Fast and automated biomarker detection in breath samples with machine learning

TL;DR

This paper introduces a deep learning-based system for rapid, automated detection of VOC biomarkers in breath samples using GC-MS data, outperforming traditional expert-led analysis in speed and accuracy.

Contribution

The study presents a novel deep learning approach that automates VOC detection from raw GC-MS data, reducing analysis time and increasing detection accuracy compared to expert-driven methods.

Findings

Outperforms expert analysis in VOC detection accuracy

Reduces data processing time significantly

Maintains high specificity in VOC identification

Abstract

Volatile organic compounds (VOCs) in human breath can reveal a large spectrum of health conditions and can be used for fast, accurate and non-invasive diagnostics. Gas chromatography-mass spectrometry (GC-MS) is used to measure VOCs, but its application is limited by expert-driven data analysis that is time-consuming, subjective and may introduce errors. We propose a system to perform GC-MS data analysis that exploits deep learning pattern recognition ability to learn and automatically detect VOCs directly from raw data, thus bypassing expert-led processing. The new proposed approach showed to outperform the expert-led analysis by detecting a significantly higher number of VOCs in just a fraction of time while maintaining high specificity. These results suggest that the proposed method can help the large-scale deployment of breath-based diagnosis by reducing time and cost, and increasing accuracy and consistency.