您好,请登录, 注册


当前位置: 首页 > 技术文献 > 应用文献 > 用于糖尿病和肺癌患者呼吸分析非侵入性电子鼻诊断技术

来源: Bhagaban Behera, Rathin Joshi, Anil Vishnu G K, Sanjay Bhalerao,Hardik J. Pandya  发布日期: 2019-07-08  访问量: 47

标签: Cyranose 320电子鼻、糖尿病、肺癌、呼吸印记、无创技术

Electronic-nose: A non-invasive technology for breath analysis of diabetes and lung cancer patients


Bhagaban Behera1, Rathin Joshi1, Anil Vishnu G K2, Sanjay Bhalerao3, 4 and Hardik J. Pandya1,*

1Biomedical and Electronic (10-6-10-9) Engineering Systems Laboratory 6 Department of Electronic Systems Engineering, 7 Indian Institute of Science, Bangalore, India 560012 8
2Center for BioSystems Science and Engineering, 9 Indian Institute of Science, Bangalore, India 560012 10
3Parivartan Healthcare, 102 MIG Colony, Indore, India 452001 11 *Corresponding author:

To cite this article before publication: Bhagaban Behera et al 2019 J. Breath Res

This Accepted Manuscript is © 2018 IOP Publishing Ltd.


In human-exhaled breath, more than 3000 volatile organic compounds (VOCs) are found which  are directly or indirectly related to internal biochemical processes in the body. Electronic noses  (E-noses) could play a potential role in screening/analyzing various respiratory and systemic diseases by studying breath signatures. E-nose integrates sensor array and an artificial neural  network that responds to specific patterns of VOCs and thus can act as a non-invasive  technology for disease monitoring. Gold standard blood glucose monitoring for diabetes diagnostics is invasive and highly uncomfortable. This contributes to the massive need for technologies which are non-invasive and can be used as an alternative to blood measurements  for glucose detection. While lung cancer is one of the deadliest cancers with the highest death rate and an extremely high yearly global burden. The conventional means such as sputum cytology, chest radiography, or computed tomography do not support wide-range population screening. Few standard non-invasive techniques such as mass spectrometry and gas  chromatography are expensive, non-portable, and requires skilled personnel for operation and  are again not suitable for massive screening. Breath contains the markers for both diabetes and  lung cancer along with markers for several diseases and thus, a non-invasive technique like E-nose would greatly improve the analysis procedures over existing invasive methods. This  review shows the state-of-the-art technologies for VOCs detection and machine-learning  approaches for two clinical models: diabetes and lung cancer detection.


Keywords: Electronic-nose, non-invasive technologies, breath signals, volatile organic  compounds, diabetes, lung cancer