Analysis of exhaled breath for dengue disease detection by low-cost electronic nose system. (28th February 2022)

• Record Type: Journal Article
• Authors: Smulko, Janusz; Chludziński, Tomasz; Majchrzak, Tomasz; Kwiatkowski, Andrzej; Borys, Sebastian; Lisset Jaimes-Mogollón, Aylen; Manuel Durán-Acevedo, Cristhian; Geovanny Perez-Ortiz, Omar; Ionescu, Radu
• Is Part Of: Measurement. Volume 190(2022)
• Publication Date: 2022-02-28
• Subjects: Electronic nose -- Low cost gas sensors -- Dengue disease -- Exhaled breath analysis -- Classification algorithms; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2022.110733
• Languages: English
• ISSNs: 0263-2241

Abstract

Graphical abstract: Highlights: Commercial resistive gas sensors were applied to detect dengue disease. We developed a portable set-up to analyse exhaled breath samples. The data processing applied differential parameters to reduce drifts impact. The random forest classification algorithm in Orange software was utilized. Abstract: This paper presents a procedure and a set-up of an electronic nose system analyzing exhaled breath to detect the patients suffering from dengue – a mosquito-borne tropical disease. Low-power resistive gas sensors (MiCS-6814, TGS8100) were used to detect volatile organic compounds (VOCs) in the exhaled breath. The end-tidal phase of patients exhaled breath was collected with a BioVOC TM breath sampler. Two strategies were assessed for breath samples measurement: either direct transfer from the BioVOC TM into the sensors test chamber, or storage in Tenax TA sorbent tubes followed by VOCs release through thermal desorption and then transfer into sensors test chamber. DC sensor resistances were recorded and processed by multivariate classifier algorithms to detect infected patients. The experimental studies were run on a group of 26 individuals (16 dengue diagnosed patients and 10 control volunteers). The detection accuracy of dengue patients was over 90%.