbiased Biomarkers in Prediction of Respiratory Disease Outcomes adults (n = 96), Unbiased Biomarkers in Prediction of Respiratory Disease Outcomes pediatric participants (n = 100), and Pharmacogenetics of Asthma Medication in Children: Medication with Anti-Inflammatory Effects 2 participants (n = 30). Atopy was defined as a positive skin prick test result (≥3 mm) and/or a positive specific IgE level (≥0.35 kU/L) for common allergens. Exhaled breath profiles were measured by using either an integrated eNose platform or the SpiroNose. Data were divided into 2 training and 2 validation sets according to the technology used. Supervised data analysis involved the use of 3 different machine learning algorithms to classify patients with atopic versus nonatopic asthma with reporting of areas under the receiver operating characteristic curves as a measure of model performance. In addition, an unsupervised approach was performed by using a bayesian network to reveal data-driven relationships between eNose volatile organic compound profiles and asthma characteristics. Results: Breath profiles of 655 participants (n = 601 adults and school-aged children with asthma and 54 preschool children with wheezing [68.2% of whom were atopic]) were included in this study. Machine learning models utilizing volatile organic compound profiles discriminated between atopic and nonatopic participants with areas under the receiver operating characteristic curves of at least 0.84 and 0.72 in the training and validation sets, respectively. The unsupervised approach revealed that breath profiles classifying atopy are not confounded by other patient characteristics. Conclusion: eNoses accurately detect atopy in individuals with asthma and wheezing in cohorts with different age groups and could be used in asthma phenotyping.

AB - © 2020 The AuthorsBackground: Electronic noses (eNoses) are emerging point-of-care tools that may help in the subphenotyping of chronic respiratory diseases such as asthma. Objective: We aimed to investigate whether eNoses can classify atopy in pediatric and adult patients with asthma. Methods: Participants with asthma and/or wheezing from 4 independent cohorts were included; BreathCloud participants (n = 429), Unbiased Biomarkers in Prediction of Respiratory Disease Outcomes adults (n = 96), Unbiased Biomarkers in Prediction of Respiratory Disease Outcomes pediatric participants (n = 100), and Pharmacogenetics of Asthma Medication in Children: Medication with Anti-Inflammatory Effects 2 participants (n = 30). Atopy was defined as a positive skin prick test result (≥3 mm) and/or a positive specific IgE level (≥0.35 kU/L) for common allergens. Exhaled breath profiles were measured by using either an integrated eNose platform or the SpiroNose. Data were divided into 2 training and 2 validation sets according to the technology used. Supervised data analysis involved the use of 3 different machine learning algorithms to classify patients with atopic versus nonatopic asthma with reporting of areas under the receiver operating characteristic curves as a measure of model performance. In addition, an unsupervised approach was performed by using a bayesian network to reveal data-driven relationships between eNose volatile organic compound profiles and asthma characteristics. Results: Breath profiles of 655 participants (n = 601 adults and school-aged children with asthma and 54 preschool children with wheezing [68.2% of whom were atopic]) were included in this study. Machine learning models utilizing volatile organic compound profiles discriminated between atopic and nonatopic participants with areas under the receiver operating characteristic curves of at least 0.84 and 0.72 in the training and validation sets, respectively. The unsupervised approach revealed that breath profiles classifying atopy are not confounded by other patient characteristics. Conclusion: eNoses accurately detect atopy in individuals with asthma and wheezing in cohorts with different age groups and could be used in asthma phenotyping.

UR - https://www.scopus.com/pages/publications/85088219111

UR - https://www.scopus.com/pages/publications/85088219111#tab=citedBy

U2 - 10.1016/j.jaci.2020.05.038

DO - 10.1016/j.jaci.2020.05.038

M3 - Article

SN - 0091-6749

VL - 146

SP - 1045

EP - 1055

JO - Journal of Allergy and Clinical Immunology

JF - Journal of Allergy and Clinical Immunology

IS - 5

ER -

eNose breath prints as a surrogate biomarker for classifying patients with asthma by atopy

Abstract

Funding

UN SDGs

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this