Modular Point-of-Care Breath Analyzer and Shape Taxonomy-Based Machine Learning for Gastric Cancer Detection.

Inese Polaka,Manohar Prasad Bhandari,Marcis Leja,Viktors Veliks,Linda Anarkulova,Armands Sivins,Marta Padilla,Ivars Tolmanis,Jan Mitrovics,Igors Ivanovs,Linda Mezmale,Ilona Vilkoite,Hossam Haick,Gidi Shani,Anna Marija Lescinska

doi:10.3390/diagnostics12020491

Abstract

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.

Highlights

Gastric cancer ranks fourth among the most common cancers worldwide
We report the diagnostic performance of a modular point-of-care breath analyzer with gold nanoparticle (GNP) and two different types of metal oxide (MOX) semiconductor sensors for the detection and identification of gastric cancer in an online mode that requires no additional breath collection procedures or laboratory settings
If we look at the performances of different combinations of distance measures, linkage approaches and feature selection methods used to select the cuts in the cluster taxonomies, we can see that the results of the ReliefF feature selection approach are not worse, as in the case of Naïve Bayes (NB)

Summary

Introduction

Gastric cancer ranks fourth among the most common cancers worldwide. It shows a lack of specific symptoms in the early stages, and is commonly characterized by late diagnosis, poor prognosis, and likely relapse [1]. Upper gastrointestinal endoscopy with biopsy is the gold standard for the diagnosis of the condition, but this operation is time-consuming, expensive, and invasive; patient compliance is poor, and the demands on medical staff and equipment are typically high. It is unaffordable for mass screening, and cannot provide the early diagnosis of gastric cancer. 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). The cluster taxonomy-based sensor reaction curve representation improved the results, and could be used in other similar applications

Results

Discussion

Conclusion