Background: Gastric cancer is one of the deadliest malignant diseases, and the non-invasive screening and diagnostics options for it are limited. In this article, we present a multi-modular device for breath analysis coupled with a machine learning approach for the detection of cancer-specific breath from the shapes of sensor response curves (taxonomies of clusters). Methods: We analyzed the breaths of 54 gastric cancer patients and 85 control group participants. The analysis was carried out using a breath analyzer with gold nanoparticle and metal oxide sensors. The response of the sensors was analyzed on the basis of the curve shapes and other features commonly used for comparison. These features were then used to train machine learning models using Naïve Bayes classifiers, Support Vector Machines and Random Forests. Results: The accuracy of the trained models reached 77.8% (sensitivity: up to 66.54%; specificity: up to 92.39%). The use of the proposed shape-based features improved the accuracy in most cases, especially the overall accuracy and sensitivity. Conclusions: The results show that this point-of-care breath analyzer and data analysis approach constitute a promising combination for the detection of gastric cancer-specific breath. The cluster taxonomy-based sensor reaction curve representation improved the results, and could be used in other similar applications.

The human body releases numerous volatile organic compounds (VOCs) through tissues and various body fluids, including breath. These compounds form a specific chemical profile that may be used to detect the colorectal cancer CRC-related changes in human metabolism and thereby diagnose this type of cancer. The main goal of this study was to investigate the volatile signatures formed by VOCs released from the CRC tissue. For this purpose, headspace solid-phase microextraction gas chromatography-mass spectrometry was applied. In total, 163 compounds were detected. Both cancerous and non-cancerous tissues emitted 138 common VOCs. Ten volatiles (2-butanone; dodecane; benzaldehyde; pyridine; octane; 2-pentanone; toluene; p-xylene; n-pentane; 2-methyl-2-propanol) occurred in at least 90% of both types of samples; 1-propanol in cancer tissue (86% in normal one), acetone in normal tissue (82% in cancer one). Four compounds (1-propanol, pyridine, isoprene, methyl thiolacetate) were found to have increased emissions from cancer tissue, whereas eleven showed reduced release from this type of tissue (2-butanone; 2-pentanone; 2-methyl-2-propanol; ethyl acetate; 3-methyl-1-butanol; d-limonene; tetradecane; dodecanal; tridecane; 2-ethyl-1-hexanol; cyclohexanone). The outcomes of this study provide evidence that the VOCs signature of the CRC tissue is altered by the CRC. The volatile constituents of this distinct signature can be emitted through exhalation and serve as potential biomarkers for identifying the presence of CRC. Reliable identification of the VOCs associated with CRC is essential to guide and tune the development of advanced sensor technologies that can effectively and sensitively detect and quantify these markers.

SummaryThe case report demonstrates painstaking, one step at a time multitherapy for the third most common cancer and the third cause of cancer death in western countries – colorectal cancer. Multitherapeutic approach at specialized centers for the treatment of colorectal cancer is the cornerstone for reaching favorable treatment results and prognosis.