6533b834fe1ef96bd129cc27

RESEARCH PRODUCT

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

Edgars VasiljevsInese PolakaHossam HaickJuha M. KortelainenMarcis LejaEmmi TurppaGidi Shani

subject

business.industryBreath sensorHealthy subjects02 engineering and technologyCancer detectionRepeatability021001 nanoscience & nanotechnologyCancer detectionPearson product-moment correlation coefficient03 medical and health sciencessymbols.namesake0302 clinical medicineSDG 3 - Good Health and Well-beingVolatile organic compunds030220 oncology & carcinogenesisClassification resultsymbolsMedicine/dk/atira/pure/sustainabledevelopmentgoals/good_health_and_well_beingDecision support for health0210 nano-technologybusinessGastric cancerClassifier (UML)Biomedical engineering

description

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.

yearjournalcountryeditionlanguage
2019-10-01
10.1109/bibe.2019.00087https://doi.org/10.1109/BIBE.2019.00087