Point‐of‐care breath sample analysis by semiconductor‐based E‐Nose technology discriminates non‐infected subjects from SARS‐CoV‐2 pneumonia patients: a multi‐analyst experiment

Abstract Metal oxide sensor‐based electronic nose (E‐Nose) technology provides an easy to use method for breath analysis by detection of volatile organic compound (VOC)‐induced changes of electrical conductivity. Resulting signal patterns are then analyzed by machine learning (ML) algorithms. This s...

Full description

Saved in:
Bibliographic Details
Main Authors: Tobias Woehrle, Florian Pfeiffer, Maximilian M. Mandl, Wolfgang Sobtzick, Jörg Heitzer, Alisa Krstova, Luzie Kamm, Matthias Feuerecker, Dominique Moser, Matthias Klein, Benedikt Aulinger, Michael Dolch, Anne‐Laure Boulesteix, Daniel Lanz, Alexander Choukér
Format: Article
Language:English
Published: Wiley 2024-11-01
Series:MedComm
Subjects:
Online Access:https://doi.org/10.1002/mco2.726
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846167446528983040
author Tobias Woehrle
Florian Pfeiffer
Maximilian M. Mandl
Wolfgang Sobtzick
Jörg Heitzer
Alisa Krstova
Luzie Kamm
Matthias Feuerecker
Dominique Moser
Matthias Klein
Benedikt Aulinger
Michael Dolch
Anne‐Laure Boulesteix
Daniel Lanz
Alexander Choukér
author_facet Tobias Woehrle
Florian Pfeiffer
Maximilian M. Mandl
Wolfgang Sobtzick
Jörg Heitzer
Alisa Krstova
Luzie Kamm
Matthias Feuerecker
Dominique Moser
Matthias Klein
Benedikt Aulinger
Michael Dolch
Anne‐Laure Boulesteix
Daniel Lanz
Alexander Choukér
author_sort Tobias Woehrle
collection DOAJ
description Abstract Metal oxide sensor‐based electronic nose (E‐Nose) technology provides an easy to use method for breath analysis by detection of volatile organic compound (VOC)‐induced changes of electrical conductivity. Resulting signal patterns are then analyzed by machine learning (ML) algorithms. This study aimed to establish breath analysis by E‐Nose technology as a diagnostic tool for severe acute respiratory syndrome coronavirus type 2 (SARS‐CoV‐2) pneumonia within a multi‐analyst experiment. Breath samples of 126 subjects with (n = 63) or without SARS‐CoV‐2 pneumonia (n = 63) were collected using the ReCIVA® Breath Sampler, enriched and stored on Tenax sorption tubes, and analyzed using an E‐Nose unit with 10 sensors. ML approaches were applied by three independent data analyst teams and included a wide range of classifiers, hyperparameters, training modes, and subsets of training data. Within the multi‐analyst experiment, all teams successfully classified individuals as infected or uninfected with an averaged area under the curve (AUC) larger than 90% and misclassification error lower than 19%, and identified the same sensor as most relevant to classification success. This new method using VOC enrichment and E‐Nose analysis combined with ML can yield results similar to polymerase chain reaction (PCR) detection and superior to point‐of‐care (POC) antigen testing. Reducing the sensor set to the most relevant sensor may prove interesting for developing targeted POC testing.
format Article
id doaj-art-35d1bf2a01ba4ed990e24c3392fd6c9d
institution Kabale University
issn 2688-2663
language English
publishDate 2024-11-01
publisher Wiley
record_format Article
series MedComm
spelling doaj-art-35d1bf2a01ba4ed990e24c3392fd6c9d2024-11-14T16:14:36ZengWileyMedComm2688-26632024-11-01511n/an/a10.1002/mco2.726Point‐of‐care breath sample analysis by semiconductor‐based E‐Nose technology discriminates non‐infected subjects from SARS‐CoV‐2 pneumonia patients: a multi‐analyst experimentTobias Woehrle0Florian Pfeiffer1Maximilian M. Mandl2Wolfgang Sobtzick3Jörg Heitzer4Alisa Krstova5Luzie Kamm6Matthias Feuerecker7Dominique Moser8Matthias Klein9Benedikt Aulinger10Michael Dolch11Anne‐Laure Boulesteix12Daniel Lanz13Alexander Choukér14Department of Anesthesiology LMU University Hospital Ludwig Maximilian University Munich GermanyDepartment of Anesthesiology LMU University Hospital Ludwig Maximilian University Munich GermanyInstitute for Medical Information Processing Biometry and Epidemiology Faculty of Medicine Ludwig Maximilian University Munich GermanyLANZ GmbH Bergisch Gladbach GermanyAirbus Defence and Space GmbH Claude‐Dornier‐Straße Immenstaad GermanyAirbus Defence and Space GmbH Claude‐Dornier‐Straße Immenstaad GermanyDepartment of Anesthesiology LMU University Hospital Ludwig Maximilian University Munich GermanyDepartment of Anesthesiology LMU University Hospital Ludwig Maximilian University Munich GermanyDepartment of Anesthesiology LMU University Hospital Ludwig Maximilian University Munich GermanyEmergency Department LMU University Hospital Ludwig Maximilian University Munich GermanyDepartment of Medicine II LMU University Hospital Ludwig Maximilian University Munich GermanyDepartment of Anesthesiology LMU University Hospital Ludwig Maximilian University Munich GermanyInstitute for Medical Information Processing Biometry and Epidemiology Faculty of Medicine Ludwig Maximilian University Munich GermanyLANZ GmbH Bergisch Gladbach GermanyDepartment of Anesthesiology LMU University Hospital Ludwig Maximilian University Munich GermanyAbstract Metal oxide sensor‐based electronic nose (E‐Nose) technology provides an easy to use method for breath analysis by detection of volatile organic compound (VOC)‐induced changes of electrical conductivity. Resulting signal patterns are then analyzed by machine learning (ML) algorithms. This study aimed to establish breath analysis by E‐Nose technology as a diagnostic tool for severe acute respiratory syndrome coronavirus type 2 (SARS‐CoV‐2) pneumonia within a multi‐analyst experiment. Breath samples of 126 subjects with (n = 63) or without SARS‐CoV‐2 pneumonia (n = 63) were collected using the ReCIVA® Breath Sampler, enriched and stored on Tenax sorption tubes, and analyzed using an E‐Nose unit with 10 sensors. ML approaches were applied by three independent data analyst teams and included a wide range of classifiers, hyperparameters, training modes, and subsets of training data. Within the multi‐analyst experiment, all teams successfully classified individuals as infected or uninfected with an averaged area under the curve (AUC) larger than 90% and misclassification error lower than 19%, and identified the same sensor as most relevant to classification success. This new method using VOC enrichment and E‐Nose analysis combined with ML can yield results similar to polymerase chain reaction (PCR) detection and superior to point‐of‐care (POC) antigen testing. Reducing the sensor set to the most relevant sensor may prove interesting for developing targeted POC testing.https://doi.org/10.1002/mco2.726breath gasCOVID‐19E‐Nosemachine learningmass spectrometrymetal oxide sensor
spellingShingle Tobias Woehrle
Florian Pfeiffer
Maximilian M. Mandl
Wolfgang Sobtzick
Jörg Heitzer
Alisa Krstova
Luzie Kamm
Matthias Feuerecker
Dominique Moser
Matthias Klein
Benedikt Aulinger
Michael Dolch
Anne‐Laure Boulesteix
Daniel Lanz
Alexander Choukér
Point‐of‐care breath sample analysis by semiconductor‐based E‐Nose technology discriminates non‐infected subjects from SARS‐CoV‐2 pneumonia patients: a multi‐analyst experiment
MedComm
breath gas
COVID‐19
E‐Nose
machine learning
mass spectrometry
metal oxide sensor
title Point‐of‐care breath sample analysis by semiconductor‐based E‐Nose technology discriminates non‐infected subjects from SARS‐CoV‐2 pneumonia patients: a multi‐analyst experiment
title_full Point‐of‐care breath sample analysis by semiconductor‐based E‐Nose technology discriminates non‐infected subjects from SARS‐CoV‐2 pneumonia patients: a multi‐analyst experiment
title_fullStr Point‐of‐care breath sample analysis by semiconductor‐based E‐Nose technology discriminates non‐infected subjects from SARS‐CoV‐2 pneumonia patients: a multi‐analyst experiment
title_full_unstemmed Point‐of‐care breath sample analysis by semiconductor‐based E‐Nose technology discriminates non‐infected subjects from SARS‐CoV‐2 pneumonia patients: a multi‐analyst experiment
title_short Point‐of‐care breath sample analysis by semiconductor‐based E‐Nose technology discriminates non‐infected subjects from SARS‐CoV‐2 pneumonia patients: a multi‐analyst experiment
title_sort point of care breath sample analysis by semiconductor based e nose technology discriminates non infected subjects from sars cov 2 pneumonia patients a multi analyst experiment
topic breath gas
COVID‐19
E‐Nose
machine learning
mass spectrometry
metal oxide sensor
url https://doi.org/10.1002/mco2.726
work_keys_str_mv AT tobiaswoehrle pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT florianpfeiffer pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT maximilianmmandl pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT wolfgangsobtzick pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT jorgheitzer pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT alisakrstova pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT luziekamm pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT matthiasfeuerecker pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT dominiquemoser pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT matthiasklein pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT benediktaulinger pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT michaeldolch pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT annelaureboulesteix pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT daniellanz pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment
AT alexanderchouker pointofcarebreathsampleanalysisbysemiconductorbasedenosetechnologydiscriminatesnoninfectedsubjectsfromsarscov2pneumoniapatientsamultianalystexperiment