Study on a Traditional Chinese Medicine constitution recognition model using tongue image characteristics and deep learning: a prospective dual-center investigation

Abstract Purpose The objective of this study was to develop a quantitatively analyzed Traditional Chinese Medicine (TCM) constitution recognition model utilizing tongue fusion features and deep learning techniques. Methods A prospective investigation was conducted on participants undergoing TCM cons...

Full description

Saved in:
Bibliographic Details
Main Authors: Yongyue Liu, Linmiao Fan, Mei Zhao, Dongshen Wei, Menglan Zhao, Yihang Dong, Xiaoqing Zhang
Format: Article
Language:English
Published: BMC 2025-06-01
Series:Chinese Medicine
Subjects:
Online Access:https://doi.org/10.1186/s13020-025-01126-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850221782750986240
author Yongyue Liu
Linmiao Fan
Mei Zhao
Dongshen Wei
Menglan Zhao
Yihang Dong
Xiaoqing Zhang
author_facet Yongyue Liu
Linmiao Fan
Mei Zhao
Dongshen Wei
Menglan Zhao
Yihang Dong
Xiaoqing Zhang
author_sort Yongyue Liu
collection DOAJ
description Abstract Purpose The objective of this study was to develop a quantitatively analyzed Traditional Chinese Medicine (TCM) constitution recognition model utilizing tongue fusion features and deep learning techniques. Methods A prospective investigation was conducted on participants undergoing TCM constitution assessment at two medical centers. Tongue images and corresponding TCM constitution data were collected from 1374 participants using specialized equipment. Both traditional and deep features were extracted from these images. Significant features associated with constitutional characteristics were identified through LASSO regression and Random Forest (RF). Eight machine learning algorithms were employed to construct and evaluate the efficacy of the models. The highest-performing model was selected as the foundational classifier for developing an integrated tongue image feature model. Model performance was comprehensively evaluated using accuracy, precision, recall, F1 score, and area under the curve (AUC). Results Analysis revealed 11 critical traditional tongue image features and 26 deep tongue image features. Three datasets were constructed: traditional tongue image features, deep tongue image features, and a fusion feature dataset incorporating both. The multilayer perceptron (MLP) model combining traditional and deep features demonstrated superior performance in TCM constitution classification compared to single-feature models. In the training phase, the model achieved an accuracy (ACC) of 0.893 and an AUC of 0.948. On the test set, it achieved an ACC of 0.837 and an AUC of 0.898, with sensitivity and specificity of 0.680 and 0.930, respectively, indicating excellent generalization ability. Conclusions This study successfully developed an intelligent TCM constitution recognition model that overcomes the limitations of traditional methods and validates the value of tongue images for accurate constitution recognition.
format Article
id doaj-art-d0008ef307cf45efab761f5f52ae9fb3
institution OA Journals
issn 1749-8546
language English
publishDate 2025-06-01
publisher BMC
record_format Article
series Chinese Medicine
spelling doaj-art-d0008ef307cf45efab761f5f52ae9fb32025-08-20T02:06:36ZengBMCChinese Medicine1749-85462025-06-0120112010.1186/s13020-025-01126-wStudy on a Traditional Chinese Medicine constitution recognition model using tongue image characteristics and deep learning: a prospective dual-center investigationYongyue Liu0Linmiao Fan1Mei Zhao2Dongshen Wei3Menglan Zhao4Yihang Dong5Xiaoqing Zhang6School of Life Sciences, Beijing University of Chinese MedicineSchool of Life Sciences, Beijing University of Chinese MedicineSchool of Life Sciences, Beijing University of Chinese MedicineSchool of Life Sciences, Beijing University of Chinese MedicineSchool of Life Sciences, Beijing University of Chinese MedicineSchool of Life Sciences, Beijing University of Chinese MedicineSchool of Life Sciences, Beijing University of Chinese MedicineAbstract Purpose The objective of this study was to develop a quantitatively analyzed Traditional Chinese Medicine (TCM) constitution recognition model utilizing tongue fusion features and deep learning techniques. Methods A prospective investigation was conducted on participants undergoing TCM constitution assessment at two medical centers. Tongue images and corresponding TCM constitution data were collected from 1374 participants using specialized equipment. Both traditional and deep features were extracted from these images. Significant features associated with constitutional characteristics were identified through LASSO regression and Random Forest (RF). Eight machine learning algorithms were employed to construct and evaluate the efficacy of the models. The highest-performing model was selected as the foundational classifier for developing an integrated tongue image feature model. Model performance was comprehensively evaluated using accuracy, precision, recall, F1 score, and area under the curve (AUC). Results Analysis revealed 11 critical traditional tongue image features and 26 deep tongue image features. Three datasets were constructed: traditional tongue image features, deep tongue image features, and a fusion feature dataset incorporating both. The multilayer perceptron (MLP) model combining traditional and deep features demonstrated superior performance in TCM constitution classification compared to single-feature models. In the training phase, the model achieved an accuracy (ACC) of 0.893 and an AUC of 0.948. On the test set, it achieved an ACC of 0.837 and an AUC of 0.898, with sensitivity and specificity of 0.680 and 0.930, respectively, indicating excellent generalization ability. Conclusions This study successfully developed an intelligent TCM constitution recognition model that overcomes the limitations of traditional methods and validates the value of tongue images for accurate constitution recognition.https://doi.org/10.1186/s13020-025-01126-wTCM constitutionTongue diagnosisDeep learningNeural network
spellingShingle Yongyue Liu
Linmiao Fan
Mei Zhao
Dongshen Wei
Menglan Zhao
Yihang Dong
Xiaoqing Zhang
Study on a Traditional Chinese Medicine constitution recognition model using tongue image characteristics and deep learning: a prospective dual-center investigation
Chinese Medicine
TCM constitution
Tongue diagnosis
Deep learning
Neural network
title Study on a Traditional Chinese Medicine constitution recognition model using tongue image characteristics and deep learning: a prospective dual-center investigation
title_full Study on a Traditional Chinese Medicine constitution recognition model using tongue image characteristics and deep learning: a prospective dual-center investigation
title_fullStr Study on a Traditional Chinese Medicine constitution recognition model using tongue image characteristics and deep learning: a prospective dual-center investigation
title_full_unstemmed Study on a Traditional Chinese Medicine constitution recognition model using tongue image characteristics and deep learning: a prospective dual-center investigation
title_short Study on a Traditional Chinese Medicine constitution recognition model using tongue image characteristics and deep learning: a prospective dual-center investigation
title_sort study on a traditional chinese medicine constitution recognition model using tongue image characteristics and deep learning a prospective dual center investigation
topic TCM constitution
Tongue diagnosis
Deep learning
Neural network
url https://doi.org/10.1186/s13020-025-01126-w
work_keys_str_mv AT yongyueliu studyonatraditionalchinesemedicineconstitutionrecognitionmodelusingtongueimagecharacteristicsanddeeplearningaprospectivedualcenterinvestigation
AT linmiaofan studyonatraditionalchinesemedicineconstitutionrecognitionmodelusingtongueimagecharacteristicsanddeeplearningaprospectivedualcenterinvestigation
AT meizhao studyonatraditionalchinesemedicineconstitutionrecognitionmodelusingtongueimagecharacteristicsanddeeplearningaprospectivedualcenterinvestigation
AT dongshenwei studyonatraditionalchinesemedicineconstitutionrecognitionmodelusingtongueimagecharacteristicsanddeeplearningaprospectivedualcenterinvestigation
AT menglanzhao studyonatraditionalchinesemedicineconstitutionrecognitionmodelusingtongueimagecharacteristicsanddeeplearningaprospectivedualcenterinvestigation
AT yihangdong studyonatraditionalchinesemedicineconstitutionrecognitionmodelusingtongueimagecharacteristicsanddeeplearningaprospectivedualcenterinvestigation
AT xiaoqingzhang studyonatraditionalchinesemedicineconstitutionrecognitionmodelusingtongueimagecharacteristicsanddeeplearningaprospectivedualcenterinvestigation