Modular Point-of-Care Breath Analyzer and Shape Taxonomy-Based Machine Learning for Gastric Cancer Detection.
breath analysis
electronic nose
gastric cancer
machine learning
screening
Journal
Diagnostics (Basel, Switzerland)
ISSN: 2075-4418
Titre abrégé: Diagnostics (Basel)
Pays: Switzerland
ID NLM: 101658402
Informations de publication
Date de publication:
14 Feb 2022
14 Feb 2022
Historique:
received:
11
01
2022
revised:
01
02
2022
accepted:
11
02
2022
entrez:
25
2
2022
pubmed:
26
2
2022
medline:
26
2
2022
Statut:
epublish
Résumé
Gastric cancer is one of the deadliest malignant diseases, and the non-invasive screening and diagnostics options for it are limited. In this article, we present a multi-modular device for breath analysis coupled with a machine learning approach for the detection of cancer-specific breath from the shapes of sensor response curves (taxonomies of clusters). We analyzed the breaths of 54 gastric cancer patients and 85 control group participants. The analysis was carried out using a breath analyzer with gold nanoparticle and metal oxide sensors. The response of the sensors was analyzed on the basis of the curve shapes and other features commonly used for comparison. These features were then used to train machine learning models using Naïve Bayes classifiers, Support Vector Machines and Random Forests. The accuracy of the trained models reached 77.8% (sensitivity: up to 66.54%; specificity: up to 92.39%). The use of the proposed shape-based features improved the accuracy in most cases, especially the overall accuracy and sensitivity. The results show that this point-of-care breath analyzer and data analysis approach constitute a promising combination for the detection of gastric cancer-specific breath. The cluster taxonomy-based sensor reaction curve representation improved the results, and could be used in other similar applications.
Sections du résumé
BACKGROUND
BACKGROUND
Gastric cancer is one of the deadliest malignant diseases, and the non-invasive screening and diagnostics options for it are limited. In this article, we present a multi-modular device for breath analysis coupled with a machine learning approach for the detection of cancer-specific breath from the shapes of sensor response curves (taxonomies of clusters).
METHODS
METHODS
We analyzed the breaths of 54 gastric cancer patients and 85 control group participants. The analysis was carried out using a breath analyzer with gold nanoparticle and metal oxide sensors. The response of the sensors was analyzed on the basis of the curve shapes and other features commonly used for comparison. These features were then used to train machine learning models using Naïve Bayes classifiers, Support Vector Machines and Random Forests.
RESULTS
RESULTS
The accuracy of the trained models reached 77.8% (sensitivity: up to 66.54%; specificity: up to 92.39%). The use of the proposed shape-based features improved the accuracy in most cases, especially the overall accuracy and sensitivity.
CONCLUSIONS
CONCLUSIONS
The results show that this point-of-care breath analyzer and data analysis approach constitute a promising combination for the detection of gastric cancer-specific breath. The cluster taxonomy-based sensor reaction curve representation improved the results, and could be used in other similar applications.
Identifiants
pubmed: 35204584
pii: diagnostics12020491
doi: 10.3390/diagnostics12020491
pmc: PMC8871298
pii:
doi:
Types de publication
Journal Article
Langues
eng
Subventions
Organisme : European Regional Development Fund
ID : PostDoc Latvia project No. 1.1.1.2/VIAA/2/18/270
Organisme : European Regional Development Fund
ID : PostDoc Latvia project No. 1.1.1.2/VIAA/3/19/495
Références
Eur Respir Rev. 2019 Jun 26;28(152):
pubmed: 31243094
Biosensors (Basel). 2021 Nov 22;11(11):
pubmed: 34821685
Br J Surg. 2019 Aug;106(9):1122-1125
pubmed: 31259390
ACS Nano. 2016 Sep 27;10(9):8169-79
pubmed: 27409521
Oncotarget. 2018 Jun 22;9(48):28805-28817
pubmed: 29988892
Anal Chem. 2020 Feb 4;92(3):2656-2664
pubmed: 31880430
J Breath Res. 2020 Nov 19;15(1):
pubmed: 33105106
Biochim Biophys Acta Rev Cancer. 2022 Jan;1877(1):188644
pubmed: 34737023
Biosensors (Basel). 2021 Sep 14;11(9):
pubmed: 34562928
Sensors (Basel). 2018 Aug 09;18(8):
pubmed: 30096939
Br J Cancer. 2013 Mar 5;108(4):941-50
pubmed: 23462808
Sci Rep. 2021 Feb 17;11(1):4014
pubmed: 33597551
Sensors (Basel). 2015 Nov 02;15(11):27804-31
pubmed: 26540056
Cancer Commun (Lond). 2020 Jun;40(6):273-278
pubmed: 32459390
J Clin Med. 2021 Oct 27;10(21):
pubmed: 34768503
Br J Cancer. 2010 Aug 10;103(4):542-51
pubmed: 20648015
ACS Nano. 2020 May 26;14(5):6067-6075
pubmed: 32271532
Cancer. 2021 Apr 15;127(8):1286-1292
pubmed: 33739456
ACS Nano. 2017 Jan 24;11(1):112-125
pubmed: 28000444
Biosensors (Basel). 2020 Jul 25;10(8):
pubmed: 32722438
J Breath Res. 2021 Oct 20;15(4):
pubmed: 34610588
Adv Mater. 2021 Sep;33(35):e2101262
pubmed: 34240473
Surg Innov. 2018 Oct;25(5):429-434
pubmed: 29909757
Front Oncol. 2021 Feb 26;11:606915
pubmed: 33747921
J Med Signals Sens. 2016 Jul-Sep;6(3):172-82
pubmed: 27563574
Eur J Gastroenterol Hepatol. 2006 Aug;18(8):821-9
pubmed: 16825897
Clin Chim Acta. 2004 Sep;347(1-2):25-39
pubmed: 15313139
J Breath Res. 2019 Oct 23;14(1):016004
pubmed: 31505480
Gut. 2016 Mar;65(3):400-7
pubmed: 25869737