Inspection of the complexion is one of the characteristics of traditional Chinese medical diagnosis. Traditional Chinese medicine puts high emphasis on inspection of the complexion and there exists detailed discussion on inspection of facial expression in Neijing. The so-called inspection of facial expression is a method to diagnose diseases according to the theory of five Zang-organs matching five elements and five colors by distinguishing various changes of facial color, such as green, red, yellow, white and black based on yin and yang doctrine and five elements theory. Nowadays, more and more experts have introduced color optical theory and modern devices into the modern research field of traditional Chinese medical diagnosis with the development of color optical theory and the renewal of determining devices, such as digital camera, color differentiation meter and spectrophotometer, to make the research more scientific and objective and avoid the deviations caused by human factors. The modern study of traditional Chinese medicine diagnosis has made fare progress, consequently enriching the contents of its facial color observation and giving a more scientific explanation of it. However, the devices being used now are still disunited; the data may be unilateral and cannot contain the whole information. So the most important task is to invent and use scientific devices conforming better with the theory of five colors observation in traditional Chinese medicine.

Glossoscopy is one of the essential part of four diagnostic methods of TCM, and objectification of tongue inspection is an important component of the TCM modernization, image collecting and analyzing technology is its major means. In the research of tongue image, extraction of the body of tongue, the segmentation of body and fur of tongue are important procedure in the recognition of tongue image. In recent years, the information study of tongue inspection has been profound gradually with the development of technology of image analysis. This paper discusses research status of extraction of the body of tongue, the segmentation of body and fur of tongue.

Abstract Traditional Chinese medicine (TCM) auscultation has a long history, and with advancements in equipment and analytical methods, the quantitative analysis of auscultation parameters has determined. However, the complexity and diversity of auscultation, along with variations in devices, analytical methods, and applications, bring challenges to its standardization and deeper application. This review presents the advancements in auscultation equipment and systems, auscultation characteristic parameters, and their application in the diagnosis of pulmonary diseases and syndromes over the past 10 years, while also exploring the progress and challenges of current digital research of auscultation. This review also proposes the establishment of standardized protocols for the collection and analysis of auscultation data, the incorporation of advanced artificial intelligence (AI) auscultation analysis methods, and an exploration of the diagnostic utility of auscultatory features in pulmonary diseases and syndromes, so as to provide more precise decision support for intelligent diagnosis of pulmonary diseases and syndromes

Objective To extract the specific symptoms of TCM syndromes of chronic fatigue (CF). Methods Epidemiological cluster sampling method was used in this trial. Totally 782 cases of CF patients were selected from universities,secondary schools,primary schools and hospitals of southern Fujian province. The subjects filled in "Scale of Clinical Symptoms of Chronic Fatigue" to record the clinical data of symptoms,tongue,and pulse for the diagnosis of specific TCM symptoms. The random forest (RF) method was adopted to encode the 95 symptoms extracted from the above-mentioned scale to select the main symptoms of common syndromes of CF and to measure the contribution of symptoms to the syndromes. Results Symptom groups of 4 syndromes of CF were achieved. Spleen deficiency syndrome:abdominal distention after eating or in afternoon,loss of appetite,sallow completion,loose stools,and emaciation; Heart deficiency syndrome:palpitation,chest fullness,thready pulse,insomnia or dream-disturbed sleep,and forgetfulness; Liver stagnation syndrome:hot temper or depression,sighing,bitter taste,dry throat,and string-taut pulse; Qi deficiency syndrome:swollen tongue with toothprints,shortness of breath,abrupt breathing,inactive talking,and spontaneous sweating. When the symptoms were inputted to the models,the model prediction accuracy was 96.13%,94.75%,95.89%,and 94.26% respectively. Conclusion The RF method has a good classification function on the syndromes of CF. Spleen deficiency syndrome,heart deficiency syndrome,liver stagnation syndrome,and qi deficiency syndrome are commonly appeared syndromes,each of them is provided with its own specific symptoms.

Methods: Data of TCM indicators (tongue, facial, and pulse diagnostics) and clinical parameters from patients diagnosed with CHD at the Cardiology Department of Shanghai Baoshan Hospital of Integrated Traditional Chinese and Western Medicine, from October 3, 2023 to March 15, 2024, were collected. Important variables were identified using importance screening and correlation analysis with CHD risk factors and laboratory markers. Six machine learning models including logistic regression (LR), decision tree (DT), support vector machine (SVM), k-nearest neighbors (KNN), random forest (RF), and gradient boosting (GB), were applied to evaluate the risk of coronary artery obstruction by combining clinical and TCM data of CHD. Model performance was assessed using metrics such as accuracy, precision, and recall, with reliability validated through ten-fold cross-validation. Results: A total of 288 patients were included in the study. Fifteen clinical risk factors, including body mass index (BMI), myoglobin, and alcohol consumption history, were incorporated into the diagnostic models. The KNN model showed good performance when combining clinical data with tongue and facial data. The SVM model performed well when clinical data was combined with pulse data. Among all the models, the KNN model with 10-fold cross-validation, which integrates the three types of TCM diagnostic data (tongue, face, and pulse) with clinical data, performs the best (accuracy: 0.837, precision: 0.814, and recall: 0.809). Conclusion Incorporating TCM diagnostic data can enhance the accuracy of coronary artery obstruction risk assessment. The KNN prediction model that integrate tongue, facial, and pulse data performs the best and can be recommended as a clinical decision support tool.

Objective: To develop a non-invasive predictive model for coronary artery stenosis severity based on adaptive multi-modal integration of traditional Chinese and western medicine data. Methods: Clinical indicators, echocardiographic data, traditional Chinese medicine (TCM) tongue manifestations, and facial features were collected from patients who underwent coronary computed tomography angiography (CTA) in the Cardiac Care Unit (CCU) of Shanghai Tenth People's Hospital between May 1, 2023 and May 1, 2024. An adaptive weighted multi-modal data fusion (AWMDF) model based on deep learning was constructed to predict the severity of coronary artery stenosis. The model was evaluated using metrics including accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic (ROC) curve (AUC). Further performance assessment was conducted through comparisons with six ensemble machine learning methods, data ablation, model component ablation, and various decision-level fusion strategies. Results: A total of 158 patients were included in the study. The AWMDF model achieved excellent predictive performance (AUC = 0.973, accuracy = 0.937, precision = 0.937, recall = 0.929, and F1 score = 0.933). Compared with model ablation, data ablation experiments, and various traditional machine learning models, the AWMDF model demonstrated superior performance. Moreover, the adaptive weighting strategy outperformed alternative approaches, including simple weighting, averaging, voting, and fixed-weight schemes. Conclusion The AWMDF model demonstrates potential clinical value in the non-invasive prediction of coronary artery disease and could serve as a tool for clinical decision support.

Objective To establish the optimum syndrome classification method by using the technology of modern TCM diagnosis and artificial intelligence analysis method for menopausal syndrome differentiation of TCM. Methods Diagnostic information of menopausal syndrome patients was collected and syndromes were classified according to TCM syndrome differentiation standard. Three kinds of common data mining classification algorithm, Bayesian network, K-nearest neighbors and support vector machine, were used for analysis on information data of the four methods of diagnosis of menopausal syndrome.Results The time, classification accuracy, coverage rate and margin curve of establishing TCM syndrome model by the three kinds of algorithm methods under the circumstances of same training and data. The influence of the number of training samples of 3 kinds of algorithm methods was analyzed, and the model established by the three kinds of algorithms was evaluated.Conclusion Bayesian network algorithm is better than the other two methods in the menopausal syndrome classification effect.

Objective To study distribution rules of TCM syndrome characteristics of menopausal syndrome; To provide references for clinical treatment and further study.Methods The articles related to menopausal syndrome in CNKI, VIP, Wanfang Data, CBM and TCMDS during Jun. 1983 to Jun. 2013 were retrieved and analyzed. The original data were input into computer and established the menopausal syndrome literature database. Methods of cluster analysis, factor analysis, and frequency analysis were combined to conduct statistical analysis.Results A total of 270 articles and 730 patients were included in the analysis, including 42 syndromes and 73 symptoms. The four diagnostic information of top 9 syndromes was analyzed by clustering and 5 kinds of basic syndrome types were obtained, including liver and kidney yin deficiency, liver depression, heart-kidney disharmony, heart and spleen deficiency, and spleen and kidney yang deficiency; the core symptoms of each syndrome were extracted by factor analysis and frequency dominance method, and the main points of syndrome differentiations were initially established. Conclusion Three methods combined with relevant expert advice were used to initially establish the syndrome diagnosis of menopause syndrome, which can lay a solid foundation for further study.

To observe the facial spectrum and color of different points, the positions of heart, liver, spleen, lung and kidney of traditional Chinese medicine reflecting on the face, in healthy participants and those with a sub-health status, so as to provide an objective basis for health evaluation.

To establish an analytical method for tongue image acquisition under natural daylight based on L*a*b* error correction, and to observe the classification rules of tongue color using color error correction.