A rising number of authors are drawing evidence on the diagnostic capacity of specific volatile organic compounds (VOCs) resulting from some body fluids. While cancer incidence in society is on the rise, it becomes clear that the analysis of these VOCs can yield new strategies to mitigate advanced cancer incidence rates. This paper presents the methodology implemented to test whether a device consisting of an electronic nose inspired by a dog’s olfactory system and olfactory neurons is significantly informative to detect breast cancer (BC). To test this device, 90 human urine samples were collected from control subjects and BC patients at a hospital. To test this system, an artificial intelligence-based classification algorithm was developed. The algorithm was firstly trained and tested with data resulting from gas chromatography-mass spectrometry (GC–MS) urine readings, leading to a classification rate of 92.31%, sensitivity of 100.00%, and specificity of 85.71% (N = 90). Secondly, the same algorithm was trained and tested with data obtained with our eNose prototype hardware, and class prediction was achieved with a classification rate of 75%, sensitivity of 100%, and specificity of 50%.
A rising number of authors are drawing evidence to the diagnostic capacity of specific volatile organic compounds (VOCs) resulting from some body fluids. While cancer incidence in society is on the rise, it becomes clear that the analysis of these VOCs can yield new strategies to mitigate advanced cancer incidence rates. This paper presents the methodology implemented to test whether a device consisting of an electronic nose inspired after a dog’s olfactory system and olfactory neurons is significantly informative to detect breast cancer (BC). To test this device, 90 human urine samples were collected from control subjects and BC patients at a hospital. To test this system, an artificial intelligence-based classification algorithm was developed. The algorithm was firstly trained and tested with data resulting from gas chromatography-mass spectrometry (GC-MS) urine readings, leading to a classification rate of 92.31%, sensitivity of 100.00%, and specificity of 85.71% (N=90). Secondly, the same algorithm was trained and tested with data obtained with our eNose prototype hardware, and class prediction was achieved with a classification rate of 75%, sensitivity of 100%, and specificity of 50%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.