Search

Colorectal cancer (CRC) is the third most common malignancy and the second most common cause of cancer-related deaths worldwide. While CRC screening is already part of organized programs in many countries, there remains a need for improved screening tools. In recent years, a potential approach for cancer diagnosis has emerged via the analysis of volatile organic compounds (VOCs) using sensor technologies. The main goal of this study was to demonstrate and evaluate the diagnostic potential of a table-top breath analyzer for detecting CRC. Breath sampling was conducted and CRC vs. non-cancer groups (105 patients with CRC, 186 non-cancer subjects) were included in analysis. The obtained data were analyzed using supervised machine learning methods (i.e., Random Forest, C4.5, Artificial Neural Network, and Naïve Bayes). Superior accuracy was achieved using Random Forest and Evolutionary Search for Features (79.3%, sensitivity 53.3%, specificity 93.0%, AUC ROC 0.734), and Artificial Neural Networks and Greedy Search for Features (78.2%, sensitivity 43.3%, specificity 96.5%, AUC ROC 0.735). Our results confirm the potential of the developed breath analyzer as a promising tool for identifying and categorizing CRC within a point-of-care clinical context. The combination of MOX sensors provided promising results in distinguishing healthy vs. diseased breath samples. Its capacity for rapid, non-invasive, and targeted CRC detection suggests encouraging prospects for future clinical screening applications.

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.