J Appl Biomed 17:67, 2019 | DOI: 10.32725/jab.2018.006

Volatile organic compounds of biofluids for detecting lung cancer by an electronic nose based on artificial neural network

Ehab I. Mohamed^1,*, Marwa A. Mohamed², Samir M. Abdel-Mageed³, Taher S. Abdel-Mohdy⁴, Mohamed I. Badawi⁵, Samy H. Darwish⁶

¹ Alexandria University, Medical Research Institute, Department of Medical Biophysics, Alexandria, Egypt

² Alexandria University, Medical Research Institute, Department of Chemical Pathology, Alexandria, Egypt

³ Alexandria University, Faculty of Science, Physics Department, Alexandria, Egypt

⁴ October 6 University, Faculty of Applied Medical Sciences, Department of Biomedical Equipment, Cairo, Egypt

⁵ Pharos University, Faculty of Allied Medical Sciences, Department of Medical Equipment, Alexandria, Egypt

⁶ Pharos University, Faculty of Engineering, Department of Electrical Engineering, Alexandria, Egypt

Lung cancer (LC) incidence represents 11.5% of all new cancers, resulting in 1.72 million deaths worldwide in 2015. With the aim to investigate the capability of the electronic nose (e-nose) technology for detecting and differentiating complex mixtures of volatile organic compounds in biofluids ex-vivo, we enrolled 50 patients with suspected LC and 50 matching controls. Tissue biopsy was taken from suspicious lung mass for histopathological evaluation and blood, exhaled breath, and urine samples were collected from all participants and qualitatively processed using e-nose. Odor-print patterns were further analysed using the principal component analysis (PCA) and artificial neural network (ANN) analysis. Adenocarcinoma, non-small cell LC and squamous cell carcinoma were the predominant pathological types among LC patients. PCA cluster-plots showed a clear distinction between LC patients and controls for all biological samples; where the overall success ratios of classification for principal components #1 and #2 were: 95.46, 82.01, and 91.66% for blood, breath and urine samples, respectively. Moreover, ANN showed a better discrimination between LC patients and controls with success ratios of 95.74, 91.67 and 100% for blood, breath and urine samples, respectively. The e-nose is an easy noninvasive tool, capable of identifying LC patients from controls with great precision.

Keywords: Artificial Neural Network; Biological Fluids; Electronic Nose; Lung Cancer; Principal Component Analysis; Urine

Conflicts of interest:

The authors have no conflict of interests to declare.

Received: November 6, 2018; Prepublished online: January 10, 2019; Published: March 19, 2019  Show citation