Repeatability Study on a Classifier for Gastric Cancer Detection from Breath Sensor Data

Emmi Turppa, Inese Polaka, Edgars Vasiljevs, Juha M. Kortelainen, Gidi Shani, Marcis Leja, Hossam Haick

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

Abstract

The SNIFFPHONE device is a portable multichannel gas sensor, aiming to detect gastric cancer (GC) from breath samples. It employs gold nanoparticle (GNP) sensors reacting to volatile organic compounds (VOCs) in the exhaled breath, a non-invasive technique to support early diagnosis. This study evaluates the repeatability of the SNIFFPHONE classification result for measurements conducted on healthy subjects over a short period of time of less than 10 minutes. Due to the portable nature of the device, repeatability is studied with respect to varying measurement location. We find the classification results repeatable with a statistically significant 81 % Pearson correlation coefficient, even though the raw sensor responses are not concluded repeatable.
Original languageEnglish
Title of host publication2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)
PublisherIEEE Institute of Electrical and Electronic Engineers
Pages450-453
Number of pages4
ISBN (Electronic)978-1-7281-4617-1
ISBN (Print)978-1-7281-4618-8
DOIs
Publication statusPublished - Oct 2019
MoE publication typeA4 Article in a conference publication
Event19th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2019 - Athens, Greece
Duration: 28 Oct 201930 Oct 2019

Conference

Conference19th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2019
Period28/10/1930/10/19

Fingerprint

Classifiers
Sensors
Chemical sensors
Volatile organic compounds
Gold
Nanoparticles

Keywords

  • Breath sensor
  • Cancer detection
  • Decision support for health
  • Gastric cancer
  • Volatile organic compunds

Cite this

Turppa, E., Polaka, I., Vasiljevs, E., Kortelainen, J. M., Shani, G., Leja, M., & Haick, H. (2019). Repeatability Study on a Classifier for Gastric Cancer Detection from Breath Sensor Data. In 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE) (pp. 450-453). [8941778] IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/BIBE.2019.00087
Turppa, Emmi ; Polaka, Inese ; Vasiljevs, Edgars ; Kortelainen, Juha M. ; Shani, Gidi ; Leja, Marcis ; Haick, Hossam. / Repeatability Study on a Classifier for Gastric Cancer Detection from Breath Sensor Data. 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE). IEEE Institute of Electrical and Electronic Engineers , 2019. pp. 450-453
@inproceedings{66a8a589cf6f4604a3b52b44bebe16a3,
title = "Repeatability Study on a Classifier for Gastric Cancer Detection from Breath Sensor Data",
abstract = "The SNIFFPHONE device is a portable multichannel gas sensor, aiming to detect gastric cancer (GC) from breath samples. It employs gold nanoparticle (GNP) sensors reacting to volatile organic compounds (VOCs) in the exhaled breath, a non-invasive technique to support early diagnosis. This study evaluates the repeatability of the SNIFFPHONE classification result for measurements conducted on healthy subjects over a short period of time of less than 10 minutes. Due to the portable nature of the device, repeatability is studied with respect to varying measurement location. We find the classification results repeatable with a statistically significant 81 {\%} Pearson correlation coefficient, even though the raw sensor responses are not concluded repeatable.",
keywords = "Breath sensor, Cancer detection, Decision support for health, Gastric cancer, Volatile organic compunds",
author = "Emmi Turppa and Inese Polaka and Edgars Vasiljevs and Kortelainen, {Juha M.} and Gidi Shani and Marcis Leja and Hossam Haick",
year = "2019",
month = "10",
doi = "10.1109/BIBE.2019.00087",
language = "English",
isbn = "978-1-7281-4618-8",
pages = "450--453",
booktitle = "2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)",
publisher = "IEEE Institute of Electrical and Electronic Engineers",
address = "United States",

}

Turppa, E, Polaka, I, Vasiljevs, E, Kortelainen, JM, Shani, G, Leja, M & Haick, H 2019, Repeatability Study on a Classifier for Gastric Cancer Detection from Breath Sensor Data. in 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)., 8941778, IEEE Institute of Electrical and Electronic Engineers , pp. 450-453, 19th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2019, 28/10/19. https://doi.org/10.1109/BIBE.2019.00087

Repeatability Study on a Classifier for Gastric Cancer Detection from Breath Sensor Data. / Turppa, Emmi; Polaka, Inese; Vasiljevs, Edgars; Kortelainen, Juha M.; Shani, Gidi; Leja, Marcis; Haick, Hossam.

2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE). IEEE Institute of Electrical and Electronic Engineers , 2019. p. 450-453 8941778.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Repeatability Study on a Classifier for Gastric Cancer Detection from Breath Sensor Data

AU - Turppa, Emmi

AU - Polaka, Inese

AU - Vasiljevs, Edgars

AU - Kortelainen, Juha M.

AU - Shani, Gidi

AU - Leja, Marcis

AU - Haick, Hossam

PY - 2019/10

Y1 - 2019/10

N2 - The SNIFFPHONE device is a portable multichannel gas sensor, aiming to detect gastric cancer (GC) from breath samples. It employs gold nanoparticle (GNP) sensors reacting to volatile organic compounds (VOCs) in the exhaled breath, a non-invasive technique to support early diagnosis. This study evaluates the repeatability of the SNIFFPHONE classification result for measurements conducted on healthy subjects over a short period of time of less than 10 minutes. Due to the portable nature of the device, repeatability is studied with respect to varying measurement location. We find the classification results repeatable with a statistically significant 81 % Pearson correlation coefficient, even though the raw sensor responses are not concluded repeatable.

AB - The SNIFFPHONE device is a portable multichannel gas sensor, aiming to detect gastric cancer (GC) from breath samples. It employs gold nanoparticle (GNP) sensors reacting to volatile organic compounds (VOCs) in the exhaled breath, a non-invasive technique to support early diagnosis. This study evaluates the repeatability of the SNIFFPHONE classification result for measurements conducted on healthy subjects over a short period of time of less than 10 minutes. Due to the portable nature of the device, repeatability is studied with respect to varying measurement location. We find the classification results repeatable with a statistically significant 81 % Pearson correlation coefficient, even though the raw sensor responses are not concluded repeatable.

KW - Breath sensor

KW - Cancer detection

KW - Decision support for health

KW - Gastric cancer

KW - Volatile organic compunds

UR - http://www.scopus.com/inward/record.url?scp=85078578239&partnerID=8YFLogxK

U2 - 10.1109/BIBE.2019.00087

DO - 10.1109/BIBE.2019.00087

M3 - Conference article in proceedings

SN - 978-1-7281-4618-8

SP - 450

EP - 453

BT - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)

PB - IEEE Institute of Electrical and Electronic Engineers

ER -

Turppa E, Polaka I, Vasiljevs E, Kortelainen JM, Shani G, Leja M et al. Repeatability Study on a Classifier for Gastric Cancer Detection from Breath Sensor Data. In 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE). IEEE Institute of Electrical and Electronic Engineers . 2019. p. 450-453. 8941778 https://doi.org/10.1109/BIBE.2019.00087