DH2.5 - Development of Exhaled Breath Monitoring System Using Semiconductive Gas Sensors and Statistical Analysis
- Event
- 17th International Meeting on Chemical Sensors - IMCS 2018
2018-07-15 - 2018-07-19
Vienna, Austria - Chapter
- Sensors for Diagnostics and Health Care 2
- Author(s)
- T. Iton, T. Miwa, A. Tsuruta, T. Akamatsu, N. Izu, W. Shin - National Institute of Advanced Industrial Science and Technology (AIST), Nagoya (Japan), J. Park, T. Hida - Aichi Cancer Center, Nagoya (Japan), Y. Sakumura - Graduate School of Biological Sciences, Nara Institute of Science and Technology, Nara (Japan), T. Eda, Y. Setoguchi - Figaro Engineering Inc., Osaka (Japan)
- Pages
- 153 - 154
- DOI
- 10.5162/IMCS2018/DH2.5
- ISBN
- 978-3-9816876-9-9
- Price
- free
Abstract
Volatile organic compounds (VOCs) in exhaled breath samples from lung cancer patients (LC) and healthy controls (HC) were analyzed by gas condenser-equipped GC/MS for development of an exhaled breath monitoring prototype system involving gas condensing units, short GC columns, and metal oxide semiconductive gas sensors. The GC/MS analysis identified 56 VOCs in exhaled breath samples from 136 volunteers, 107 LC and 29 HC, and selected four target VOCs by simple statistical analyses. The first prototype analyzed exhaled breath samples from 101 volunteers (74 LC and 27 HC). The prototype system exhibited a level of performance similar to that of the gas condenser- GC/MS system for breath analysis. Subsequently, we developed the second prototype which used advanced statistical analysis, support vector machine algorithm (SVM), for improving high percentage of correct answers. The SVM was also carried out for selected new target VOCs from results of the GC/MS analysis. The short GC columns of the second prototype were selected for detecting the new four target VOCs.