A Deep Multimodal Fusion Framework Integrating SERS, Clinical Data, and Metabolomics for Noninvasive MASH Diagnosis
Analytical Chemistry · 27.01.2026 · 98 (3) · 1950-1960
DOI: 10.1021/acs.analchem.5c04917 ↗Kurz gefasst
Fachartikel in der Zeitschrift Analytical Chemistry, online erschienen am 10.01.2026. Verfasst von Weilin Wu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education, Fujian Provincial Key Laboratory of Photonics Technolo…. Hauptthemen laut MEDLINE: Spectrum Analysis, Raman, Metabolomics, Deep Learning, Fatty Liver. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: Natural Science Foundation of Fujian Province, National Natural Science Foundation of China, Science Fund Program for Excellent Young Scientists of Fujian.
Abstract (Originalsprache)
Metabolic dysfunction-associated steatotic liver disease (MASLD), particularly its progressive form, metabolic dysfunction-associated steatohepatitis (MASH), presents significant diagnostic challenges due to its complex etiology and heterogeneous clinical presentation. While surface-enhanced Raman spectroscopy (SERS) offers promising molecular-level sensitivity, its diagnostic accuracy is limited when used alone, hindering its suitability for clinical diagnostic applications. To address these challenges, we introduce MedFusionNet (MFN), a novel multimodal deep learning framework that integrates SERS spectra, clinical-biochemical (CB) parameters, and bile acid (BA) metabolomics for noninvasive MASH diagnosis. MFN leverages a Product-of-Experts (PoE)-based variational fusion architecture to capture intermodality interactions and latent correlations, and jointly learns a shared latent representation through a multiloss optimization strategy. When applied to a biopsy-confirmed MASLD cohort (n = 240), MFN outperformed both conventional and multimodal baseline models in predictive accuracy and robustness. SHapley Additive exPlanations (SHAP), combined with stratified 5-fold cross-validation, provides fine-grained interpretability across modalities. These findings underscore MFN's potential as a scalable, clinically actionable framework for early MASH detection and broader applications in complex disease diagnostics.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education, Fujian Provincial Key Laboratory of Photonics Technology, Fujian Normal University, Fuzhou 350117, China.
- School of Intelligent Manufacturing, Putian University, Putian 351100, China.
- Children's Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Children and Adolescents' Health and Diseases, Hangzhou 310052, China.
- MAFLD Research Center, Department of Hepatology, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou 325015, China.
- Key Laboratory of Diagnosis and Treatment for the Development of Chronic Liver Disease in Zhejiang Province, Wenzhou 325035, China.
- Institute of Hepatology, Wenzhou Medical University, Wenzhou 325035, China.
ORCID-Profile: Jing Wang
Förderung
- Natural Science Foundation of Fujian Province
- National Natural Science Foundation of China
- Science Fund Program for Excellent Young Scientists of Fujian
- Educational Research Project for Young and Middle-aged Teachers in Fujian Province
- Fujian Province
Zitieren
APA
Wu, W., Lu, D., Ni, Y., Huang, Z., Zheng, M. H., & Wang, J. (2026). A Deep Multimodal Fusion Framework Integrating SERS, Clinical Data, and Metabolomics for Noninvasive MASH Diagnosis. Analytical Chemistry, 98(3), 1950-1960. https://doi.org/10.1021/acs.analchem.5c04917
Vancouver
Wu W, Lu D, Ni Y, Huang Z, Zheng MH, Wang J. A Deep Multimodal Fusion Framework Integrating SERS, Clinical Data, and Metabolomics for Noninvasive MASH Diagnosis. Analytical Chemistry. 2026;98(3):1950-1960. doi:10.1021/acs.analchem.5c04917
BibTeX
@article{Wu2026,
author = {Wu, Weilin and Lu, Dechan and Ni, Yan and Huang, Zufang and Zheng, Ming-Hua and Wang, Jing},
title = {A Deep Multimodal Fusion Framework Integrating SERS, Clinical Data, and Metabolomics for Noninvasive MASH Diagnosis},
journal = {Analytical Chemistry},
year = {2026},
volume = {98},
number = {3},
pages = {1950--1960},
doi = {10.1021/acs.analchem.5c04917}
}
EUVIMED