Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Exploring Machine Learning Algorithms for Infection Detection Using GC-IMS Data: A Preliminary Study

Christos Sardianos, Chrysostomos Symvoulidis, Matthias Schlögl, Iraklis Varlamis, Georgios Th. Papadopoulos

TL;DR

The paper addresses rapid, non-invasive infection detection using GC-IMS data by integrating ML within a LIMS platform to automate data handling, biomarker discovery, and classification. It analyzes 76 breath-sample GC-IMS datasets with a PCA-based dimensionality reduction and evaluates multiple classifiers, finding Random Forest and Support Vector Machines to perform best, with PLS-DA also competitive. The study demonstrates the feasibility of a combined GC-IMS ML pipeline for early infection detection and outlines a scalable path toward broader validation and interpretability. Overall, the work provides a concrete, workflow-oriented framework that could enable timely, biomarker-driven diagnostics in clinical settings and informs future enhancements with deep learning and explainability.

Abstract

The developing field of enhanced diagnostic techniques in the diagnosis of infectious diseases, constitutes a crucial domain in modern healthcare. By utilizing Gas Chromatography-Ion Mobility Spectrometry (GC-IMS) data and incorporating machine learning algorithms into one platform, our research aims to tackle the ongoing issue of precise infection identification. Inspired by these difficulties, our goals consist of creating a strong data analytics process, enhancing machine learning (ML) models, and performing thorough validation for clinical applications. Our research contributes to the emerging field of advanced diagnostic technologies by integrating Gas Chromatography-Ion Mobility Spectrometry (GC-IMS) data and machine learning algorithms within a unified Laboratory Information Management System (LIMS) platform. Preliminary trials demonstrate encouraging levels of accuracy when employing various ML algorithms to differentiate between infected and non-infected samples. Continuing endeavors are currently concentrated on enhancing the effectiveness of the model, investigating techniques to clarify its functioning, and incorporating many types of data to further support the early detection of diseases.

Exploring Machine Learning Algorithms for Infection Detection Using GC-IMS Data: A Preliminary Study

TL;DR

The paper addresses rapid, non-invasive infection detection using GC-IMS data by integrating ML within a LIMS platform to automate data handling, biomarker discovery, and classification. It analyzes 76 breath-sample GC-IMS datasets with a PCA-based dimensionality reduction and evaluates multiple classifiers, finding Random Forest and Support Vector Machines to perform best, with PLS-DA also competitive. The study demonstrates the feasibility of a combined GC-IMS ML pipeline for early infection detection and outlines a scalable path toward broader validation and interpretability. Overall, the work provides a concrete, workflow-oriented framework that could enable timely, biomarker-driven diagnostics in clinical settings and informs future enhancements with deep learning and explainability.

Abstract

The developing field of enhanced diagnostic techniques in the diagnosis of infectious diseases, constitutes a crucial domain in modern healthcare. By utilizing Gas Chromatography-Ion Mobility Spectrometry (GC-IMS) data and incorporating machine learning algorithms into one platform, our research aims to tackle the ongoing issue of precise infection identification. Inspired by these difficulties, our goals consist of creating a strong data analytics process, enhancing machine learning (ML) models, and performing thorough validation for clinical applications. Our research contributes to the emerging field of advanced diagnostic technologies by integrating Gas Chromatography-Ion Mobility Spectrometry (GC-IMS) data and machine learning algorithms within a unified Laboratory Information Management System (LIMS) platform. Preliminary trials demonstrate encouraging levels of accuracy when employing various ML algorithms to differentiate between infected and non-infected samples. Continuing endeavors are currently concentrated on enhancing the effectiveness of the model, investigating techniques to clarify its functioning, and incorporating many types of data to further support the early detection of diseases.
Paper Structure (15 sections, 3 figures, 1 table)

This paper contains 15 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background and Motivation
  3. Objectives of the Research
  4. Literature Review
  5. Methodology
  6. Overview of the Platform
  7. Data Collection and Preprocessing
  8. Understanding GC-IMS data principles
  9. GC-IMS data analysis
  10. Experimental Setup
  11. GC-IMS Data Description
  12. Machine Learning Models and Classification
  13. Discussion
  14. Challenges and Considerations
  15. Future Directions

Figures (3)

  • Figure 1: The proposed pipeline used in the LIMS platform for data collection, processing and analysis.
  • Figure 2: Schematic representation of the GC-IMS system with separation of VOCs in gas chromatography component and ion mobility. (Image source: www.odournet.com)
  • Figure 3: Visualization of one instance per class (Infection/No infection) in the GC-IMS data samples used for the classification algorithms development.