ORIGINAL RESEARCH article
Front. Endocrinol.
Sec. Cellular Endocrinology
This article is part of the Research TopicAdvanced AI and Omics Integration for Liver Disease ResearchView all articles
Harnessing Serum VOCs and Machine Learning for the Early Detection of MAFLD
Provisionally accepted
- 1Shandong University of Traditional Chinese Medicine, Jinan, China
- 2Shandong Provincial Third Hospital, Jinan, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Metabolic dysfunction-associated fatty liver disease (MAFLD) is a complex metabolic disorder and a leading cause of chronic liver disease worldwide. Conventional diagnostic tools such as ultrasound lack sensitivity for early-stage disease, underscoring the need for new approaches. Metabolomics, particularly the analysis of volatile organic compounds (VOCs) in biofluids, has emerged as a promising strategy for biomarker discovery. In this preliminary single-center study, we analyzed serum VOCs from 199 participants (110 MAFLD patients and 89 healthy controls) using gas chromatography–ion mobility spectrometry (GC-IMS) and applied machine learning algorithms to construct diagnostic models. Significant differences were observed in age, weight, body mass index, liver function, and lipid profiles between groups. A total of 79 VOCs were detected, of which 54 were significantly different (29 identified and 25 unidentified). Among the machine learning approaches tested, the random forest model achieved the best performance with a Test AUC of 0.941, sensitivity of 86.7%, and specificity of 88.5%. Seven key VOCs were identified, including two upregulated (2-Butoxyethanol, Cyclopentanone-D) and five downregulated compounds ((E)-3-hexenoic acid, 2-Ethylbutanal, 2-Propyl Acetate, Benzaldehyde-M, Furaneol). Some VOCs showed correlations with pathological indicators of MAFLD; notably, 2-pentylfuran varied significantly across disease grades, suggesting a potential role in stage-specific evaluation. Overall, these findings demonstrate that serum VOCs hold potential as a non-invasive diagnostic tool for MAFLD. However, given the limited sample size and single-center design, further validation in larger, multi-center, and longitudinal studies will be necessary to confirm their clinical utility, particularly for early detection.
Keywords: Metabolic dysfunction-associated fatty liver disease, Volatile Organic Compounds, Gas chromatography–ion mobility spectrometry, machine learning, biomarker, early diagnosis
Received: 24 Aug 2025; Accepted: 29 Oct 2025.
Copyright: © 2025 Li, Zhao, Zhang and Zhuang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: wei Xue Zhuang, zhuangxuewei@sdu.edu.cn
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.