Volatile organic compounds (VOCs) present in exhaled breath can help in analyzing biochemical processes in the human body.
Liver diseases can be traced using VOCs as biomarkers for physiological and pathophysiological conditions.
In this work, researchers proposed a non-invasive and quick breath monitoring approach for early detection and progress monitoring of liver diseases using Isoprene, Limonene, and Dimethyl sulfide (DMS) as potential biomarkers.
A pilot study is performed to design a dataset that includes the concentration of the biomarker analyzed from the breath sample before and after study subjects performed an exercise. A machine learning approach is applied for the prediction of scores for liver function diagnosis.
This pilot study demonstrated that Isoprene, limonene, and DMS can be potential biomarkers for liver disease. This study design involves an exercise in the breath collection protocol that includes healthy subjects and liver patients.
There is a significant difference in the breath profile that has been found between liver patients and healthy people. Breath profile data is analyzed using four different regression methods.
Researchers showed that clinical scores can be predicated on our machine learning regression approach and breath profile data.
The regression result can estimate the clinical scores which imply the concentration of biomarkers varies according to the liver condition.
The designed breath collection protocol includes a brief duration exercise which is a novel approach according to the best of our knowledge in the field of liver-related study.
Published: 07 February 2022
source:
https://www.nature.com/articles/s41598-022-05808-5
https://doi.org/10.1038/s41598-022-05808-5
Comments