{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:46:21Z","timestamp":1787024781623,"version":"build-2736575974"},"reference-count":45,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Human adenoviruses (HAdVs) and COVID-19 are prominent respiratory pathogens with overlapping clinical presentations, including fever, cough, and sore throat, posing significant diagnostic challenges without viral testing. Tongue image diagnosis, a noninvasive method used in traditional Chinese medicine, has shown correlations with specific respiratory infections, but its application remains underexplored in differentiating HAdVs from COVID-19. Advances in artificial intelligence offer opportunities to enhance tongue image analysis for more objective and accurate diagnostics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to develop and validate artificial intelligence\u2013based predictive models using tongue image features to differentiate COVID-19 from adenoviral respiratory infections, thereby improving diagnostic accuracy and integrating traditional diagnostic methods with modern medical technologies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 280 tongue images were collected from 58 patients with COVID-19, 84 patients with HAdVs, and 30 healthy controls. Deep learning methods were applied to extract tongue features, including color, coating, fissures, papillae, tooth marks, and granules. Four machine learning classifiers, logistic regression, random forest, gradient boosting model, and extreme gradient boosting, were developed to differentiate COVID-19 and HAdV infections. The key features identified by the machine learning algorithms were further visualized in a 2D space.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Nine tongue features showed significant differences among groups (all\n                      <jats:italic>P<\/jats:italic>\n                      &lt;.05), including coating color (red, green, and blue), presence of tooth marks, coating crack ratio, moisture level, texture directionality, roughness, and contrast. The extreme gradient boosting model achieved the highest diagnostic performance with an area under the receiver operating characteristic curve of 0.84 (95% CI 0.78-0.90) and an area under the precision-recall curve above 0.70. Shapley additive explanations analysis indicated tongue color, moisture, and texture as key contributors.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our findings demonstrate the potential of tongue diagnosis in identifying pathogens responsible for acute respiratory tract infections at the time of admission. This approach holds significant clinical implications, offering the potential to reduce clinician workloads while improving diagnostic accuracy and the overall quality of medical care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/74102","type":"journal-article","created":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T15:30:07Z","timestamp":1750779007000},"page":"e74102-e74102","source":"Crossref","is-referenced-by-count":4,"title":["Tongue Image\u2013Based Diagnosis of Acute Respiratory Tract Infection Using Machine Learning: Algorithm Development and Validation"],"prefix":"10.2196","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8688-6628","authenticated-orcid":false,"given":"Qianzi","family":"Che","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8098-1245","authenticated-orcid":false,"given":"Yuanming","family":"Leng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6371-1406","authenticated-orcid":false,"given":"Wei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3187-2621","authenticated-orcid":false,"given":"Xihao","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7139-077X","authenticated-orcid":false,"given":"Zhongxia","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6554-2041","authenticated-orcid":false,"given":"Lizheng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9170-4430","authenticated-orcid":false,"given":"Feibiao","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7129-016X","authenticated-orcid":false,"given":"Ruilin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,8,25]]},"reference":[{"issue":"4","key":"R1","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1055\/s-0031-1283287","article-title":"Adenovirus","volume":"32","author":"Lynch","journal-title":"Semin Respir Crit Care Med"},{"issue":"2","key":"R2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pntd.0011151","article-title":"Prevalence of human infection with respiratory adenovirus in China: a systematic review and meta-analysis","volume":"17","author":"Liu","journal-title":"PLoS Negl Trop Dis"},{"key":"R3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijid.2024.107052","article-title":"Global analysis of respiratory viral circulation and timing of epidemics in the pre-COVID-19 and COVID-19 pandemic eras, based on data from the Global Influenza Surveillance and Response System (GISRS)","volume":"144","author":"Del Riccio","journal-title":"Int J Infect Dis"},{"issue":"3","key":"R4","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s41579-022-00807-9","article-title":"The effects of the COVID-19 pandemic on community respiratory virus activity","volume":"21","author":"Chow","journal-title":"Nat Rev Microbiol"},{"issue":"19","key":"R5","doi-asserted-by":"publisher","DOI":"10.3346\/jkms.2024.39.e171","article-title":"Epidemiology of respiratory viruses in Korean children before and after the COVID-19 pandemic: a prospective study from national surveillance system","volume":"39","author":"Cho","journal-title":"J Korean Med Sci"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.3389\/fmicb.2021.629971","article-title":"The epidemiology, molecular, and clinical of human adenoviruses in children hospitalized with acute respiratory infections","volume":"12","author":"Wen","journal-title":"Front Microbiol"},{"issue":"4","key":"R7","doi-asserted-by":"publisher","DOI":"10.3390\/pathogens13040316","article-title":"Respiratory viral coinfections: insights into epidemiology, immune response, pathology, and clinical outcomes","volume":"13","author":"Babawale","journal-title":"Pathogens"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.1016\/j.phrs.2020.105187","article-title":"Current policies and measures on the development of traditional Chinese medicine in China","volume":"163","author":"Wang","journal-title":"Pharmacol Res"},{"issue":"4","key":"R9","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1111\/jebm.12460","article-title":"Diagnosis and treatment guideline for Chinese medicine on acute trachea\u2010bronchitis","volume":"14","author":"Li","journal-title":"J Evidence Based Medicine"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","DOI":"10.1111\/dth.14578","article-title":"Oral manifestations of COVID-19 disease: A review article","volume":"34","author":"Iranmanesh","journal-title":"Dermatol Ther"},{"issue":"6","key":"R11","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1542\/hpeds.2020-0123","article-title":"COVID-19 and Kawasaki Disease: Novel Virus and Novel Case","volume":"10","author":"Jones","journal-title":"Hosp Pediatr"},{"issue":"3","key":"R12","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1093\/jpids\/piaa069","article-title":"Multisystem Inflammatory Syndrome in Children During the Coronavirus 2019 Pandemic: A Case Series","volume":"9","author":"Chiotos","journal-title":"J Pediatric Infect Dis Soc"},{"issue":"262","key":"R13","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1016\/j.ajem.2020.08.018","article-title":"Melkersson-Rosenthal Syndrome Induced by COVID-19","volume":"41","author":"Ta\u015fl\u0131dere","journal-title":"Am J Emerg Med"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2021.104429","article-title":"Establishment of noninvasive diabetes risk prediction model based on tongue features and machine learning techniques","volume":"149","author":"Li","journal-title":"Int J Med Inform"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104622","article-title":"Application of computer tongue image analysis technology in the diagnosis of NAFLD","volume":"135","author":"Jiang","journal-title":"Comput Biol Med"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2023.1154294","article-title":"A lung cancer risk warning model based on tongue images","volume":"14","author":"Shi","journal-title":"Front Physiol"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2023.101834","article-title":"Development of a tongue image-based machine learning tool for the diagnosis of gastric cancer: a prospective multicentre clinical cohort study","volume":"57","author":"Yuan","journal-title":"EClinicalMedicine"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.08.038","article-title":"An automatic multi-view disease detection system via Collective Deep Region-based Feature Representation","volume":"115","author":"Zhou","journal-title":"Future Gener Comput Syst"},{"issue":"6","key":"R19","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12061503","article-title":"COVID-19 diagnosis: a comprehensive review of the RT-qPCR method for detection of SARS-CoV-2","volume":"12","author":"Dutta","journal-title":"Diagnostics (Basel)"},{"issue":"6","key":"R20","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1111\/tid.12022","article-title":"European guidelines for diagnosis and treatment of adenovirus infection in leukemia and stem cell transplantation: summary of ECIL-4 (2011)","volume":"14","author":"Matthes-Martin","journal-title":"Transpl Infect Dis"},{"key":"R21","unstructured":"Bochkovskiy A Wang CY Liao HYM . Yolov4: optimal speed and accuracy of object detection. arXiv. Preprint posted online on Apr 23, 2020. arXiv:200410934"},{"key":"R22","unstructured":"O\u2019Shea K . An introduction to convolutional neural networks. arXiv. Preprint posted online on Dec 2, 2015. [doi: 10.48550\/arXiv.1511.08458]"},{"issue":"4","key":"R23","doi-asserted-by":"publisher","first-page":"862","DOI":"10.1007\/s10278-021-00478-7","article-title":"A comprehensive study of data augmentation strategies for prostate cancer detection in diffusion-weighted MRI using convolutional neural networks","volume":"34","author":"Hao","journal-title":"J Digit Imaging"},{"issue":"6","key":"R24","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1109\/TSMC.1978.4309999","article-title":"Textural features corresponding to visual perception","volume":"8","author":"Tamura","journal-title":"IEEE Trans Syst, Man, Cybern"},{"issue":"10","key":"R25","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.1016\/j.jclinepi.2006.01.014","article-title":"Review: a gentle introduction to imputation of missing values","volume":"59","author":"Donders","journal-title":"J Clin Epidemiol"},{"key":"R26","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez A Garc\u00eda S Galar M Prati RC Krawczyk B Herrera F . Learning from Imbalanced Data. Springer; 2018.","DOI":"10.1007\/978-3-319-98074-4"},{"key":"R27","doi-asserted-by":"crossref","unstructured":"Marcilio WE Eler DM , editors. From explanations to feature selection: assessing SHAP values as feature selection mechanism. Presented at: 2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI); Nov 7-10, 2020; Porto de Galinhas, Brazil.","DOI":"10.1109\/SIBGRAPI51738.2020.00053"},{"issue":"1","key":"R28","doi-asserted-by":"publisher","first-page":"3221","DOI":"10.5555\/2627435.2697068","article-title":"Accelerating t-SNE using tree-based algorithms","volume":"15","author":"Van Der Maaten","journal-title":"J Mach Learn Res"},{"issue":"1","key":"R29","doi-asserted-by":"publisher","DOI":"10.1002\/rmv.2365","article-title":"Respiratory viral co-infections in patients with COVID-19 and associated outcomes: a systematic review and meta-analysis","volume":"33","author":"Krumbein","journal-title":"Rev Med Virol"},{"key":"R30","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101951","article-title":"Grouping attributes zero-shot learning for tongue constitution recognition","volume":"109","author":"Wen","journal-title":"Artif Intell Med"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103693","article-title":"A tongue features fusion approach to predicting prediabetes and diabetes with machine learning","volume":"115","author":"Li","journal-title":"J Biomed Inform"},{"key":"R32","volume":"2016","author":"Mai","journal-title":"AMIA Annu Symp Proc"},{"issue":"4","key":"R33","doi-asserted-by":"publisher","first-page":"772","DOI":"10.1016\/j.jmii.2023.04.011","article-title":"Clinical characteristics of hospitalized children with community-acquired pneumonia and respiratory infections: using machine learning approaches to support pathogen prediction at admission","volume":"56","author":"Chang","journal-title":"J Microbiol Immunol Infect"},{"issue":"1","key":"R34","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.imr.2018.03.001","article-title":"Advances in automated tongue diagnosis techniques","volume":"8","author":"Tania","journal-title":"Integr Med Res"},{"issue":"9","key":"R35","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/JBHI.2020.2986376","article-title":"Multi-task joint learning model for segmenting and classifying tongue images using a deep neural network","volume":"24","author":"Xu","journal-title":"IEEE J Biomed Health Inform"},{"key":"R36","doi-asserted-by":"publisher","DOI":"10.1155\/2017\/7452427","article-title":"Tongue images classification based on constrained high dispersal network","volume":"2017","author":"Meng","journal-title":"Evid Based Complement Alternat Med"},{"issue":"6","key":"R37","doi-asserted-by":"publisher","first-page":"3237","DOI":"10.1097\/JS9.0000000000001241","article-title":"Multimodal learning system integrating electronic medical records and hysteroscopic images for reproductive outcome prediction and risk stratification of endometrial injury: a multicenter diagnostic study","volume":"110","author":"Li","journal-title":"Int J Surg"},{"key":"R38","doi-asserted-by":"publisher","DOI":"10.1590\/pboci.2021.109","article-title":"Analysis of tongue color-associated features among patients with PCR-confirmed COVID-19 infection in Ukraine","volume":"21","author":"Horzov","journal-title":"Pesqui Bras Odontopediatria Cl\u00edn Integr"},{"issue":"6","key":"R39","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.19852\/j.cnki.jtcm.20220922.004","article-title":"Tongue and pulse features of 668 asymptomatic patients infected with the severe acute respiratory syndrome coronavirus 2 omicron variant in Shanghai","volume":"42","author":"Wen","journal-title":"J Tradit Chin Med"},{"issue":"4","key":"R40","doi-asserted-by":"publisher","DOI":"10.47690\/JCV.2021.1403","article-title":"Diagnosis and management of TCM on infected or suspected patients with Covid-19-48 cases study in UK","volume":"01","author":"D","journal-title":"JCV"},{"issue":"3","key":"R41","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.3001143","article-title":"Single-cell longitudinal analysis of SARS-CoV-2 infection in human airway epithelium identifies target cells, alterations in gene expression, and cell state changes","volume":"19","author":"Ravindra","journal-title":"PLoS Biol"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2022.870216","article-title":"Therapy targets SARS-CoV-2 infection-induced cell death","volume":"13","author":"Zhu","journal-title":"Front Immunol"},{"key":"R43","doi-asserted-by":"crossref","unstructured":"Wang ZC Cai XH Chan J . Tongue coating in COVID-19 patients: a case-control study. medRxiv. Preprint posted online on Apr 15, 2024. [doi: 10.1101\/2022.03.14.22272342]","DOI":"10.1101\/2022.03.14.22272342"},{"issue":"12","key":"R44","doi-asserted-by":"publisher","first-page":"942","DOI":"10.1007\/s11655-012-1298-y","article-title":"Study on the correlation of tongue manifestation with fibrinogen and neutrophil in acute cerebral infarction patients","volume":"18","author":"Gao","journal-title":"Chin J Integr Med"},{"issue":"7","key":"R45","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/s11655-011-0784-1","article-title":"Research on the relationship between thick greasy tongue fur formation and vascular endothelial cell permeability with the protein expression of zonula occludens-1","volume":"17","author":"Qi","journal-title":"Chin J Integr Med"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e74102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:05:06Z","timestamp":1782842706000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2025\/1\/e74102"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":45,"URL":"https:\/\/doi.org\/10.2196\/74102","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,25]]},"article-number":"v13i4e74102"}}