{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T08:32:50Z","timestamp":1793781170055,"version":"4.6.1"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Background and objective<\/jats:title>\n                    <jats:p>Coronary artery disease (CAD) is a major threat to human health, and early non-invasive identification is crucial for its prevention and management. However, current diagnostic methods still face limitations in terms of non-invasiveness, cost, and accessibility. Tongue and facial features have been recognized as closely associated with CAD. To address these challenges, this study proposes a dual-modal diagnostic model incorporating a feature-wise gating mechanism to enable intelligent, non-invasive CAD detection based on tongue and facial images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 936 participants were enrolled in this study, and standardized tongue and facial images were collected from each subject. Image segmentation was performed using MedSAM, followed by deep semantic feature extraction using the MDFA-Swin network. Traditional color and texture features were also incorporated. A feature-guided gating mechanism was developed to enable personalized multimodal fusion of tongue and facial features. The diagnostic performance of the proposed model was evaluated on an independent external test set. In addition, SHAP (SHapley Additive Explanations) analysis were conducted to enhance model interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed CAD diagnostic model based on fused multidimensional tongue and facial features (TF_FGC) demonstrated excellent performance in internal validation (AUC\u202f=\u202f0.945, Accuracy\u202f=\u202f0.872) and maintained good generalizability on the external test set (AUC\u202f=\u202f0.896, Accuracy\u202f=\u202f0.825). The SHAP analysis identified T_contrast, T_RGB_R, T_homogeneity, F_homogeneity, F_RGB_B, F_RGB_G, F_RGB_R, and F_contrast as the most influential features driving model predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed dual-branch fusion model demonstrates high diagnostic accuracy, strong interpretability, and good generalizability. By integrating traditional color and texture features with deep semantic representations, this approach offers a promising solution for non-invasive and intelligent screening of CAD, providing a novel perspective and practical support for clinical decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1662577","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T06:26:25Z","timestamp":1763360785000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["An explainable dual-modal diagnostic model for coronary artery disease: a feature-gated approach using tongue and facial image features"],"prefix":"10.3389","volume":"8","author":[{"given":"Mei","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manrui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linmiao","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongsheng","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1504281","DOI":"10.3389\/frai.2025.1504281","article-title":"Transfer learning-based hybrid VGG16-machine learning approach for heart disease detection with explainable artificial intelligence","volume":"8","author":"Addisu","year":"2025","journal-title":"Front Artif Intell"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e23354","DOI":"10.1016\/j.heliyon.2023.e23354","article-title":"Deep learning of heart-sound signals for efficient prediction of obstructive coronary artery disease","volume":"10","author":"Ainiwaer","year":"2024","journal-title":"Heliyon"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1080\/01621459.2017.1401542","article-title":"Principal component analysis of high-frequency data","volume":"114","author":"A\u00eft-Sahalia","year":"2019","journal-title":"J. Am. Stat. Assoc."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"2886","DOI":"10.1016\/j.jacc.2014.02.606","article-title":"2013 ACC\/AHA guideline on the assessment of cardiovascular risk","volume":"63","author":"Andrus","year":"2014","journal-title":"J. Am. Coll. Cardiol."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/0030-4220(94)90290-9","article-title":"Arterial supply to the floor of the mouth and lingual gingiva","volume":"77","author":"Bavitz","year":"1994","journal-title":"Oral Surg. Oral Med. Oral Pathol."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e146","DOI":"10.1161\/CIR.0000000000000485","article-title":"Heart disease and stroke statistics-2017 update: a report from the American Heart Association","volume":"135","author":"Benjamin","year":"2017","journal-title":"Circulation"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"e67","DOI":"10.1161\/CIR.0000000000000558","article-title":"Heart disease and stroke statistics-2018 update: a report from the American Heart Association","volume":"137","author":"Benjamin","year":"2018","journal-title":"Circulation"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1161\/CIRCULATIONAHA.113.001696","article-title":"Visible age-related signs and risk of ischemic heart disease in the general population: a prospective cohort study","volume":"129","author":"Christoffersen","year":"2014","journal-title":"Circulation"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.arr.2015.11.002","article-title":"Visible aging signs as risk markers for ischemic heart disease: epidemiology, pathogenesis and clinical implications","volume":"25","author":"Christoffersen","year":"2016","journal-title":"Ageing Res. Rev."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"e007217","DOI":"10.1161\/CIRCIMAGING.117.007217","article-title":"Diagnostic accuracy of a machine-learning approach to coronary computed tomographic angiography-based fractional flow reserve: result from the MACHINE consortium","volume":"11","author":"Coenen","year":"2018","journal-title":"Circ. Cardiovasc. Imaging"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1161\/CIRCULATIONAHA.107.699579","article-title":"General cardiovascular risk profile for use in primary care: the Framingham heart study","volume":"117","author":"D\u2019Agostino","year":"2008","journal-title":"Circulation"},{"key":"ref12","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1384977","DOI":"10.3389\/fcvm.2024.1384977","article-title":"Feasibility of tongue image detection for coronary artery disease: based on deep learning","volume":"11","author":"Duan","year":"","journal-title":"Front. Cardiovas. Med."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"441","DOI":"10.3233\/THC-230590","article-title":"Machine learning aided non-invasive diagnosis of coronary heart disease based on tongue features fusion","volume":"32","author":"Duan","year":"","journal-title":"Technol. Health Care"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/s13246-018-0635-x","article-title":"Glossokinetic potential based tongue\u2013machine interface for 1-D extraction","volume":"41","author":"Gorur","year":"2018","journal-title":"Australas. Phys. Eng. Sci. Med."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"319","DOI":"10.18280\/ts.360404","article-title":"GKP signal processing using deep CNN and SVM for tongue-machine interface","volume":"36","author":"Gorur","year":"2019","journal-title":"Traitement Signal."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"910","DOI":"10.2176\/nmc.52.910","article-title":"Endovascular revascularization of external carotid artery occlusion causing tongue infarction: case report","volume":"52","author":"Kagami","year":"2012","journal-title":"Neurol. Med. Chir. (Tokyo)"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"796","DOI":"10.3390\/bioengineering10070796","article-title":"Detection of cardiovascular disease from clinical parameters using a one-dimensional convolutional neural network","volume":"10","author":"Khan Mamun","year":"2023","journal-title":"Bioengineering"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1007\/s10489-020-01859-1","article-title":"End-to-end CNN+ LSTM deep learning approach for bearing fault diagnosis","volume":"51","author":"Khorram","year":"2021","journal-title":"Appl. Intell."},{"key":"ref20","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1093\/eurheartj\/ehz425","article-title":"2019 ESC guidelines for the diagnosis and management of chronic coronary syndromes: the task force for the diagnosis and management of chronic coronary syndromes of the European Society of Cardiology (ESC)","volume":"41","author":"Knuuti","year":"2020","journal-title":"Eur. Heart J."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1016\/j.jacc.2019.02.060","article-title":"Prognostic implications of plaque characteristics and stenosis severity in patients with coronary artery disease","volume":"73","author":"Lee","year":"2019","journal-title":"J. Am. Coll. Cardiol."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1436278","DOI":"10.3389\/fcvm.2024.1436278","article-title":"Tongue color parameters in predicting the degree of coronary stenosis: a retrospective cohort study of 282 patients with coronary angiography","volume":"11","author":"Li","year":"2024","journal-title":"Front. Cardiovasc. Med."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"702110","DOI":"10.3389\/fcvm.2021.702110","article-title":"Traditional Chinese medicine for coronary artery disease treatment: clinical evidence from randomized controlled trials","volume":"8","author":"Liang","year":"2021","journal-title":"Front. Cardiovasc. Med."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"4400","DOI":"10.1093\/eurheartj\/ehaa640","article-title":"Feasibility of using deep learning to detect coronary artery disease based on facial photo","volume":"41","author":"Lin","year":"2020","journal-title":"Eur. Heart J."},{"key":"ref25","author":"Lin","year":"2020"},{"key":"ref26","author":"Liu","year":"2021"},{"key":"ref27","first-page":"736","article-title":"A unified approach to interpreting model predictions","volume-title":"Advances in neural information processing systems","author":"Lundberg","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat. Commun."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"107952","DOI":"10.1016\/j.compbiomed.2024.107952","article-title":"Predicting coronary heart disease in Chinese diabetics using machine learning","volume":"169","author":"Ma","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"102918","DOI":"10.1016\/j.media.2023.102918","article-title":"Segment anything model for medical image analysis: an experimental study","volume":"89","author":"Mazurowski","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"e0318542","DOI":"10.1371\/journal.pone.0318542","article-title":"Advancing malware imagery classification with explainable deep learning: a state-of-the-art approach using SHAP, LIME and grad-CAM","volume":"20","author":"Nazim","year":"2025","journal-title":"PLoS One"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1080\/14786440109462720","article-title":"LIII. On lines and planes of closest fit to systems of points in space","volume":"2","author":"Pearson","year":"1901","journal-title":"Lond. Edinb. Dubl. Philos. Mag. J. Sci."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1089\/acm.2020.0008","article-title":"A quantitative diagnostic method for phlegm and blood stasis syndrome in coronary heart disease using tongue, face, and pulse indexes: an exploratory pilot study","volume":"26","author":"Ren","year":"2020","journal-title":"J. Altern. Complement. Med."},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1063\/5.0180182","article-title":"Development of coronary heart disease diagnosis system based on facial imagery","author":"Rismawan","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1093\/bib\/bbae479","article-title":"AESurv: autoencoder survival analysis for accurate early prediction of coronary heart disease","volume":"25","author":"Shen","year":"2024","journal-title":"Brief. Bioinform."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"987","DOI":"10.3390\/cancers16050987","article-title":"Classification of Mobile-based Oral Cancer images using the vision transformer and the Swin transformer","volume":"16","author":"Song","year":"2024","journal-title":"Cancers (Basel)"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1682","DOI":"10.1097\/HJH.0000000000002075","article-title":"Coronary heart disease diagnosis by artificial neural networks including aortic pulse wave velocity index and clinical parameters","volume":"37","author":"Vall\u00e9e","year":"2019","journal-title":"J. Hypertens."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"5899975","DOI":"10.1155\/2022\/5899975","article-title":"Deep learning based tongue prickles detection in traditional Chinese medicine","volume":"2022","author":"Wang","year":"2022","journal-title":"Evid. Based Complement. Alternat. Med."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"1837","DOI":"10.1161\/01.CIR.97.18.1837","article-title":"Prediction of coronary heart disease using risk factor categories","volume":"97","author":"Wilson","year":"1998","journal-title":"Circulation"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"101097","DOI":"10.1016\/j.jocmr.2024.101097","article-title":"Image navigator-based, automated coronary magnetic resonance angiography for the detection of coronary artery stenosis","volume":"26","author":"Wood","year":"2024","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref41","first-page":"616","article-title":"Cluster analysis on TCM syndromes in 319 coronary artery disease patients for establishment of syndrome diagnostic figure","volume":"27","author":"Wu","year":"2007","journal-title":"Zhongguo Zhong Xi Yi Jie He Za Zhi"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1016\/j.imed.2022.09.002","article-title":"Tongue diagnosis based on hue-saturation value color space: controlled study of tongue appearance in patients treated with percutaneous coronary intervention for coronary heart disease","volume":"3","author":"Xia","year":"2023","journal-title":"Intellig. Med."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1515\/mr-2021-0018","article-title":"Digital tongue image analyses for health assessment","volume":"1","author":"Xie","year":"2021","journal-title":"Med. Rev."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s13020-025-01059-4","article-title":"Construction of machine learning-based models for screening the high-risk patients with gastric precancerous lesions","volume":"20","author":"Yu","year":"2025","journal-title":"Chin. Med."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"108238","DOI":"10.1016\/j.compbiomed.2024.108238","article-title":"Segment anything model for medical image segmentation: current applications and future directions","volume":"171","author":"Zhang","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"1592593","DOI":"10.3389\/fphys.2025.1592593","article-title":"A non-invasive prediction model for coronary artery stenosis severity based on multimodal data","volume":"16","author":"Zhang","year":"2025","journal-title":"Front. Physiol."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1662577\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T06:26:27Z","timestamp":1763360787000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1662577\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"references-count":46,"alternative-id":["10.3389\/frai.2025.1662577"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1662577","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,17]]},"article-number":"1662577"}}