EUVIMEDOpdag EUVIMED
ValidierungsstudieOpen access

Tongue Image–Based Diagnosis of Acute Respiratory Tract Infection Using Machine Learning: Algorithm Development and Validation

Qianzi Che iD, Yuanming Leng iD, Wei Yang iD, Xihao Cao iD, Zhongxia Wang iD, Lizheng Liu iD, Feibiao Xie iD, Ruilin Wang iD

JMIR Medical Informatics · 2025

DOI: 10.2196/74102 ↗

At a glance

Validierungsstudie in JMIR Medical Informatics, 2025. Written by Qianzi Che and 7 co-authors. Institution: Institute of Clinical Basic Medicine of Chinese Medicine, Chinese Academy of Traditional Chinese Medicine, No.16, Nanxiao street, Dongzhimen, Dongche…. Major MEDLINE topics: COVID-19, Tongue, Machine Learning, Respiratory Tract Infections. 45 references. The full text is freely available in PubMed Central.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

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.

Objective

This study aims to develop and validate artificial intelligence–based 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.

Methods

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.

Results

Nine tongue features showed significant differences among groups (all P

Subjects

MeSH terms (MEDLINE)

COVID-19TongueMachine LearningRespiratory Tract InfectionsAdenovirus Infections, HumanHumansMaleFemaleAlgorithmsMiddle AgedSARS-CoV-2AdultDiagnosis, DifferentialAged

Author keywords

COVID-19human adenovirusesimage feature extractionmachine learningtongue diagnosistraditional Chinese medicine

Authors and institutions

  • Institute of Clinical Basic Medicine of Chinese Medicine, Chinese Academy of Traditional Chinese Medicine, No.16, Nanxiao street, Dongzhimen, Dongcheng District, Beijing, 100700, China.
  • Department of Biostatistics, School of Public Health, Boston University, Boston, MA, United States.
  • Department of Mathematics and Statistics, Boston University, Boston, MA, United States.
  • Department of Traditional Chinese Medicine for Liver Diseases, Fifth Medical Center of the Chinese People's Liberation Army General Hospital, No. 100 West Fourth Ring Middle Road, Fengtai District, Beijing, 1000039, Chi…
  • Institute of Engineering and Applied Technology, Fudan University, Shanghai, China.
  • School of Mathematics and Statistics, Central South University, Hunan, China.

ORCID profiles: Qianzi Che, Yuanming Leng, Wei Yang, Xihao Cao, Zhongxia Wang, Lizheng Liu, Feibiao Xie, Ruilin Wang

Cite

APA

Che, Q., Leng, Y., Yang, W., Cao, X., Wang, Z., Liu, L., Xie, F., & Wang, R. (2025). Tongue Image–Based Diagnosis of Acute Respiratory Tract Infection Using Machine Learning: Algorithm Development and Validation. JMIR Medical Informatics. https://doi.org/10.2196/74102

Vancouver

Che Q, Leng Y, Yang W, Cao X, Wang Z, Liu L, et al. Tongue Image–Based Diagnosis of Acute Respiratory Tract Infection Using Machine Learning: Algorithm Development and Validation. JMIR Medical Informatics. 2025. doi:10.2196/74102

BibTeX
@article{Che2025,
  author = {Che, Qianzi and Leng, Yuanming and Yang, Wei and Cao, Xihao and Wang, Zhongxia and Liu, Lizheng and Xie, Feibiao and Wang, Ruilin},
  title = {Tongue Image–Based Diagnosis of Acute Respiratory Tract Infection Using Machine Learning: Algorithm Development and Validation},
  journal = {JMIR Medical Informatics},
  year = {2025},
  doi = {10.2196/74102}
}
Start for free →