Fx-Net and PureNet: Convolutional Neural Network architecture for discrimination of Chronic Obstructive Pulmonary Disease from smokers and healthy subjects through electronic nose signals

• Published in: Computers in biology and medicine Vol. 148; p. 105913
• Main Authors: Avian, Cries, Mahali, Muhammad Izzuddin, Putro, Nur Achmad Sulistyo, Prakosa, Setya Widyawan, Leu, Jenq-Shiou
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.09.2022; Elsevier Limited
• Subjects: Artificial neural networks; Chronic obstructive pulmonary disease; Chronic obstructive pulmonary disease (COPD); Classifiers; Computer architecture; Convolutional neural network; Electronic nose; Electronic noses; Feature extraction; Internal Medicine; Kernel principal component analysis; Lung cancer; Lung diseases; Machine learning; Mortality; Neural networks; Obstructive lung disease; Other; Principal components analysis; Sensors; Signal processing; Smoking; Standard deviation; VOCs; Volatile organic compounds; Chronic obstructive pulmonary disease (COPD); Kernel principal component analysis; Convolutional neural network; Lung cancer; Electronic nose
• DOI: 10.1016/j.compbiomed.2022.105913
• ISSN: 0010-4825; 1879-0534

As one of the most reliable and significant indicators, Chronic Obstructive Pulmonary Disease (COPD) becomes a robust predictor of lung cancer early detection, the world's leading cause of cancer death. One of the methods is to analyze the Volatile Organic Compounds (VOCs) in exhaled breath using electronic noses (E-noses), which have become emerging tools for analyzing breath because of their potential and promising technology for diagnosing. However, the signal processing of the E-Nose sensor becomes vital in exposing information about the subject condition, which most researchers strive to accomplish. We proposed a Convolutional Neural Network (CNN) architecture to classify COPD in smokers and non-smokers, healthy subjects, and smokers from E-Nose signals to contribute to this field. Two models were constructed following E-Nose signal processing state-of-the-arts. One was by combined feature extraction and classifier, and the second was by CNN, which directly processed the raw signal. In addition, various feature extraction and classifier (Machine Learning and CNN) used in prior research were investigated. Using 3K and 5K Fold cross-validation results demonstrated that our proposed models outperformed in Kernel Principal Component Analysis (KPCA) with Fx-ConvNet and Pure-ConvNet. They all reached maximum F1-Score with zero standard deviation values indicating a consistent result. Further experiments also showed that KPCA contributed to the increasing performance of some classifiers with average F1-Score 0.933 and 0.068 as standard deviation values. •CNN architecture is designed for discrimination of COPD from smokers and healthy subjects.•Two architectures were built following the state-of-the-art model's technique.•Kernel principal component analysis assigned to extract E-Nose signal on first CNN model.•Explored all combinations of feature extraction and machine learning, also prior CNN model for model comparison.•Both proposed models have outperformed performance compared to the state-of-the-art.