Metabolic dysfunction-associated fatty liver disease (MAFLD) represents a predominant cause of chronic liver disease, underscoring the demand for accessible, non-invasive diagnostic tools. Tongue diagnosis in Traditional Chinese Medicine provides a distinctive perspective on systemic health, though it remains largely subjective. This study aimed to develop an interpretable multimodal deep learning model for MAFLD screening by integrating quantitative tongue image features with routine clinical data.
Methods
From 904 screened candidates, 477 subjects (157 healthy, 320 MAFLD) were included and randomly allocated to training, validation, and test sets in an 8:1:1 ratio. All participants underwent standardized tongue imaging (International Commission on Illumination L*a*b color features) and comprehensive clinical evaluation. We constructed a dual-stream deep learning model, combining a ConvNeXt-Tiny network for tongue images and a multilayer perceptron for clinical variables. Feature fusion was achieved via a Dynamic Affine Feature Transformation module, and the model was trained using weighted cross-entropy loss.
Results
MAFLD patients showed significant metabolic abnormalities compared to healthy controls. A progressive decrease in tongue yellowness (b* value) was observed with advancing fibrosis. On an independent test set (n = 48), the multimodal model achieved 97.92% accuracy, Quadratic Weighted Kappa of 0.9538, and 96.88% sensitivity, and 100% specificity, outperforming single-modality and serological models. Interpretability analyses confirmed the model's focus on clinically relevant tongue regions and key metabolic drivers.
Conclusions
This study successfully developed and validated a clinically oriented, multimodal auxiliary screening and diagnostic model for MAFLD that integrates objective TCM tongue appearance features with conventional metabolic indicators. Through interpretable fusion analysis, it provides a practical application for using TCM tongue appearance as a "window" for the non-invasive assessment of MAFLD. This model holds promise as a new non-invasive, low-cost, and efficient tool for MAFLD screening, particularly in regions with limited healthcare resources.
Full text
https://www.xiahepublishing.com/2310-8819/JCTH-2025-00631
The study was recently published in the Journal of Clinical and Translational Hepatology .
The Journal of Clinical and Translational Hepatology (JCTH) is owned by the Second Affiliated Hospital of Chongqing Medical University and published by XIA & HE Publishing Inc. JCTH publishes high quality, peer reviewed studies in the translational and clinical human health sciences of liver diseases. JCTH has established high standards for publication of original research, which are characterized by a study's novelty, quality, and ethical conduct in the scientific process as well as in the communication of the research findings. Each issue includes articles by leading authorities on topics in hepatology that are germane to the most current challenges in the field. Special features include reports on the latest advances in drug development and technology that are relevant to liver diseases. Regular features of JCTH also include editorials, correspondences and invited commentaries on rapidly progressing areas in hepatology. All articles published by JCTH, both solicited and unsolicited, must pass our rigorous peer review process.
