Dataset Information

A deep learning approach for detecting liver cirrhosis from volatolomic analysis of exhaled breath.

ABSTRACT: Liver disease such as cirrhosis is known to cause changes in the composition of volatile organic compounds (VOC) present in patient breath samples. Previous studies have demonstrated the diagnosis of liver cirrhosis from these breath samples, but studies are limited to a handful of discrete, well-characterized compounds. We utilized VOC profiles from breath samples from 46 individuals, 35 with cirrhosis and 11 healthy controls. A deep-neural network was optimized to discriminate between healthy controls and individuals with cirrhosis. A 1D convolutional neural network (CNN) was accurate in predicting which patients had cirrhosis with an AUC of 0.90 (95% CI: 0.75, 0.99). Shapley Additive Explanations characterized the presence of discrete, observable peaks which were implicated in prediction, and the top peaks (based on the average SHAP profiles on the test dataset) were noted. CNNs demonstrate the ability to predict the presence of cirrhosis based on a full volatolomics profile of patient breath samples. SHAP values indicate the presence of discrete, detectable peaks in the VOC signal.

SUBMITTER: Wieczorek M

PROVIDER: S-EPMC9556819 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A deep learning approach for detecting liver cirrhosis from volatolomic analysis of exhaled breath.

Wieczorek Mikolaj M Weston Alexander A Ledenko Matthew M Thomas Jonathan Nelson JN Carter Rickey R Patel Tushar T

Frontiers in medicine 20220929

Liver disease such as cirrhosis is known to cause changes in the composition of volatile organic compounds (VOC) present in patient breath samples. Previous studies have demonstrated the diagnosis of liver cirrhosis from these breath samples, but studies are limited to a handful of discrete, well-characterized compounds. We utilized VOC profiles from breath samples from 46 individuals, 35 with cirrhosis and 11 healthy controls. A deep-neural network was optimized to discriminate between healthy ...[more]

PMID: 36250077

Similar Datasets

Project description:BackgroundThe potential of exhaled breath sampling and analysis has long attracted interest in the areas of medical diagnosis and disease monitoring. This interest is attributed to its non-invasive nature, access to an unlimited sample supply (i.e., breath), and the potential to facilitate a rapid at patient diagnosis. However, progress from laboratory setting to routine clinical practice has been slow. Different methodologies of breath sampling, and the consequent difficulty in comparing and combining data, are considered to be a major contributor to this. To fulfil the potential of breath analysis within clinical and pre-clinical medicine, standardisation of some approaches to breath sampling and analysis will be beneficial.ObjectivesThe aim of this review is to investigate the heterogeneity of breath sampling methods by performing an in depth bibliometric search to identify the current state of art in the area. In addition, the review will discuss and critique various breath sampling methods for off-line breath analysis.MethodsLiterature search was carried out in databases MEDLINE, BIOSIS, EMBASE, INSPEC, COMPENDEX, PQSCITECH, and SCISEARCH using the STN platform which delivers peer-reviewed articles. Keywords searched for include breath, sampling, collection, pre-concentration, volatile. Forward and reverse search was then performed on initially included articles. The breath collection methodologies of all included articles was subsequently reviewed.ResultsSampling methods differs between research groups, for example regarding the portion of breath being targeted. Definition of late expiratory breath varies between studies.ConclusionsBreath analysis is an interdisciplinary field of study using clinical, analytical chemistry, data processing, and metabolomics expertise. A move towards standardisation in breath sampling is currently being promoted within the breath research community with a view to harmonising analysis and thereby increasing robustness and inter-laboratory comparisons.

Dataset Information

A deep learning approach for detecting liver cirrhosis from volatolomic analysis of exhaled breath.

Publications

A deep learning approach for detecting liver cirrhosis from volatolomic analysis of exhaled breath.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets