{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T04:55:57Z","timestamp":1790916957460,"version":"4.1.0"},"reference-count":55,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82470352"],"award-info":[{"award-number":["82470352"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["advanced.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Advanced Science"],"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    While most biomarkers currently rely on invasive laboratory testing, which limits large\u2010scale or repeated screening, scalable non\u2010invasive methods could transform population screening and personalized health management. Facial photographs, as a ubiquitous and non\u2010invasive data source, offer such potential but remain underexplored for clinical biomarker prediction. Existing supervised approaches are constrained by the availability of clinically labeled data, whereas general\u2010purpose vision models are optimized for non\u2010clinical tasks and may inadequately capture subtle, multiscale, and spatially distributed clinical facial features. To address these limitations, we developed MedicalFaceFound, a facial foundation model pretrained on over 10 million images and evaluated across 62 biomarkers spanning eight physiological systems. It performed best among the Swin\u2010Large and ResNet18 for 45 (73%) biomarkers and generalized across four independent external cohorts (median Pearson's\n                    <jats:italic>r<\/jats:italic>\n                    \u00a0=\u00a00.172), with strong performance for RBC, eGFR, and HDL\u2010C (median\n                    <jats:italic>r<\/jats:italic>\n                    \u00a0=\u00a00.478, 0.442, and 0.430, respectively). MedicalFaceFound also outperformed polygenic risk score models for 14 of 26 biomarkers, and face\u2010estimated cardiovascular biomarkers were strongly associated with coronary stenosis (AUC\u00a0=\u00a00.66). The model retained predictive performance with 400 labeled samples and was feasible to deploy as a smartphone application, supporting scalable, non\u2010invasive biomarker assessment and personalized risk screening.\n                  <\/jats:p>","DOI":"10.1002\/advs.77861","type":"journal-article","created":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T04:36:33Z","timestamp":1790915793000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Facial Foundation Model for Clinical Biomarker Prediction and Real\u2010World Mobile Deployment"],"prefix":"10.1002","author":[{"given":"Tingfeng","family":"Xu","sequence":"first","affiliation":[{"name":"China National Center for Bioinformation  Beijing China"},{"name":"Beijing Institute of Genomics Chinese Academy of Sciences  Beijing China"},{"name":"University of Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1224-3080","authenticated-orcid":false,"given":"Huixuan","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences  Beijing China"},{"name":"Institute of Computing Technology Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Lin","sequence":"additional","affiliation":[{"name":"Beijing Anzhen Hospital Capital Medical University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[{"name":"China National Center for Bioinformation  Beijing China"},{"name":"Beijing Institute of Genomics Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5388-2321","authenticated-orcid":false,"given":"Yaodong","family":"Ding","sequence":"additional","affiliation":[{"name":"Beijing Anzhen Hospital Capital Medical University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangqiao","family":"Liao","sequence":"additional","affiliation":[{"name":"China National Center for Bioinformation  Beijing China"},{"name":"Beijing Institute of Genomics Chinese Academy of Sciences  Beijing China"},{"name":"University of Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyu","family":"Chen","sequence":"additional","affiliation":[{"name":"China National Center for Bioinformation  Beijing China"},{"name":"Beijing Institute of Genomics Chinese Academy of Sciences  Beijing China"},{"name":"University of Chinese Academy of Sciences  Beijing China"},{"name":"Cardiovascular Disease Initiative Broad Institute of MIT and Harvard  Cambridge MA USA"},{"name":"Department of Cardiology Beijing Daxing Hospital  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jichen","family":"Wen","sequence":"additional","affiliation":[{"name":"China National Center for Bioinformation  Beijing China"},{"name":"Beijing Institute of Genomics Chinese Academy of Sciences  Beijing China"},{"name":"University of Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongqiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"China National Center for Bioinformation  Beijing China"},{"name":"Beijing Institute of Genomics Chinese Academy of Sciences  Beijing China"},{"name":"University of Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Hao","sequence":"additional","affiliation":[{"name":"China National Center for Bioinformation  Beijing China"},{"name":"Beijing Institute of Genomics Chinese Academy of Sciences  Beijing China"},{"name":"University of Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weixiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"China National Center for Bioinformation  Beijing China"},{"name":"Beijing Institute of Genomics Chinese Academy of Sciences  Beijing China"},{"name":"University of Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cardiovascular Research Center Massachusetts General Hospital  Boston MA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences  Beijing China"},{"name":"Institute of Computing Technology Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6983-0799","authenticated-orcid":false,"given":"Yong","family":"Zeng","sequence":"additional","affiliation":[{"name":"Beijing Anzhen Hospital Capital Medical University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6010-1792","authenticated-orcid":false,"given":"Hu","family":"Han","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences  Beijing China"},{"name":"Institute of Computing Technology Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3753-508X","authenticated-orcid":false,"given":"Minxian","family":"Wang","sequence":"additional","affiliation":[{"name":"China National Center for Bioinformation  Beijing China"},{"name":"Beijing Institute of Genomics Chinese Academy of Sciences  Beijing China"},{"name":"University of Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1602\/neurorx.1.2.182"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev\u2010physiol\u2010020518\u2010114605"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010024\u201002905\u2010y"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41573\u2010025\u201001165\u2010w"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.copbio.2022.102738"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/adma.202309705"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589\u20107500(20)30216\u20108"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551\u2010018\u20100195\u20100"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaad.2025.06.035"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000357"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010023\u201002640\u2010w"},{"key":"e_1_2_10_13_1","doi-asserted-by":"crossref","unstructured":"K.He X.Chen S.Xie Y.Li P.Dollar andR.Girshick \u201cMasked Autoencoders Are Scalable Vision Learners \u201d in2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2022) 15979\u201315988 https:\/\/doi.org\/10.1109\/CVPR52688.2022.01553.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.18689"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551\u2010024\u201001257\u20109"},{"key":"e_1_2_10_16_1","doi-asserted-by":"crossref","unstructured":"Z.Xie Z.Zhang andY.Cao \u201cSimMIM: A Simple Framework for Masked Image Modeling \u201d in2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2022) 9643\u20139653 https:\/\/doi.org\/10.1109\/CVPR52688.2022.00943.","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010023\u201006555\u2010x"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010024\u201002856\u20104"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010024\u201002959\u2010y"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010024\u201008378\u2010w"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2026.114691"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2026.114577"},{"key":"e_1_2_10_23_1","doi-asserted-by":"crossref","unstructured":"X.Chen S.Xie andK.He \u201cAn Empirical Study of Training Self\u2010Supervised Vision Transformers \u201d in2021 IEEE\/CVF International Conference on Computer Vision (ICCV)(IEEE 2021) 9620\u20139629 https:\/\/doi.org\/10.1109\/ICCV48922.2021.00950 Montreal QC Canada 2021.","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123881"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3005687"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010018\u20100279\u20100"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41588\u2010021\u201001010\u2010x"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehaa640"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.landig.2025.03.002"},{"key":"e_1_2_10_30_1","doi-asserted-by":"crossref","unstructured":"B.Ma W.Zhang F.Qiu andY.Ding \u201cA Unified Approach to Facial Affect Analysis: The MAE\u2010Face Visual Representation \u201d in2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (IEEE 2023) 5924\u20135933 https:\/\/doi.org\/10.1109\/CVPRW59228.2023.00630.","DOI":"10.1109\/CVPRW59228.2023.00630"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.17671\/gazibtd.1399077"},{"key":"e_1_2_10_32_1","doi-asserted-by":"crossref","unstructured":"H. O.Shahreza A.George andS.Marcel \u201cFace Reconstruction From Face Embeddings Using Adapter to a Face Foundation Model \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)(2025):5584\u20135593 https:\/\/doi.org\/10.1109\/CVPRW67362.2025.00555.","DOI":"10.1109\/CVPRW67362.2025.00555"},{"key":"e_1_2_10_33_1","doi-asserted-by":"crossref","unstructured":"L.Qin M.Wang andC.Deng \u201cSwinFace: A Multi\u2010Task Transformer for Face Recognition Expression Recognition Age Estimation and Attribute Estimation \u201d inIEEE Transactions on Circuits and Systems for Video Technology(IEEE 2023) 2223\u20132234 https:\/\/doi.org\/10.1109\/TCSVT.2023.3304724.","DOI":"10.1109\/TCSVT.2023.3304724"},{"key":"e_1_2_10_34_1","doi-asserted-by":"publisher","DOI":"10.1101\/2025.04.29.25326370"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746\u2010023\u201000811\u20100"},{"key":"e_1_2_10_36_1","doi-asserted-by":"crossref","unstructured":"Z.Liu Y.Lin Y.Cao et\u00a0al. \u201cSwin Transformer: Hierarchical Vision Transformer Using Shifted Windows \u201d in2021 IEEE\/CVF International Conference on Computer Vision (ICCV)(IEEE 2021):9992\u201310002 https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_2_10_37_1","doi-asserted-by":"crossref","unstructured":"Q.Cao L.Shen W.Xie O. M.Parkhi andA.Zisserman \u201cVGGFace2: A Dataset for Recognising Faces Across Pose and Age \u201d in2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018)(IEEE 2018):67\u201374 https:\/\/doi.org\/10.48550\/arXiv.1710.08092.","DOI":"10.1109\/FG.2018.00020"},{"key":"e_1_2_10_38_1","doi-asserted-by":"crossref","unstructured":"J.Deng W.Dong R.Socher L.\u2010J.Li K.Li andL.Fei\u2010Fei \u201cImageNet: A Large\u2010Scale Hierarchical Image Database \u201d in2009 IEEE Conference on Computer Vision and Pattern Recognition(IEEE 2009) 248\u2013255 https:\/\/doi.org\/10.1109\/CVPR.2009.5206848.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3307156"},{"key":"e_1_2_10_40_1","doi-asserted-by":"crossref","unstructured":"K.He X.Zhang S.Ren andJ.Sun \u201cDeep Residual Learning for Image Recognition \u201d inProceedings of the IEEE conference on computer vision and pattern recognition(IEEE 2016):770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41588\u2010024\u201001937\u2010x"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1214\/10\u2010STS330"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10654\u2010021\u201000794\u2010w"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.adj1182"},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41588\u2010022\u201001038\u20107"},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehaf297"},{"key":"e_1_2_10_47_1","unstructured":"C.Cui T.Sun M.Lin et\u00a0al. \u201cPaddleOCR 3.0 Technical Report \u201darXiv(2025) https:\/\/doi.org\/10.48550\/arXiv.2507.05595."},{"key":"e_1_2_10_48_1","doi-asserted-by":"crossref","unstructured":"T.Hempel A. A.Abdelrahman andA.Al\u2010Hamadi \u201cTowards Robust and Unconstrained Full Range of Rotation Head Pose Estimation \u201dIEEE Transactions on Image Processing33(2024):2377\u20132387 https:\/\/doi.org\/10.48550\/arXiv.2309.07654 arXiv:2309.07654.","DOI":"10.1109\/TIP.2024.3378180"},{"key":"e_1_2_10_49_1","doi-asserted-by":"crossref","unstructured":"S. I.SerengilandA.Ozpinar \u201cLightFace: A Hybrid Deep Face Recognition Framework \u201d in2020 Innovations in Intelligent Systems and Applications Conference (ASYU)(IEEE 2020) 1\u20135 https:\/\/doi.org\/10.1109\/ASYU50717.2020.9259802.","DOI":"10.1109\/ASYU50717.2020.9259802"},{"key":"e_1_2_10_50_1","unstructured":"X.Li W.Wang L.Yang andJ.Yang \u201cUniform Masking: Enabling MAE Pre\u2010Training for Pyramid\u2010Based Vision Transformers With Locality \u201darXiv(2022) https:\/\/doi.org\/10.48550\/arXiv.2205.10063."},{"key":"e_1_2_10_51_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1711.05101"},{"key":"e_1_2_10_52_1","unstructured":"X.Li Y.Grandvalet andF.Davoine \u201cExplicit Inductive Bias for Transfer Learning With Convolutional Networks \u201d inProceedings of the 35th International Conference on Machine Learning (PMLR 2018):2825\u20132834."},{"key":"e_1_2_10_53_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13742\u2010015\u20100047\u20108"},{"key":"e_1_2_10_54_1","doi-asserted-by":"publisher","DOI":"10.1038\/ng.3656"},{"key":"e_1_2_10_55_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v017.i01"},{"key":"e_1_2_10_56_1","unstructured":"C.Jin Z.Guo Y.Lin L.Luo andH.Chen \u201cLabel\u2010Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions \u201darXiv(2025) https:\/\/doi.org\/10.48550\/arXiv.2303.12484."}],"container-title":["Advanced Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/advs.77861","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/advs.77861","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/advs.77861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T04:36:38Z","timestamp":1790915798000},"score":1,"resource":{"primary":{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/10.1002\/advs.77861"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":55,"alternative-id":["10.1002\/advs.77861"],"URL":"https:\/\/doi.org\/10.1002\/advs.77861","archive":["Portico"],"relation":{},"ISSN":["2198-3844","2198-3844"],"issn-type":[{"value":"2198-3844","type":"print"},{"value":"2198-3844","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]},"assertion":[{"value":"2026-06-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e77861"}}