Core Concepts
This research aims to develop a robust data analytics process and enhance machine learning models to accurately differentiate between infected and non-infected samples using Gas Chromatography-Ion Mobility Spectrometry (GC-IMS) data.
Abstract
This research focuses on integrating advanced diagnostic tools, specifically Gas Chromatography-Ion Mobility Spectrometry (GC-IMS), with machine learning techniques to tackle the challenge of precise infection identification. The key highlights are:
The research aims to create a Laboratory Information Management System (LIMS) platform that coordinates the entire process of handling high-dimensional GC-IMS data, including data collection, preprocessing, and analysis using machine learning algorithms.
The data preprocessing stage involves implementing quality assurance checks, artifact detection, denoising, baseline correction, and data transformation to ensure data quality and consistency for subsequent analysis.
Various machine learning algorithms, such as decision trees, logistic regression, random forest, support vector machines (SVM), and partial least squares discriminant analysis (PLS-DA), are evaluated for their performance in differentiating between infected and non-infected samples.
Preliminary results demonstrate promising accuracy levels when employing these machine learning techniques on the GC-IMS data, highlighting the potential of this approach for infection detection.
Ongoing efforts are focused on enhancing the effectiveness of the models, investigating techniques to improve their interpretability, and incorporating additional data sources to further support the early detection of diseases.
Stats
The GC-IMS data used in this study consists of 76 pre-processed instances, each represented by a matrix of 4080 x 3150 dimensions, where the X dimension is the Drift Time and the Y dimension is the Retention Time, and the values represent the intensity of the concentration of each compound.
Quotes
"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."
"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."