Detecting multiple sclerosis via breath analysis using an eNose, a pilot study

In the present study we investigated whether multiple sclerosis (MS) can be detected via exhaled breath analysis using an electronic nose (eNose). The AeonoseTM (an eNose, The eNose Company, Zutphen, the Netherlands) is a diagnostic test device to detect patterns of volatile organic compounds in exh...

Full description

Saved in:
Bibliographic Details
Published in:Journal of breath research 2021-04, Vol.15 (2), p.27101
Main Authors: Ettema, A R, Lenders, M W P M, Vliegen, J, Slettenaar, A, Tjepkema-Cloostermans, M C, de Vos, C C
Format: Article
Language:English
Subjects:
Breath Tests
Electronic Nose
exhaled breath analysis
Humans
Multiple Sclerosis
multiple sclerosis (MS)
Pilot Projects
Prospective Studies
VOCs
Volatile Organic Compounds
volatile organic compounds (VOCs)
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the present study we investigated whether multiple sclerosis (MS) can be detected via exhaled breath analysis using an electronic nose (eNose). The AeonoseTM (an eNose, The eNose Company, Zutphen, the Netherlands) is a diagnostic test device to detect patterns of volatile organic compounds in exhaled breath. We evaluated whether the AeonoseTM can make a distinction between the breath patterns of patients with MS and healthy control subjects. In this mono-center, prospective, non-invasive study, 124 subjects with a confirmed diagnosis of MS and 129 control subjects each breathed into the AeonoseTM for 5 min. Exhaled breath data was used to train an artificial neural network (ANN) predictive model. To investigate the influence of medication intake we created a second predictive model with a subgroup of MS patients without medication prescribed for MS. The ANN model based on the entire dataset was able to distinguish MS patients from healthy controls with a sensitivity of 0.75 (95% CI: 0.66-0.82) and specificity of 0.60 (0.51-0.69). The model created with the subgroup of MS patients not using medication and the healthy control subjects had a sensitivity of 0.93 (0.82-0.98) and a specificity of 0.74 (0.65-0.81). The study showed that the AeonoseTM is able to make a distinction between MS patients and healthy control subjects, and could potentially provide a quick screening test to assist in diagnosing MS. Further research is needed to determine whether the AeonoseTM is able to differentiate new MS patients from subjects who will not get the diagnosis.
ISSN:1752-7155
1752-7163
DOI:10.1088/1752-7163/abd080