Pub Date : 2026-06-01Epub Date: 2026-06-11DOI: 10.1016/j.dcmed.2026.05.004
Liu Lihui , Hu Kaiwen , Zhou Yana
<div><h3>Objective</h3><div>To map the research landscape of artificial intelligence (AI)-assisted tongue diagnosis through bibliometric analysis and to quantify its diagnostic accuracy and clinical interpretability through a diagnostic test accuracy (DTA) meta-analysis.</div></div><div><h3>Methods</h3><div>For the bibliometric analysis, the Web of Science Core Collection (WoSCC) was queried for English-language articles and reviews on AI-assisted tongue diagnosis published between January 1, 2014 and December 31, 2025, and analysed using Bibliometrix, VOSviewer, and CiteSpace, with major output dimensions including annual publication output and disciplinary distribution, journal and citation characteristics, country/region and institutional collaboration, author networks, keyword co-occurrence, and keyword burst detection. For the DTA meta-analysis, four databases [Scopus, PubMed, Web of Science, and China National Knowledge Infrastructure (CNKI)] were searched in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses of Diagnostic Test Accuracy (PRISMA-DTA) guidelines. A bivariate random-effects model hierarchical summary receiver operating characteristic (HSROC) was used to pool sensitivity and specificity, with subgroup analyses by disease category, AI model architecture, and sample-size strata. Methodological quality was assessed with the Quality Assessment of Diagnostic Accuracy Studies version 2 (QUADAS-2) tool, and publication bias was evaluated by Deeks’ funnel plot asymmetry test.</div></div><div><h3>Results</h3><div>A total of 198 publications met the bibliometric eligibility criteria. Annual output increased 24.5-fold (from 2 in 2014 to 49 in 2025), with the period 2022 – 2025 alone accounting for 65.2% of all publications. China contributed approximately 83.5% of all institutional affiliations, with Shanghai University of Traditional Chinese Medicine and Jiatuo Xu being the most productive institution and author, respectively. Keyword analysis identified four thematic clusters (AI and deep-learning architectures, image processing and segmentation, traditional Chinese medicine (TCM)-specific applications, and disease-specific applications) and a temporal evolution from traditional machine learning to deep learning and transformer-based, explainable, and multimodal AI architectures. Sixteen DTA meta-analysis studies (14 755 participants) covering metabolic and hepatic disorders, oncological and oral lesions, cardiovascular risk, diabetes, and other clinical applications were included in the DTA meta-analysis. The pooled sensitivity was 90.3% [95% confidence interval (CI): 86.7% – 93.1%] and the pooled specificity was 93.0% (95% CI: 90.6% – 94.7%); the area under the summary receiver operating characteristic (SROC) curve (AUC) was 0.961. Heterogeneity was substantial (<em>I</em><sup>2</sup> = 95.8% for sensitivity; <em>I</em><sup>2</sup> = 92.1% for specificity). Subgroup performance was broadly consisten
{"title":"Visualization analysis and clinical interpretability evaluation of artificial intelligence-assisted tongue diagnosis","authors":"Liu Lihui , Hu Kaiwen , Zhou Yana","doi":"10.1016/j.dcmed.2026.05.004","DOIUrl":"10.1016/j.dcmed.2026.05.004","url":null,"abstract":"<div><h3>Objective</h3><div>To map the research landscape of artificial intelligence (AI)-assisted tongue diagnosis through bibliometric analysis and to quantify its diagnostic accuracy and clinical interpretability through a diagnostic test accuracy (DTA) meta-analysis.</div></div><div><h3>Methods</h3><div>For the bibliometric analysis, the Web of Science Core Collection (WoSCC) was queried for English-language articles and reviews on AI-assisted tongue diagnosis published between January 1, 2014 and December 31, 2025, and analysed using Bibliometrix, VOSviewer, and CiteSpace, with major output dimensions including annual publication output and disciplinary distribution, journal and citation characteristics, country/region and institutional collaboration, author networks, keyword co-occurrence, and keyword burst detection. For the DTA meta-analysis, four databases [Scopus, PubMed, Web of Science, and China National Knowledge Infrastructure (CNKI)] were searched in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses of Diagnostic Test Accuracy (PRISMA-DTA) guidelines. A bivariate random-effects model hierarchical summary receiver operating characteristic (HSROC) was used to pool sensitivity and specificity, with subgroup analyses by disease category, AI model architecture, and sample-size strata. Methodological quality was assessed with the Quality Assessment of Diagnostic Accuracy Studies version 2 (QUADAS-2) tool, and publication bias was evaluated by Deeks’ funnel plot asymmetry test.</div></div><div><h3>Results</h3><div>A total of 198 publications met the bibliometric eligibility criteria. Annual output increased 24.5-fold (from 2 in 2014 to 49 in 2025), with the period 2022 – 2025 alone accounting for 65.2% of all publications. China contributed approximately 83.5% of all institutional affiliations, with Shanghai University of Traditional Chinese Medicine and Jiatuo Xu being the most productive institution and author, respectively. Keyword analysis identified four thematic clusters (AI and deep-learning architectures, image processing and segmentation, traditional Chinese medicine (TCM)-specific applications, and disease-specific applications) and a temporal evolution from traditional machine learning to deep learning and transformer-based, explainable, and multimodal AI architectures. Sixteen DTA meta-analysis studies (14 755 participants) covering metabolic and hepatic disorders, oncological and oral lesions, cardiovascular risk, diabetes, and other clinical applications were included in the DTA meta-analysis. The pooled sensitivity was 90.3% [95% confidence interval (CI): 86.7% – 93.1%] and the pooled specificity was 93.0% (95% CI: 90.6% – 94.7%); the area under the summary receiver operating characteristic (SROC) curve (AUC) was 0.961. Heterogeneity was substantial (<em>I</em><sup>2</sup> = 95.8% for sensitivity; <em>I</em><sup>2</sup> = 92.1% for specificity). Subgroup performance was broadly consisten","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"9 2","pages":"Pages 223-240"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148214661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-06-01Epub Date: 2026-06-11DOI: 10.1016/j.dcmed.2026.05.008
Dehghandar Mohammad , Nikbakht Maryam , Nadarabadi Fatemeh Yousefi
Objective
To perform a comparative evaluation of Mamdani and Takagi-Sugeno (TS) fuzzy inference systems for predicting peripheral vascular resistance from photoplethysmogram (PPG) signals, incorporating diagnostic parameters from Persian medicine (PM) pulsology.
Methods
Both fuzzy inference systems were implemented in MATLAB R2021b and validated using leave-one-out cross-validation (LOOCV) on clinical PM pulse diagnostic data collected from 35 healthy volunteers. The dataset included pulse frequency scale (1 – 6) and weakness scale (1 – 4) alongside corresponding PPG-derived peripheral vascular resistance indices (range: 0.019 – 0.983). The Mamdani system (with 35 rules) was designed using trapezoidal and triangular membership functions, a singleton fuzzifier, a product inference engine, and a centroid defuzzifier. The TS system (with 6 rules) was configured as a first-order model with Gaussian input membership functions. System performance was quantitatively evaluated using mean absolute error (MAE), root mean square error (RMSE), and the coefficient of determination (R2). Statistical significance of performance differences was assessed using a paired t test.
Results
he Mamdani inference system showed much higher prediction accuracy than the TS system. Comparative analysis revealed a substantial advantage for the Mamdani system (MAE = 0.007 63 ± 0.001 20, RMSE = 0.008 58 ± 0.001 50, R2 = 0.998 40 ± 0.000 80) over the TS system (MAE = 0.015 40 ± 0.002 10, RMSE = 0.022 48 ± 0.002 80, R2 = 0.989 20 ± 0.001 50). A paired t test comparing the absolute errors of the 35 LOOCV folds confirmed statistical significance [t (34) = 5.07, P < 0.001].
Conclusion
he findings suggest the potential suitability of the Mamdani system for certain precision-oriented analytical tasks. Both systems exhibit practical utility for integrative medicine diagnostics and wearable health-monitoring applications for healthy individuals, enabling a modern computational translation of PM pulsology.
{"title":"Comparative evaluation of Mamdani and Takagi-Sugeno fuzzy systems for predicting peripheral vascular resistance from photoplethysmogram signals using Persian medicine pulsology","authors":"Dehghandar Mohammad , Nikbakht Maryam , Nadarabadi Fatemeh Yousefi","doi":"10.1016/j.dcmed.2026.05.008","DOIUrl":"10.1016/j.dcmed.2026.05.008","url":null,"abstract":"<div><h3>Objective</h3><div>To perform a comparative evaluation of Mamdani and Takagi-Sugeno (TS) fuzzy inference systems for predicting peripheral vascular resistance from photoplethysmogram (PPG) signals, incorporating diagnostic parameters from Persian medicine (PM) pulsology.</div></div><div><h3>Methods</h3><div>Both fuzzy inference systems were implemented in MATLAB R2021b and validated using leave-one-out cross-validation (LOOCV) on clinical PM pulse diagnostic data collected from 35 healthy volunteers. The dataset included pulse frequency scale (1 – 6) and weakness scale (1 – 4) alongside corresponding PPG-derived peripheral vascular resistance indices (range: 0.019 – 0.983). The Mamdani system (with 35 rules) was designed using trapezoidal and triangular membership functions, a singleton fuzzifier, a product inference engine, and a centroid defuzzifier. The TS system (with 6 rules) was configured as a first-order model with Gaussian input membership functions. System performance was quantitatively evaluated using mean absolute error (MAE), root mean square error (RMSE), and the coefficient of determination (<em>R</em><sup>2</sup>). Statistical significance of performance differences was assessed using a paired <em>t</em> test.</div></div><div><h3>Results</h3><div>he Mamdani inference system showed much higher prediction accuracy than the TS system. Comparative analysis revealed a substantial advantage for the Mamdani system (MAE = 0.007 63 ± 0.001 20, RMSE = 0.008 58 ± 0.001 50, <em>R</em><sup>2</sup> = 0.998 40 ± 0.000 80) over the TS system (MAE = 0.015 40 ± 0.002 10, RMSE = 0.022 48 ± 0.002 80, <em>R</em><sup>2</sup> = 0.989 20 ± 0.001 50). A paired <em>t</em> test comparing the absolute errors of the 35 LOOCV folds confirmed statistical significance [<em>t</em> (34) = 5.07, <em>P</em> < 0.001].</div></div><div><h3>Conclusion</h3><div>he findings suggest the potential suitability of the Mamdani system for certain precision-oriented analytical tasks. Both systems exhibit practical utility for integrative medicine diagnostics and wearable health-monitoring applications for healthy individuals, enabling a modern computational translation of PM pulsology.</div></div>","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"9 2","pages":"Pages 257-264"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148214683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-06-01Epub Date: 2026-06-11DOI: 10.1016/j.dcmed.2026.05.005
Chen Qingqing , Zhang Hua , Guo Dong , Cai Hong , Lu Yiyu
<div><h3>Objective</h3><div>To elucidate the biological basis of traditional Chinese medicine (TCM) syndromes from the perspective of “same syndrome, different diseases” in patients with chronic hepatitis B (CHB), liver cirrhosis (LC), and hepatocellular carcinoma (HCC), thereby providing a complementary approach for the diagnosis and treatment of chronic liver diseases (CLD).</div></div><div><h3>Methods</h3><div>To investigate the dynamic characteristics of TCM syndromes in CLD, transcriptomic profiling of peripheral blood mononuclear cells (PBMCs) was performed from patients with CHB, LC, or HCC presenting with three TCM syndromes: liver gallbladder dampness heat syndrome (LGDHS), liver depression spleen deficiency syndrome (LDSDS), and liver kidney Yin deficiency syndrome (LKYDS). These participants were recruited at Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine between August 1, 2018 and December 31, 2021. Differentially expressed genes (DEGs) were identified using the random variance model (RVM) <em>F</em> test with false discovery rate (FDR) correction. Principal component analysis (PCA) and unsupervised hierarchical clustering were applied to visualize sample grouping. Dynamic network biomarkers (DNB) analysis was employed to detect critical transition stages during syndrome evolution, followed by Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses to characterize the functional roles and pathway involvement of the DNB members. Random forest (RF) analysis and the area under the receiver operating characteristic (ROC) curves (AUC) were used to rank the importance of candidate genes. External validation was performed using microarray data from an independent CLD cohort (GSE89377) and RNA-seq data from The Cancer Genome Atlas Liver Hepatocellular Carcinoma (TCGA-LIHC) dataset. Additionally, reverse transcription quantitative polymerase chain reaction (RT-qPCR) was performed on an independent cohort of LC patients to validate the expression levels of the candidate genes.</div></div><div><h3>Results</h3><div>The study included a total of 132 participants. DNB analysis identified LDSDS stage as a critical tipping point during TCM syndrome evolution across CHB, LC, and HCC. The phosphoinositide 3-kinase/protein kinase B (PI3K-AKT) signaling pathway was consistently enriched in the DNB analysis across all three types of CLD, suggesting its potential involvement in the critical transition of TCM syndromes. Among the 24 core DNB members of the PI3K-AKT pathway, four genes—integrin subunit beta 1 (<em>ITGB1</em>), collagen type IV alpha 1 chain (<em>COL4A1</em>), collagen type IV alpha 2 chain (<em>COL4A2</em>), and DNA damage inducible transcript 3 (<em>DDIT3</em>)—were identified by RF analysis (Gini score > 1) and ROC analysis. ROC analysis demonstrated high discriminative ability for distinguishing LGDHS from LKYDS in CHB patients, with AUC of <styled-conten
{"title":"Molecular features of traditional Chinese medicine syndrome evolution in chronic liver diseases: a dynamic network biomarker analysis","authors":"Chen Qingqing , Zhang Hua , Guo Dong , Cai Hong , Lu Yiyu","doi":"10.1016/j.dcmed.2026.05.005","DOIUrl":"10.1016/j.dcmed.2026.05.005","url":null,"abstract":"<div><h3>Objective</h3><div>To elucidate the biological basis of traditional Chinese medicine (TCM) syndromes from the perspective of “same syndrome, different diseases” in patients with chronic hepatitis B (CHB), liver cirrhosis (LC), and hepatocellular carcinoma (HCC), thereby providing a complementary approach for the diagnosis and treatment of chronic liver diseases (CLD).</div></div><div><h3>Methods</h3><div>To investigate the dynamic characteristics of TCM syndromes in CLD, transcriptomic profiling of peripheral blood mononuclear cells (PBMCs) was performed from patients with CHB, LC, or HCC presenting with three TCM syndromes: liver gallbladder dampness heat syndrome (LGDHS), liver depression spleen deficiency syndrome (LDSDS), and liver kidney Yin deficiency syndrome (LKYDS). These participants were recruited at Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine between August 1, 2018 and December 31, 2021. Differentially expressed genes (DEGs) were identified using the random variance model (RVM) <em>F</em> test with false discovery rate (FDR) correction. Principal component analysis (PCA) and unsupervised hierarchical clustering were applied to visualize sample grouping. Dynamic network biomarkers (DNB) analysis was employed to detect critical transition stages during syndrome evolution, followed by Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses to characterize the functional roles and pathway involvement of the DNB members. Random forest (RF) analysis and the area under the receiver operating characteristic (ROC) curves (AUC) were used to rank the importance of candidate genes. External validation was performed using microarray data from an independent CLD cohort (GSE89377) and RNA-seq data from The Cancer Genome Atlas Liver Hepatocellular Carcinoma (TCGA-LIHC) dataset. Additionally, reverse transcription quantitative polymerase chain reaction (RT-qPCR) was performed on an independent cohort of LC patients to validate the expression levels of the candidate genes.</div></div><div><h3>Results</h3><div>The study included a total of 132 participants. DNB analysis identified LDSDS stage as a critical tipping point during TCM syndrome evolution across CHB, LC, and HCC. The phosphoinositide 3-kinase/protein kinase B (PI3K-AKT) signaling pathway was consistently enriched in the DNB analysis across all three types of CLD, suggesting its potential involvement in the critical transition of TCM syndromes. Among the 24 core DNB members of the PI3K-AKT pathway, four genes—integrin subunit beta 1 (<em>ITGB1</em>), collagen type IV alpha 1 chain (<em>COL4A1</em>), collagen type IV alpha 2 chain (<em>COL4A2</em>), and DNA damage inducible transcript 3 (<em>DDIT3</em>)—were identified by RF analysis (Gini score > 1) and ROC analysis. ROC analysis demonstrated high discriminative ability for distinguishing LGDHS from LKYDS in CHB patients, with AUC of <styled-conten","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"9 2","pages":"Pages 241-256"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148214617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-06-01Epub Date: 2026-06-11DOI: 10.1016/j.dcmed.2026.05.012
Ling Xiong , Baoyin Sachula , Aobi Desi , Ni Ha , Dong Zhiheng , Wu Lan , Jin Bao , Ji Linbayaer
<div><h3>Objective</h3><div>To systematically evaluate the clinical efficacy of topical preparations of Mongolian medicine Manggari hot compress therapy (hereafter referred to as Manggari hot compress therapy) in treating cervical spondylotic radiculopathy (CSR) and explore the possible pharmacological material basis in the formula, providing evidence for the clinical application of Mongolian medicine in the treatment of CSR.</div></div><div><h3>Methods</h3><div>The clinical trial employed a randomized, controlled, open-label, and outcome-assessor-blinded design. The CSR patients who were treated at the Department of Traditional Therapeutics Outpatient Clinic, Xilinguole Meng Mongolian General Hospital between July 1, 2024 and August 31, 2025, were enrolled. They were randomly assigned to three groups: an oral control group (administration of oral administration of mecobalamin tablets combined with cervical electric traction), an experimental group (Manggari external hot compress), and a patch control group (flurbiprofen gel plaster). The intervention lasted two weeks. Before and after treatment, the following subjective indicators were recorded: Mongolian Medicine Syndrome (MMS) score, Visual Analog Scale (VAS) score, Northwick Park Neck Pain Questionnaire (NPQ) score, and tongue morphology. Serum levels of inflammatory markers [tumor necrosis factor (TNF)-α, interleukin (IL)-6, and IL-1β)] and oxidative stress markers [malondialdehyde (MDA) content, superoxide dismutase (SOD) activity, and glutathione peroxidase (GSH-Px) activity] were measured using enzyme-linked immunosorbent assay (ELISA). Overall therapeutic efficacy was evaluated. One month after treatment completion, a follow-up assessment was conducted, and the MMS, VAS, and NPQ scores were recorded again for all patients. For the pharmacological substance exploration, ultra-high-performance liquid chromatography-Q-exactive orbitrap-mass (UHPLC-QE-MS) was employed to analyze blood-absorbed prototype components of Manggari, under both positive and negative ion modes. The targeting relationship between the core active compounds and the target protein was validated using molecular docking.</div></div><div><h3>Results</h3><div>This study ultimately included 90 patients with CSR for analysis. Baseline characteristics showed no statistically significant differences among the three groups (<em>P</em> > 0.05). (i) Symptom scores. After treatment, the MMS, VAS, and NPQ scores decreased significantly from baseline in all three groups (<em>P</em> < 0.001). At follow-up, there was no significant difference in MMS, VAS, and NPQ scores of the experimental group compared with those at the end of the treatment (<em>P</em> > 0.05). After treatment, the experimental group showed significantly greater reductions in MMS, VAS, and NPQ scores than oral control and patch control groups (<em>P</em> < 0.001). At follow-up, these differences remained significant (<em>P</em> < 0.001). (ii) Inflammat
{"title":"Clinical efficacy and pharmacological basis of Mongolian medicine Manggari hot compress therapy for cervical spondylotic radiculopathy: a randomized controlled trial and serum pharmacochemistry study","authors":"Ling Xiong , Baoyin Sachula , Aobi Desi , Ni Ha , Dong Zhiheng , Wu Lan , Jin Bao , Ji Linbayaer","doi":"10.1016/j.dcmed.2026.05.012","DOIUrl":"10.1016/j.dcmed.2026.05.012","url":null,"abstract":"<div><h3>Objective</h3><div>To systematically evaluate the clinical efficacy of topical preparations of Mongolian medicine Manggari hot compress therapy (hereafter referred to as Manggari hot compress therapy) in treating cervical spondylotic radiculopathy (CSR) and explore the possible pharmacological material basis in the formula, providing evidence for the clinical application of Mongolian medicine in the treatment of CSR.</div></div><div><h3>Methods</h3><div>The clinical trial employed a randomized, controlled, open-label, and outcome-assessor-blinded design. The CSR patients who were treated at the Department of Traditional Therapeutics Outpatient Clinic, Xilinguole Meng Mongolian General Hospital between July 1, 2024 and August 31, 2025, were enrolled. They were randomly assigned to three groups: an oral control group (administration of oral administration of mecobalamin tablets combined with cervical electric traction), an experimental group (Manggari external hot compress), and a patch control group (flurbiprofen gel plaster). The intervention lasted two weeks. Before and after treatment, the following subjective indicators were recorded: Mongolian Medicine Syndrome (MMS) score, Visual Analog Scale (VAS) score, Northwick Park Neck Pain Questionnaire (NPQ) score, and tongue morphology. Serum levels of inflammatory markers [tumor necrosis factor (TNF)-α, interleukin (IL)-6, and IL-1β)] and oxidative stress markers [malondialdehyde (MDA) content, superoxide dismutase (SOD) activity, and glutathione peroxidase (GSH-Px) activity] were measured using enzyme-linked immunosorbent assay (ELISA). Overall therapeutic efficacy was evaluated. One month after treatment completion, a follow-up assessment was conducted, and the MMS, VAS, and NPQ scores were recorded again for all patients. For the pharmacological substance exploration, ultra-high-performance liquid chromatography-Q-exactive orbitrap-mass (UHPLC-QE-MS) was employed to analyze blood-absorbed prototype components of Manggari, under both positive and negative ion modes. The targeting relationship between the core active compounds and the target protein was validated using molecular docking.</div></div><div><h3>Results</h3><div>This study ultimately included 90 patients with CSR for analysis. Baseline characteristics showed no statistically significant differences among the three groups (<em>P</em> > 0.05). (i) Symptom scores. After treatment, the MMS, VAS, and NPQ scores decreased significantly from baseline in all three groups (<em>P</em> < 0.001). At follow-up, there was no significant difference in MMS, VAS, and NPQ scores of the experimental group compared with those at the end of the treatment (<em>P</em> > 0.05). After treatment, the experimental group showed significantly greater reductions in MMS, VAS, and NPQ scores than oral control and patch control groups (<em>P</em> < 0.001). At follow-up, these differences remained significant (<em>P</em> < 0.001). (ii) Inflammat","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"9 2","pages":"Pages 302-316"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148214618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-06-01Epub Date: 2026-06-11DOI: 10.1016/j.dcmed.2026.05.007
Wang Yu , Ding Pengcheng , Li Zhentao , Zhang Jiyu , Tu Liping , Xu Jijie , Xu Jiatuo
<div><h3>Objective</h3><div>To explore whether digital facial and tongue diagnostic technologies can support the assessment of coronary heart disease (CHD) patients for coronary artery stenosis severity, and examine potential associations between digital tongue diagnosis features and myocardial biomarkers.</div></div><div><h3>Methods</h3><div>The TFDA-1 face and tongue diagnosis instrument and the TDAS analysis system were used to perform intelligent visual examination and analysis of the facial and tongue in CHD patients who attended the Department of Cardiology at Shanghai Baoshan Hospital of Integrated Traditional Chinese and Western Medicine between October 2, 2023 and July 31, 2024. Variables were screened using principal component analysis (PCA) and multicollinearity analysis to construct four machine learning models, including random forest, LightGBM, decision tree, and naive Bayes, for the early prediction of coronary artery stenosis severity. Model performance metrics, including sensitivity, specificity, precision, F1 score, accuracy, and the area under the receiver operating characteristic (ROC) curve (AUC), were evaluated. Visual analyses were performed using the SHapley Additive exPlanations (SHAP) interpreter and decision curve analysis. For patients after percutaneous coronary intervention (PCI), a conceptual model linking cardiac biomarkers and tongue diagnosis was constructed using the partial least squares structural equation modeling (PLS-SEM), and its validity was assessed.</div></div><div><h3>Results</h3><div>A total of 459 CHD patients were enrolled and assigned to a PCI group and a non-PCI group (which comprised two subgroups: mild stenosis or less group, moderate stenosis or greater group). For sublingual vein (SV) features, the PCI group had lower SV-a and SV-b than the other groups (<em>P</em> < 0.01 and <em>P</em> < 0.05, respectively). For tongue surface features, the PCI group had significantly higher tongue body (TB)-L, TB-a, and TB-b (<em>P</em> < 0.05, <em>P</em> < 0.01, and <em>P</em> < 0.001, respectively), as well as higher tongue coating (TC)-a and TC-b (<em>P</em> < 0.01 and <em>P</em> < 0.001, respectively). Age, SV-a, SV-b, creatine kinase-myocardial band (CK-MB), CK, TC-a, lip-L, and lip-b were incorporated in the machine learning models. The random forest model performed best, with an AUC of 0.924, an F1 score of 0.839, precision of 0.807, accuracy of 0.864, sensitivity of 0.873, and specificity of 0.839. Decision curve analysis indicated that both LightGBM and random forest had clinical utility. PLS-SEM confirmed the pathway relationships: myocardial biomarkers → TB and myocardial biomarkers → TC (coefficient = – 0.238, <em>t</em> = 2.239, <em>P</em> = 0.025, and coefficient = – 0.270, <em>t</em> = 2.522, <em>P</em> = 0.012, respectively).</div></div><div><h3>Conclusion</h3><div>This study developed a noninvasive early warning model for coronary artery stenosis in patients with CHD. It
目的探讨数字面部和舌头诊断技术是否可以支持冠心病患者冠状动脉狭窄严重程度的评估，并研究数字舌头诊断特征与心肌生物标志物之间的潜在关联。方法对2023年10月2日至2024年7月31日在上海宝山中西医结合医院心内科就诊的冠心病患者，采用TFDA-1型面部舌部诊断仪和TDAS分析系统对患者面部舌部进行智能视觉检查和分析。采用主成分分析（PCA）和多重共线性分析筛选变量，构建随机森林、LightGBM、决策树和朴素贝叶斯4种机器学习模型，用于早期预测冠状动脉狭窄严重程度。评估模型性能指标，包括敏感性、特异性、精密度、F1评分、准确度和受试者工作特征曲线下面积（AUC）。使用SHapley加性解释（SHAP）解释器和决策曲线分析进行可视化分析。针对经皮冠状动脉介入治疗（PCI）患者，采用偏最小二乘结构方程模型（PLS-SEM）构建了心脏生物标志物与舌诊之间的概念模型，并对其有效性进行了评估。结果共纳入459例冠心病患者，分为PCI组和非PCI组（包括轻度狭窄或更少组、中度狭窄或更大组）。舌下静脉（SV）特征，PCI组SV-a和SV-b低于其他组（P <； 0.01和P <； 0.05）。舌面特征方面，PCI组舌体(TB)-L、TB-a、TB-b显著增高（P < 0.05, P < 0.01, P < 0.001），舌苔(TC)-a、TC-b显著增高（P < 0.01, P < 0.001）。将年龄、SV-a、SV-b、肌酸激酶-心肌带（CK- mb）、CK、TC-a、lip-L和lip-b纳入机器学习模型。随机森林模型最优，AUC为0.924，F1评分为0.839，精度为0.807，准确度为0.864，灵敏度为0.873，特异性为0.839。决策曲线分析表明，LightGBM和random forest均具有临床应用价值。PLS-SEM证实了心肌生物标志物→TB和心肌生物标志物→TC的通路关系（系数= - 0.238,t = 2.239, P = 0.025，系数= - 0.270,t = 2.522, P = 0.012）。结论本研究建立了冠心病患者冠状动脉狭窄的无创预警模型。应用PLS-SEM研究pci后心脏生物标志物与舌诊之间的关系，并验证了所提出的关联链。综上所述，结合现代数字技术的智能中医视觉诊断可为冠心病风险评估和综合健康管理提供支持。
{"title":"Facial and tongue features in traditional Chinese medicine for coronary artery stenosis warning and their association chain with cardiac biomarkers","authors":"Wang Yu , Ding Pengcheng , Li Zhentao , Zhang Jiyu , Tu Liping , Xu Jijie , Xu Jiatuo","doi":"10.1016/j.dcmed.2026.05.007","DOIUrl":"10.1016/j.dcmed.2026.05.007","url":null,"abstract":"<div><h3>Objective</h3><div>To explore whether digital facial and tongue diagnostic technologies can support the assessment of coronary heart disease (CHD) patients for coronary artery stenosis severity, and examine potential associations between digital tongue diagnosis features and myocardial biomarkers.</div></div><div><h3>Methods</h3><div>The TFDA-1 face and tongue diagnosis instrument and the TDAS analysis system were used to perform intelligent visual examination and analysis of the facial and tongue in CHD patients who attended the Department of Cardiology at Shanghai Baoshan Hospital of Integrated Traditional Chinese and Western Medicine between October 2, 2023 and July 31, 2024. Variables were screened using principal component analysis (PCA) and multicollinearity analysis to construct four machine learning models, including random forest, LightGBM, decision tree, and naive Bayes, for the early prediction of coronary artery stenosis severity. Model performance metrics, including sensitivity, specificity, precision, F1 score, accuracy, and the area under the receiver operating characteristic (ROC) curve (AUC), were evaluated. Visual analyses were performed using the SHapley Additive exPlanations (SHAP) interpreter and decision curve analysis. For patients after percutaneous coronary intervention (PCI), a conceptual model linking cardiac biomarkers and tongue diagnosis was constructed using the partial least squares structural equation modeling (PLS-SEM), and its validity was assessed.</div></div><div><h3>Results</h3><div>A total of 459 CHD patients were enrolled and assigned to a PCI group and a non-PCI group (which comprised two subgroups: mild stenosis or less group, moderate stenosis or greater group). For sublingual vein (SV) features, the PCI group had lower SV-a and SV-b than the other groups (<em>P</em> < 0.01 and <em>P</em> < 0.05, respectively). For tongue surface features, the PCI group had significantly higher tongue body (TB)-L, TB-a, and TB-b (<em>P</em> < 0.05, <em>P</em> < 0.01, and <em>P</em> < 0.001, respectively), as well as higher tongue coating (TC)-a and TC-b (<em>P</em> < 0.01 and <em>P</em> < 0.001, respectively). Age, SV-a, SV-b, creatine kinase-myocardial band (CK-MB), CK, TC-a, lip-L, and lip-b were incorporated in the machine learning models. The random forest model performed best, with an AUC of 0.924, an F1 score of 0.839, precision of 0.807, accuracy of 0.864, sensitivity of 0.873, and specificity of 0.839. Decision curve analysis indicated that both LightGBM and random forest had clinical utility. PLS-SEM confirmed the pathway relationships: myocardial biomarkers → TB and myocardial biomarkers → TC (coefficient = – 0.238, <em>t</em> = 2.239, <em>P</em> = 0.025, and coefficient = – 0.270, <em>t</em> = 2.522, <em>P</em> = 0.012, respectively).</div></div><div><h3>Conclusion</h3><div>This study developed a noninvasive early warning model for coronary artery stenosis in patients with CHD. It","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"9 2","pages":"Pages 184-196"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148214688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-06-01Epub Date: 2026-06-11DOI: 10.1016/j.dcmed.2026.05.006
Zhang Tongbin , Xu Haoran , Wang Ziyi , Pan Chuanjun , Wang Zheng , Wang Lei
<div><h3>Objective</h3><div>To address the lack of fine-grained clinical recognition for specific Yang deficiency syndrome subtypes and the limitations of conventional object detection models in extracting irregular, low-contrast tongue phenotypes. This study aims to develop an objective subtype recognition framework based on an improved You Only Look Once nano (YOLO11n) architecture, using a standardized visual phenotype matrix to translate macroscopic traditional Chinese medicine (TCM) descriptions into quantifiable clinical targets.</div></div><div><h3>Methods</h3><div>This cross-sectional diagnostic study consecutively enrolled adult inpatients admitted to the Department of Thyroid and Breast Surgery, The First Affiliated Hospital of Wannan Medical University (Yijishan Hospital), between September 1, 2024 and June 1, 2025, who were suspected of having Yang deficiency constitution based on initial TCM consultation. Clinical tongue image data were collected for analysis. Based on an Expert Visual Phenotype Annotation Matrix, a five-category recognition system was established, including the following TCM syndrome subtypes: spleen-dampness exuberance syndrome, mild kidney Yang deficiency syndrome, upper heat and lower cold syndrome, simultaneous Yin-Yang deficiency syndrome, and Yin deficiency and fluid depletion syndrome (negative control). The proposed Yang deficiency YOLO (YD-YOLO) model, built upon the YOLO11n baseline, integrates the Cross Stage Partial with kernel size 2 (C3k2)-GhostBottleneck-Dynamic Convolution (GBDC) module into the backbone to adaptively extract low-contrast features, and embeds the multipath aggregation coordinate attention (MACA) mechanism into the neck to suppress background interference through multi-scale spatial coordination. Gradient-weighted class activation mapping (Grad-CAM) was used to visualize feature attribution and evaluate the biological plausibility of the model’s focus. Model performance was evaluated through ablation and comparative experiments using mean average precision (mAP), precision, recall, F1 score, inference speed (frames per second, FPS), overall accuracy, Cohen’s kappa, and the area under the receiver operating characteristic (ROC) curve (AUC).</div></div><div><h3>Results</h3><div>Based on the final inclusion of 1 186 clinical cases, the YD-YOLO model had an overall accuracy of 91.5%, a Cohen’s kappa of 0.912, and an mAP@50 of 0.731 [higher than the YOLO11n baseline (0.681)], with AUC ranging from 0.91 to 0.97 across all TCM syndrome subtypes. Among the TCM syndrome subtypes, the mild kidney Yang deficiency syndrome had the highest mAP@50 (0.900), and the inference speed reached 89.00 FPS. Grad-CAM analysis showed that the model localized activation to key TCM pathological features, such as marginal tooth marks and focal root coatings, while suppressing non-diagnostic oral background noise.</div></div><div><h3>Conclusion</h3><div>The YD-YOLO model demonstrates the feasibility of deep learn
目的解决临床对特定阳虚证亚型缺乏细粒度识别和常规目标检测模型在提取不规则、低对比舌表型方面的局限性。本研究旨在开发一个基于改进的You Only Look Once nano （YOLO11n）架构的客观亚型识别框架，使用标准化的视觉表型矩阵将宏观中医描述转化为可量化的临床靶标。方法采用横断面诊断方法，连续选取皖南医科大学第一附属医院（一积山医院）甲状腺乳腺外科于2024年9月1日至2025年6月1日经中医初步会诊疑似阳虚体质的成年住院患者。收集临床舌象资料进行分析。基于专家视觉表型注释矩阵，建立五类识别体系，包括脾湿盛证、轻度肾阳虚证、上热下寒证、阴阳同时虚证、阴虚液虚证（阴性对照）等中医证型。提出的阳虚YOLO （YD-YOLO）模型以YOLO11n基线为基础，在主干中集成了核尺寸为2的Cross Stage Partial (C3k2)-GhostBottleneck-Dynamic Convolution （GBDC）模块自适应提取低对比度特征，在颈部中嵌入多径聚集坐标注意（MACA）机制，通过多尺度空间协调抑制背景干扰。梯度加权类激活映射（Grad-CAM）用于可视化特征归属并评估模型焦点的生物合理性。通过消融和对比实验评估模型的性能，包括平均精度（mAP）、精度、召回率、F1评分、推理速度（每秒帧数，FPS）、总体精度、科恩kappa和接收者工作特征（ROC）曲线下面积（AUC）。结果在最终纳入1 186例临床病例的基础上，YD-YOLO模型的总体准确率为91.5%,Cohen’s kappa为0.912，mAP@50为0.731[高于YOLO11n基线（0.681）]，所有中医证候亚型的AUC范围为0.91 ~ 0.97。在中医证候亚型中，轻肾阳虚证得分最高mAP@50(0.900)，推理速度达到89.00 FPS。gradi - cam分析显示，该模型将激活定位于关键的中医病理特征，如牙印边缘和病灶根膜，同时抑制非诊断性口腔背景噪声。结论采用深度学习模型对中医阳虚亚型进行细粒度分型是可行的。通过将视觉表型量化与模型可解释性相结合，所提出的框架为辨证提供了客观依据，支持标准化数字诊断系统的发展，并为中医实践提供临床决策支持。
{"title":"Deep learning for subtype recognition of Yang deficiency tongue images in traditional Chinese medicine","authors":"Zhang Tongbin , Xu Haoran , Wang Ziyi , Pan Chuanjun , Wang Zheng , Wang Lei","doi":"10.1016/j.dcmed.2026.05.006","DOIUrl":"10.1016/j.dcmed.2026.05.006","url":null,"abstract":"<div><h3>Objective</h3><div>To address the lack of fine-grained clinical recognition for specific Yang deficiency syndrome subtypes and the limitations of conventional object detection models in extracting irregular, low-contrast tongue phenotypes. This study aims to develop an objective subtype recognition framework based on an improved You Only Look Once nano (YOLO11n) architecture, using a standardized visual phenotype matrix to translate macroscopic traditional Chinese medicine (TCM) descriptions into quantifiable clinical targets.</div></div><div><h3>Methods</h3><div>This cross-sectional diagnostic study consecutively enrolled adult inpatients admitted to the Department of Thyroid and Breast Surgery, The First Affiliated Hospital of Wannan Medical University (Yijishan Hospital), between September 1, 2024 and June 1, 2025, who were suspected of having Yang deficiency constitution based on initial TCM consultation. Clinical tongue image data were collected for analysis. Based on an Expert Visual Phenotype Annotation Matrix, a five-category recognition system was established, including the following TCM syndrome subtypes: spleen-dampness exuberance syndrome, mild kidney Yang deficiency syndrome, upper heat and lower cold syndrome, simultaneous Yin-Yang deficiency syndrome, and Yin deficiency and fluid depletion syndrome (negative control). The proposed Yang deficiency YOLO (YD-YOLO) model, built upon the YOLO11n baseline, integrates the Cross Stage Partial with kernel size 2 (C3k2)-GhostBottleneck-Dynamic Convolution (GBDC) module into the backbone to adaptively extract low-contrast features, and embeds the multipath aggregation coordinate attention (MACA) mechanism into the neck to suppress background interference through multi-scale spatial coordination. Gradient-weighted class activation mapping (Grad-CAM) was used to visualize feature attribution and evaluate the biological plausibility of the model’s focus. Model performance was evaluated through ablation and comparative experiments using mean average precision (mAP), precision, recall, F1 score, inference speed (frames per second, FPS), overall accuracy, Cohen’s kappa, and the area under the receiver operating characteristic (ROC) curve (AUC).</div></div><div><h3>Results</h3><div>Based on the final inclusion of 1 186 clinical cases, the YD-YOLO model had an overall accuracy of 91.5%, a Cohen’s kappa of 0.912, and an mAP@50 of 0.731 [higher than the YOLO11n baseline (0.681)], with AUC ranging from 0.91 to 0.97 across all TCM syndrome subtypes. Among the TCM syndrome subtypes, the mild kidney Yang deficiency syndrome had the highest mAP@50 (0.900), and the inference speed reached 89.00 FPS. Grad-CAM analysis showed that the model localized activation to key TCM pathological features, such as marginal tooth marks and focal root coatings, while suppressing non-diagnostic oral background noise.</div></div><div><h3>Conclusion</h3><div>The YD-YOLO model demonstrates the feasibility of deep learn","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"9 2","pages":"Pages 197-210"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148214689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-06-01Epub Date: 2026-06-11DOI: 10.1016/j.dcmed.2026.05.010
He Jiayi , Xie Jiadong , Hu Kongfa , Li Haiyan
Objective
This study proposes a clustering framework for Chinese materia medica (CMM) based on a large language model (LLM), aiming to explore potential compatibility patterns among CMMs from the semantic perspective of CMM property theory.
Methods
First, a CMM property knowledge base was constructed based on Chinese Materia Medica, including 567 commonly used CMMs characterized by four properties, five flavors, and meridian tropism. Then, 49 CMMs derived from 10 prescriptions for Zangdu (脏毒, pathogenic toxins) recorded in Waike Zhengzong (《外科正宗》, Orthodox Manual of External Medicine) and Yangke Xinde Ji (《疡科心得集》, Collected Insights on Ulcer Medicine) were selected as the experimental dataset. Five semantic representation methods—One-Hot, Word2Vec, Bidirectional Encoder Representations from Transformers (BERT), Beijing Academy of Artificial Intelligence General Embedding (BGE), and Qwen—were applied to encode CMM property information into vector representations. Subsequently, t-distributed Stochastic Neighbor Embedding (t-SNE) was used for nonlinear dimensionality reduction on high-dimensional semantic vectors, followed by k-means clustering (k = 7). Clustering performance was evaluated using the Silhouette Score (SS), Davies-Bouldin Index (DBI), and Calinski-Harabasz Index (CHI).
Results
The Qwen-based clustering method, CMM-EmbedCluster, achieved the highest SS (0.607 4) and CHI (158.057 2), as well as the lowest DBI (0.499 5), indicating improved cluster separation and compactness compared with other methods. Visualization of CMM clustering results showed that the clusters were well separated in the low-dimensional space, with strong inter-cluster discrimination and high intra-cluster functional consistency. Further interpretability analysis of CMM clustering results revealed stable structural differences among clusters in terms of four properties, five flavors, and meridian tropism, forming functional partitions consistent with CMM property theory.
Conclusion
CMM-EmbedCluster utilizes an LLM to achieve semantic-level representation and clustering of CMMs within the framework of CMM property theory, providing support for exploring potential compatibility patterns among CMMs from the perspective of CMM property semantics.
目的提出一种基于大语言模型（LLM）的中药材聚类框架，旨在从中医药材属性理论的语义角度探索中医药材之间潜在的兼容模式。方法首先，以中药材为基础，建立中医中药属性知识库，包括567种常用中医中药，具有四性、五味、经向等特点；然后，选取《外医正宗》（《正统外医学手册》）和《阳科信德集》（《疡溃疡医学真识集》）中记载的10种“藏毒”方剂中的49种中药作为实验数据集。采用one - hot、Word2Vec、双向编码器表示（BERT）、北京人工智能通用嵌入研究院（BGE）和qwen五种语义表示方法，将CMM属性信息编码为向量表示。随后，采用t分布随机邻居嵌入（t-SNE）对高维语义向量进行非线性降维，然后进行k-means聚类（k = 7）。采用Silhouette Score （SS）、Davies-Bouldin Index （DBI）和Calinski-Harabasz Index （CHI）评价聚类性能。结果基于qwen的CMM-EmbedCluster聚类方法获得了最高的SS（0.607 4）和CHI(158.057 2)，最低的DBI(0.499 5)，表明与其他方法相比，聚类分离和紧凑性得到了改善。CMM聚类结果的可视化显示，聚类在低维空间中分离良好，具有较强的簇间判别性和较高的簇内功能一致性。进一步对CMM聚类结果进行可解释性分析，发现各聚类在四性、五味、经向等方面存在稳定的结构差异，形成了符合CMM性质理论的功能分区。结论CMM- embedcluster利用LLM在CMM属性理论框架下实现了CMM的语义级表示和聚类，为从CMM属性语义的角度探索CMM之间潜在的兼容模式提供了支持。
{"title":"CMM-EmbedCluster: a clustering framework for Chinese materia medica based on large language model and Chinese materia medica property theory","authors":"He Jiayi , Xie Jiadong , Hu Kongfa , Li Haiyan","doi":"10.1016/j.dcmed.2026.05.010","DOIUrl":"10.1016/j.dcmed.2026.05.010","url":null,"abstract":"<div><h3>Objective</h3><div>This study proposes a clustering framework for Chinese materia medica (CMM) based on a large language model (LLM), aiming to explore potential compatibility patterns among CMMs from the semantic perspective of CMM property theory.</div></div><div><h3>Methods</h3><div>First, a CMM property knowledge base was constructed based on <em>Chinese Materia Medica</em>, including 567 commonly used CMMs characterized by four properties, five flavors, and meridian tropism. Then, 49 CMMs derived from 10 prescriptions for Zangdu (脏毒, pathogenic toxins) recorded in <em>Waike Zhengzong</em> (《外科正宗》, <em>Orthodox Manual of External Medicine</em>) and <em>Yangke Xinde Ji</em> (《疡科心得集》, <em>Collected Insights on Ulcer Medicine</em>) were selected as the experimental dataset. Five semantic representation methods—One-Hot, Word2Vec, Bidirectional Encoder Representations from Transformers (BERT), Beijing Academy of Artificial Intelligence General Embedding (BGE), and Qwen—were applied to encode CMM property information into vector representations. Subsequently, t-distributed Stochastic Neighbor Embedding (t-SNE) was used for nonlinear dimensionality reduction on high-dimensional semantic vectors, followed by <em>k</em>-means clustering (<em>k</em> = 7). Clustering performance was evaluated using the Silhouette Score (SS), Davies-Bouldin Index (DBI), and Calinski-Harabasz Index (CHI).</div></div><div><h3>Results</h3><div>The Qwen-based clustering method, CMM-EmbedCluster, achieved the highest SS (0.607 4) and CHI (158.057 2), as well as the lowest DBI (0.499 5), indicating improved cluster separation and compactness compared with other methods. Visualization of CMM clustering results showed that the clusters were well separated in the low-dimensional space, with strong inter-cluster discrimination and high intra-cluster functional consistency. Further interpretability analysis of CMM clustering results revealed stable structural differences among clusters in terms of four properties, five flavors, and meridian tropism, forming functional partitions consistent with CMM property theory.</div></div><div><h3>Conclusion</h3><div>CMM-EmbedCluster utilizes an LLM to achieve semantic-level representation and clustering of CMMs within the framework of CMM property theory, providing support for exploring potential compatibility patterns among CMMs from the perspective of CMM property semantics.</div></div>","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"9 2","pages":"Pages 278-289"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148214621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To investigate the protective effects of Gouqizi (Lycii Fructus, GQZ)-Danshen (Salviae Miltiorrhizae Radix et Rhizoma, DS) against hydrogen peroxide (H2O2)-induced oxidative injury in 661W retinal photoreceptor cells and to explore whether these effects involve angiopoietin-like 4 (ANGPTL4).
Methods
Liquid chromatography-mass spectrometry (LC-MS) was used to identify the major components of GQZ-DS aqueous extract. An H2O2-induced oxidative injury model was established in 661W cells. Working concentrations of H2O2 and GQZ-DS were determined using the cell counting kit-8 (CCK-8) assay. Cells were subjected to GQZ-DS, ANGPTL4 knockdown, or ANGPTL4 overexpression as indicated. Flow cytometry was used to analyze cell cycle distribution, apoptotic rate, and intracellular reactive oxygen species (ROS). Colorimetric determination of malondialdehyde (MDA) content and superoxide dismutase (SOD) activity using the thiobarbituric acid (TBA) method was performed. The protein expression level of ANGPTL4 was assessed by immunofluorescence. Reverse transcription-quantitative polymerase chain reaction (RT-qPCR) was performed to quantify the mRNA level of ANGPTL4. Western blot was used to detect the protein levels of ANGPTL4 and cleaved caspase-3.
Results
LC-MS identified five major constituents in the GQZ-DS aqueous extract: 2-O-β-D-glucopyranosyl-L-ascorbic acid, rutin, D-galactose, salvianolic acid A, and tanshinone IIA. The CCK-8 method selected 300 μmol/L H2O2 as the oxidative stress condition for experiments, and 0.05 and 0.1 g/mL were selected as the low and high doses of GQZ-DS, respectively, for subsequent experiments. The intervention with H2O2 resulted in reduced cell viability, elevated ROS and MDA levels, decreased SOD activity, increased apoptotic rate, upregulated cleaved caspase-3 expression, and G0/G1 phase cell cycle arrest of 661W cells. Both low and high doses of GQZ-DS alleviated these alterations, with high dose exhibiting stronger protective effects (P < 0.05 or P < 0.01). GQZ-DS also downregulated ANGPTL4 expression at both the mRNA and protein levels. Following plasmid transfection of cells, the study further revealed that ANGPTL4 knockdown mitigated oxidative stress and apoptosis-related injury, whereas ANGPTL4 overexpression exacerbated these pathological changes. Moreover, GQZ-DS partially reversed the degree of cellular oxidative damage induced by ANGPTL4 overexpression. [
Conclusion
GQZ-DS can alleviate the H2O2-induced oxidative injury of 661W retinal photoreceptor cells, and the effects are related to the down-regulation of ANGPTL4 expression.
{"title":"Attenuation of oxidative injury in retinal photoreceptor cells by Gouqizi (Lycii Fructus) and Danshen (Salviae Miltiorrhizae Radix et Rhizoma) through modulation of ANGPTL4","authors":"Peng Jun , Jiang Junjiang , Zhong Junnan , Zhou Siyi , Hu Tingyan , Chen Xuyu , Peng Qinghua , Zhou Yasha","doi":"10.1016/j.dcmed.2026.05.011","DOIUrl":"10.1016/j.dcmed.2026.05.011","url":null,"abstract":"<div><h3>Objective</h3><div>To investigate the protective effects of Gouqizi (Lycii Fructus, GQZ)-Danshen (Salviae Miltiorrhizae Radix et Rhizoma, DS) against hydrogen peroxide (H<sub>2</sub>O<sub>2</sub>)-induced oxidative injury in 661W retinal photoreceptor cells and to explore whether these effects involve angiopoietin-like 4 (ANGPTL4).</div></div><div><h3>Methods</h3><div>Liquid chromatography-mass spectrometry (LC-MS) was used to identify the major components of GQZ-DS aqueous extract. An H<sub>2</sub>O<sub>2</sub>-induced oxidative injury model was established in 661W cells. Working concentrations of H<sub>2</sub>O<sub>2</sub> and GQZ-DS were determined using the cell counting kit-8 (CCK-8) assay. Cells were subjected to GQZ-DS, ANGPTL4 knockdown, or ANGPTL4 overexpression as indicated. Flow cytometry was used to analyze cell cycle distribution, apoptotic rate, and intracellular reactive oxygen species (ROS). Colorimetric determination of malondialdehyde (MDA) content and superoxide dismutase (SOD) activity using the thiobarbituric acid (TBA) method was performed. The protein expression level of ANGPTL4 was assessed by immunofluorescence. Reverse transcription-quantitative polymerase chain reaction (RT-qPCR) was performed to quantify the mRNA level of ANGPTL4. Western blot was used to detect the protein levels of ANGPTL4 and cleaved caspase-3.</div></div><div><h3>Results</h3><div>LC-MS identified five major constituents in the GQZ-DS aqueous extract: 2-O-β-D-glucopyranosyl-L-ascorbic acid, rutin, D-galactose, salvianolic acid A, and tanshinone IIA. The CCK-8 method selected 300 μmol/L H<sub>2</sub>O<sub>2</sub> as the oxidative stress condition for experiments, and 0.05 and 0.1 g/mL were selected as the low and high doses of GQZ-DS, respectively, for subsequent experiments. The intervention with H<sub>2</sub>O<sub>2</sub> resulted in reduced cell viability, elevated ROS and MDA levels, decreased SOD activity, increased apoptotic rate, upregulated cleaved caspase-3 expression, and G0/G1 phase cell cycle arrest of 661W cells. Both low and high doses of GQZ-DS alleviated these alterations, with high dose exhibiting stronger protective effects (<em>P</em> < 0.05 or <em>P</em> < 0.01). GQZ-DS also downregulated ANGPTL4 expression at both the mRNA and protein levels. Following plasmid transfection of cells, the study further revealed that ANGPTL4 knockdown mitigated oxidative stress and apoptosis-related injury, whereas ANGPTL4 overexpression exacerbated these pathological changes. Moreover, GQZ-DS partially reversed the degree of cellular oxidative damage induced by ANGPTL4 overexpression. <strong>[</strong></div></div><div><h3>Conclusion</h3><div>GQZ-DS can alleviate the H<sub>2</sub>O<sub>2</sub>-induced oxidative injury of 661W retinal photoreceptor cells, and the effects are related to the down-regulation of ANGPTL4 expression.</div></div>","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"9 2","pages":"Pages 290-301"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148214620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yin-Yang theory is one of the core components of the foundational theory of traditional Chinese medicine (TCM), yet its classification as philosophical or scientific has long been controversial. To move beyond the longstanding either-philosophy-or-science debate surrounding Yin-Yang theory in TCM, this article, for the first time, proposes a three-level framework spanning macro, meso, and micro perspectives. At the macro level, Yin and Yang are a theoretical achievement of ancient Chinese natural philosophy, used to explain universal laws governing how the cosmos operates, which constitutes Yin-Yang theory in philosophy; at the meso level, Huangdi Neijing (《黄帝内经》, Inner Canon of Huangdi) translated Yin-Yang from a cosmological framework into medical discourse, making it a core methodological basis for clinical pattern differentiation and treatment, which constitutes Yin-Yang theory in medicine; at the micro level, Yin-Yang theory in TCM has increasingly converged with modern science, showing scientific features that are testable and reproducible, which constitutes Yin-Yang theory in science. The article further demonstrates that Yin-Yang theory in TCM differs markedly from Yin-Yang as a general philosophical doctrine in core application and practical orientation: in the course of its medical transformation, elements related to life phenomena were selectively incorporated, while, within a medical context, abstract propositions such as cosmological speculation were bracketed and rendered concrete, thereby achieving a practice-oriented transition from philosophy to medicine. Based on this, the present study conducts analyses from four aspects, namely philosophical roots, clinical application, modern scientific interpretation, and implications for life sciences; it substantiates the logical basis for Yin-Yang theory in TCM as the overarching framework for clinical pattern differentiation and treatment, reviews modern research progress from perspectives such as systems science and network regulation, and explores its potential value in advancing a new paradigm of state-based medicine. The study suggests that an accurate understanding of Yin-Yang theory in TCM requires moving beyond the either-philosophy-or-science binary and analyzing specific issues on a case-by-case basis. Across different perspectives, Yin-Yang theory in TCM has philosophical, medical, and scientific attributes. Only by grounding the theory in actual clinical efficacy and engaging with modern science can the innovative development of Yin-Yang theory in TCM be promoted, thereby providing valuable Eastern insights for building a life science system with original Chinese contributions.
{"title":"The macro, meso, and micro dimensions of Yin-Yang theory in traditional Chinese medicine: a three-level analysis of Yin and Yang","authors":"Ouyang Miao , Zhang Gedi , Yu Mengdan , Liu Hongning","doi":"10.1016/j.dcmed.2026.05.003","DOIUrl":"10.1016/j.dcmed.2026.05.003","url":null,"abstract":"<div><div>Yin-Yang theory is one of the core components of the foundational theory of traditional Chinese medicine (TCM), yet its classification as philosophical or scientific has long been controversial. To move beyond the longstanding either-philosophy-or-science debate surrounding Yin-Yang theory in TCM, this article, for the first time, proposes a three-level framework spanning macro, meso, and micro perspectives. At the macro level, Yin and Yang are a theoretical achievement of ancient Chinese natural philosophy, used to explain universal laws governing how the cosmos operates, which constitutes Yin-Yang theory in philosophy; at the meso level, <em>Huangdi Neijing</em> (《黄帝内经》, <em>Inner Canon of Huangdi</em>) translated Yin-Yang from a cosmological framework into medical discourse, making it a core methodological basis for clinical pattern differentiation and treatment, which constitutes Yin-Yang theory in medicine; at the micro level, Yin-Yang theory in TCM has increasingly converged with modern science, showing scientific features that are testable and reproducible, which constitutes Yin-Yang theory in science. The article further demonstrates that Yin-Yang theory in TCM differs markedly from Yin-Yang as a general philosophical doctrine in core application and practical orientation: in the course of its medical transformation, elements related to life phenomena were selectively incorporated, while, within a medical context, abstract propositions such as cosmological speculation were bracketed and rendered concrete, thereby achieving a practice-oriented transition from philosophy to medicine. Based on this, the present study conducts analyses from four aspects, namely philosophical roots, clinical application, modern scientific interpretation, and implications for life sciences; it substantiates the logical basis for Yin-Yang theory in TCM as the overarching framework for clinical pattern differentiation and treatment, reviews modern research progress from perspectives such as systems science and network regulation, and explores its potential value in advancing a new paradigm of state-based medicine. The study suggests that an accurate understanding of Yin-Yang theory in TCM requires moving beyond the either-philosophy-or-science binary and analyzing specific issues on a case-by-case basis. Across different perspectives, Yin-Yang theory in TCM has philosophical, medical, and scientific attributes. Only by grounding the theory in actual clinical efficacy and engaging with modern science can the innovative development of Yin-Yang theory in TCM be promoted, thereby providing valuable Eastern insights for building a life science system with original Chinese contributions.</div></div>","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"9 2","pages":"Pages 211-222"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148214690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-06-01Epub Date: 2026-06-11DOI: 10.1016/j.dcmed.2026.05.002
Li Danyang , Ai Min , Zhou Pai , Deng Ying , Yang Chaoyang , Peng Qinghua
The philosophy of “treating disease before its onset” is a fundamental concept of traditional Chinese medicine (TCM), permeating its diagnostic and therapeutic framework, and is central to clinical practice. However, current TCM diagnostic and treatment models for the “pre-disease to disease” window period face several limitations, including the lack of comprehensive clinical parameters, difficulties in characterizing and integrating heterogeneous multimodal data, and insufficient dynamic precision in interventions and efficacy evaluations. To address these issues, guided by Professor Candong Li’s theory of TCM stateology, this study focuses on integrating objective multimodal data. It proposes a new model for personalized TCM diagnosis and treatment targeting the “pre-disease to disease” window period. This approach first proposes the idea of restructuring the conceptual framework of “symptom” and integrating multi-source heterogeneous data at macroscopic, mesoscopic, and microscopic levels to form a three-dimensional assessment indicator system. By integrating graph neural networks, convolutional neural networks, attention mechanisms, and knowledge graph-guided weight allocation, this approach enables collaborative representation, alignment, and fusion of multi-source data. Subsequently, it plans to construct a multimodal fusion model at both feature and decision levels, in order to establish mappings between indicators and TCM state elements, and to screen key indicators characterizing pathological evolution during the window period. Furthermore, it proposes a technical path for enhancing model interpretability using methods such as SHapley Additive exPlanations (SHAP) and Ablation-CAM++. Finally, with state assessment as the core, it proposes the concept of constructing a dynamic evaluation method for individualized diagnosis and treatment based on time-series data analysis using algorithms such as long short-term memory (LSTM) networks and gated recurrent units (GRUs). Moreover, a causal inference framework and semi-supervised learning strategies are introduced to enable quantitative evaluation of individual intervention effects and to provide interpretable therapeutic feedback, forming a complete technical path from data representation and fusion, weight adjustment, and interpretability analysis, to dynamic diagnosis feedback. This study aims to address deficiencies in the current TCM diagnosis and treatment model during the “pre-disease to disease” window period and to provide an operational framework for the clinical practice of TCM’s “treating disease before its onset”.
{"title":"Construction of the clinical diagnosis and treatment model during the “pre-disease to disease” window period in traditional Chinese medicine: integration of objective multimodal data from the perspective of traditional Chinese medicine stateology","authors":"Li Danyang , Ai Min , Zhou Pai , Deng Ying , Yang Chaoyang , Peng Qinghua","doi":"10.1016/j.dcmed.2026.05.002","DOIUrl":"10.1016/j.dcmed.2026.05.002","url":null,"abstract":"<div><div>The philosophy of “treating disease before its onset” is a fundamental concept of traditional Chinese medicine (TCM), permeating its diagnostic and therapeutic framework, and is central to clinical practice. However, current TCM diagnostic and treatment models for the “pre-disease to disease” window period face several limitations, including the lack of comprehensive clinical parameters, difficulties in characterizing and integrating heterogeneous multimodal data, and insufficient dynamic precision in interventions and efficacy evaluations. To address these issues, guided by Professor Candong Li’s theory of TCM stateology, this study focuses on integrating objective multimodal data. It proposes a new model for personalized TCM diagnosis and treatment targeting the “pre-disease to disease” window period. This approach first proposes the idea of restructuring the conceptual framework of “symptom” and integrating multi-source heterogeneous data at macroscopic, mesoscopic, and microscopic levels to form a three-dimensional assessment indicator system. By integrating graph neural networks, convolutional neural networks, attention mechanisms, and knowledge graph-guided weight allocation, this approach enables collaborative representation, alignment, and fusion of multi-source data. Subsequently, it plans to construct a multimodal fusion model at both feature and decision levels, in order to establish mappings between indicators and TCM state elements, and to screen key indicators characterizing pathological evolution during the window period. Furthermore, it proposes a technical path for enhancing model interpretability using methods such as SHapley Additive exPlanations (SHAP) and Ablation-CAM++. Finally, with state assessment as the core, it proposes the concept of constructing a dynamic evaluation method for individualized diagnosis and treatment based on time-series data analysis using algorithms such as long short-term memory (LSTM) networks and gated recurrent units (GRUs). Moreover, a causal inference framework and semi-supervised learning strategies are introduced to enable quantitative evaluation of individual intervention effects and to provide interpretable therapeutic feedback, forming a complete technical path from data representation and fusion, weight adjustment, and interpretability analysis, to dynamic diagnosis feedback. This study aims to address deficiencies in the current TCM diagnosis and treatment model during the “pre-disease to disease” window period and to provide an operational framework for the clinical practice of TCM’s “treating disease before its onset”.</div></div>","PeriodicalId":33578,"journal":{"name":"Digital Chinese Medicine","volume":"9 2","pages":"Pages 173-183"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148214622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：