TCM tongue diagnosis index of early-stage breast cancer

Exploring hepatic fibrosis screening via deep learning analysis of tongue images

Background

Tongue inspection, an essential diagnostic method in Traditional Chinese Medicine (TCM), has the potential for early-stage disease screening. This study aimed to evaluate the effectiveness of deep learning-based analysis of tongue images for hepatic fibrosis screening.

Methods

A total of 1083 tongue images were collected from 741 patients and divided into training, validation, and test sets. DenseNet-201, a convolutional neural network, was employed to train the AI model using these tongue images. The predictive performance of AI was assessed and compared with that of FIB-4, using real-time two-dimensional shear wave elastography as the reference standard.

Results

The proposed AI model achieved an accuracy of 0.845 (95% CI: 0.79-0.90) and 0.814 (95% CI: 0.76-0.87) in the validation and test sets, respectively, with negative predictive values (NPVs) exceeding 90% in both sets. The AI model outperformed FIB-4 in all aspects, and when combined with FIB-4, the NPV reached 94.4%.

Conclusion

Tongue inspection, with the assistance of AI, could serve as a first-line screening method for hepatic fibrosis.

Using Advanced Convolutional Neural Network Approaches to Reveal Patient Age, Gender, and Weight Based on Tongue Images

The human tongue has been long believed to be a window to provide important insights into a patient's health in medicine. The present study introduced a novel approach to predict patient age, gender, and weight inferences based on tongue images using pretrained deep convolutional neural networks (CNNs). Our results demonstrated that the deep CNN models (e.g., ResNeXt) trained on dorsal tongue images produced excellent results for age prediction with a Pearson correlation coefficient of 0.71 and a mean absolute error (MAE) of 8.5 years. We also obtained an excellent classification of gender, with a mean accuracy of 80% and an AUC (area under the receiver operating characteristic curve) of 88%. ResNeXt model also obtained a moderate level of accuracy for weight prediction, with a Pearson correlation coefficient of 0.39 and a MAE of 9.06 kg. These findings support our hypothesis that the human tongue contains crucial information about a patient. This study demonstrated the feasibility of using the pretrained deep CNNs along with a large tongue image dataset to develop computational models to predict patient medical conditions for noninvasive, convenient, and inexpensive patient health monitoring and diagnosis.

Association between color value of tongue and T2DM based on dose-response analyses using restricted cubic splines in China: A cross-sectional study

This study aimed to explore the relationship between international commission on illumination (CIE) L*a*b* color value of tongue and type 2 diabetes mellitus (T2DM). We used restricted cubic spline method and logistic regression method to assess the relationship between CIE L*a*b* color value of tongue and T2DM. A total of 2439 participants (991 T2DM and 1448 healthy) were included. A questionnaire survey and tongue images obtained with tongue diagnosis analysis-1 were analyzed. As required, chi-square and t tests were applied to compare the T2DM and healthy categories. Our findings suggest the 95% confidence interval and odds ratio for body mass index, hypertension, and age were 0.670 (0.531-0.845), 13.461 (10.663-16.993), and 2.595 (2.324-2.897), respectively, when compared to the healthy group. A linear dose-response relationship with an inverse U-shape was determined between CIE L* and CIE a* values and T2DM (P < .001 for overall and P < .001 for nonlinear). Furthermore, U-shaped and linear dose-response associations were identified between T2DM and CIE b* values (P = .0160 for nonlinear). Additionally, in adults, the CIE L*a*b* color value had a correlation with T2DM. This novel perspective provides a multidimensional understanding of traditional Chinese medicine tongue color, elucidating the potential of CIE L*a*b* color values of tongue in the diagnosis of T2DM.

Predictive value of TCM tongue characteristics for chemotherapy-induced myelosuppression in patients with lung cancer

This study aimed to investigate the clinical predictors, including traditional Chinese medicine tongue characteristics and other clinical parameters for chemotherapy-induced myelosuppression (CIM), and then to develop a clinical prediction model and construct a nomogram. A total of 103 patients with lung cancer were prospectively enrolled in this study. All of them were scheduled to receive first-line chemotherapy regimens. Participants were randomly assigned to either the training group (n = 52) or the test group (n = 51). Tongue characteristics and clinical parameters were collected before the start of chemotherapy, and then the incidence of myelosuppression was assessed after treatment. We used univariate logistic regression analysis to identify the risk predictors for assessing the incidence of CIM. Moreover, we developed a predictive model and a nomogram using multivariate logistic regression analysis. Finally, we evaluated the predictive performance of the model by examining the area under the curve value of the receiver operating characteristic, calibration curve, and decision curve analysis. As a result, a total of 3 independent predictors were found to be associated with the CIM in multivariate regression analysis: the fat tongue (OR = 3.67), Karnofsky performance status score (OR = 0.11), and the number of high-toxic drugs in chemotherapy regimens (OR = 4.78). Then a model was constructed using these 3 predictors and it exhibited a robust predictive performance with an area under the curve of 0.82 and the consistent calibration curves. Besides, the decision curve analysis results suggested that applying this predictive model can result in more net clinical benefit for patients. We established a traditional Chinese medicine prediction model based on the tongue characteristics and clinical parameters, which could serve as a useful tool for assessing the risk of CIM.

A Framework to Predict Gastric Cancer Based on Tongue Features and Deep Learning

Gastric cancer has become a global health issue, severely disrupting daily life. Early detection in gastric cancer patients and immediate treatment contribute significantly to the protection of human health. However, routine gastric cancer examinations carry the risk of complications and are time-consuming. We proposed a framework to predict gastric cancer non-invasively and conveniently. A total of 703 tongue images were acquired using a bespoke tongue image capture instrument, then a dataset containing subjects with and without gastric cancer was created. As the images acquired by this instrument contain non-tongue areas, the Deeplabv3+ network was applied for tongue segmentation to reduce the interference in feature extraction. Nine tongue features were extracted, relationships between tongue features and gastric cancer were explored by using statistical methods and deep learning, finally a prediction framework for gastric cancer was designed. The experimental results showed that the proposed framework had a strong detection ability, with an accuracy of 93.6%. The gastric cancer prediction framework created by combining statistical methods and deep learning proposes a scheme for exploring the relationships between gastric cancer and tongue features. This framework contributes to the effective early diagnosis of patients with gastric cancer.

Machine Learning-Based Technique for the Severity Classification of Sublingual Varices according to Traditional Chinese Medicine

Tongue diagnosis, a noninvasive examination, is an essential step for syndrome differentiation and treatment in traditional Chinese medicine (TCM). Sublingual vein (SV) is examined to determine the presence of blood stasis and blood stasis syndrome. Many studies have shown that the degree of SV stasis positively correlates with disease severity. However, the diagnoses of SV examination are often subjective because they are influenced by factors such as physicians’ experience and color perception, resulting in different interpretations. Therefore, objective and scientific diagnostic approaches are required to determine the severity of sublingual varices. This study aims at developing a computer-assisted system based on machine learning (ML) techniques for diagnosing the severity of sublingual varicose veins. We conducted a comparative study of the performance of several supervised ML models, including the support vendor machine, K-neighbor, decision tree, linear regression, and Ridge classifier and their variants. The main task was to differentiate sublingual varices into mild and severe by using images of patients’ SVs. To improve diagnostic accuracy and to accelerate the training process, we proposed using two model reduction techniques, namely, the principal component analysis in conjunction with the slice inverse regression and the convolution neural network (CNN), to extract valuable features during the preprocessing of data. Our results showed that these two extraction methods can reduce the training time for the ML methods, and the Ridge-CNN method can achieve an accuracy rate as high as 87.5%, which is similar to that of experienced TCM physicians. This computer-aided tool can be used for reference clinical diagnosis. Furthermore, it can be employed by junior physicians to learn and to use in clinical settings.

Microbiological characteristics of different tongue coatings in adults

Background

Tongue coating is an important health indicator in traditional Chinese medicine (TCM). The tongue coating microbiome can distinguish disease patients from healthy controls. To study the relationship between different types of tongue coatings and health, we analyzed the species composition of different types of tongue coatings and the co-occurrence relationships between microorganisms in Chinese adults.

From June 2019 to October 2020, 158 adults from Hangzhou and Shaoxing City, Zhejiang Province, were enrolled. We classified the TCM tongue coatings into four different types: thin white tongue fur (TWF), thin yellow tongue fur (TYF), white greasy tongue fur (WGF), and yellow greasy tongue fur (YGF). Tongue coating specimens were collected and used for 16S rRNA gene sequencing using the Illumina MiSeq system. Wilcoxon rank-sum and permutational multivariate analysis of variance tests were used to analyze the data. The microbial networks in the four types of tongue coatings were inferred independently using sparse inverse covariance estimation for ecological association inference.

Results

The microbial composition was similar among the different tongue coatings; however, the abundance of microorganisms differed. TWF had a higher abundance of Fusobacterium periodonticum and Neisseria mucosa, the highest α-diversity, and a highly connected community (average degree = 3.59, average closeness centrality = 0.33). TYF had the lowest α-diversity, but the most species in the co-occurrence network diagram (number of nodes = 88). The platelet-to-lymphocyte ratio (PLR) was associated with tongue coating (P = 0.035), and the YGF and TYF groups had higher PLR values. In the co-occurrence network, Aggregatibacter segnis was the “driver species” of the TWF and TYF groups and correlated with C-reactive protein (P < 0.05). Streptococcus anginosus was the “driver species” in the YGF and TWF groups and was positively correlated with body mass index and weight (P < 0.05).

Conclusion

Different tongue coatings have similar microbial compositions but different abundances of certain bacteria. The co-occurrence of microorganisms in the different tongue coatings also varies. The significance of different tongue coatings in TCM theory is consistent with the characteristics and roles of the corresponding tongue-coating microbes. This further supports considering tongue coating as a risk factor for disease.

Tongue Manifestation in Patients with Osteonecrosis of the Femoral Head: A Cross-sectional Study

OBJECTIVE

Although tongue manifestation is a vital component of Traditional Chinese Medicine (TCM), relevant research on patients with osteonecrosis of the femoral head (ONFH) is still lacking. This study will explore the characteristic tongue manifestation of ONFH patients to inform future research and clinical practice.

METHODS

This is a cross-sectional study. All ONFH patients meeting criteria and their clinical data were collected from the online China osteonecrosis of the femoral head database (CONFHD) since it was created. Organized tongue manifestations of eligible patients through the tongue manifestation acquisition instrument, including tongue shape, tongue color, tongue coating thickness, tongue coating color and tongue coating moisture. We used descriptive analysis for the general information while systematic clustering analysis for the better summary of tongue characteristics.

RESULTS

A total of 375 ONFH patients were included with an average age of 46.3 years. Most patients appeared with enlarged tongue body (54.4%), and the proportions of pale and red tongue (62.4%) were higher than others. Tongue coating were mainly showed as thick (64.5%), white (57.6%) and moist (79.7%). Comparison of tongue shape between different causes of ONFH had a significant statistically difference (P = 0.000). Tongue manifestations could be cluster analyzed into three categories which were matched into four TCM syndromes.

CONCLUSIONS

The tongue manifestation of ONFH patients has a significant change both in tongue body and coating, and different features may be related to the ONFH pathology. This study provides new and valuable tongue informations for a preliminary screening of ONFH patients.

Deep learning model for tongue cancer diagnosis using endoscopic images

In this study, we developed a deep learning model to identify patients with tongue cancer based on a validated dataset comprising oral endoscopic images. We retrospectively constructed a dataset of 12,400 verified endoscopic images from five university hospitals in South Korea, collected between 2010 and 2020 with the participation of otolaryngologists. To calculate the probability of malignancy using various convolutional neural network (CNN) architectures, several deep learning models were developed. Of the 12,400 total images, 5576 images related to the tongue were extracted. The CNN models showed a mean area under the receiver operating characteristic curve (AUROC) of 0.845 and a mean area under the precision-recall curve (AUPRC) of 0.892. The results indicate that the best model was DenseNet169 (AUROC 0.895 and AUPRC 0.918). The deep learning model, general physicians, and oncology specialists had sensitivities of 81.1%, 77.3%, and 91.7%; specificities of 86.8%, 75.0%, and 90.9%; and accuracies of 84.7%, 75.9%, and 91.2%, respectively. Meanwhile, fair agreement between the oncologist and the developed model was shown for cancer diagnosis (kappa value = 0.685). The deep learning model developed based on the verified endoscopic image dataset showed acceptable performance in tongue cancer diagnosis.

A Clinical Study on the Relationship Among Insomnia, Tongue Diagnosis, and Oral Microbiome

Currently, there is a lack of adequate methods to assess insomnia objectively. This study addresses the usefulness of tongue features and oral microbial profile as a potential diagnostic biomarker of insomnia. One hundred insomniac patients and 20 healthy control subjects were selected. Their demographic and clinical characteristics, as well as the tongue diagnostic indices and oral microbial profile, were examined. Compared to the control group, insomniac patients showed a higher abnormal low-frequency/high-frequency (LF/HF) ratio. In tongue diagnosis, the indices related to lightness of tongue body and tongue coating were higher in the insomniac group vs. the control group. Furthermore, linear discriminant analysis (LDA) of oral microbial population revealed that the relative abundances of Clostridia, Veillonella, Bacillus and Lachnospiraceae were significantly higher in the insomniac patients than the control group. Additionally, the tongue features of the insomniac group exhibited that the non-coating group had a poor sleep condition compared to the thick-coating group, although the difference was insignificant. On the other hand, the oral microbial communities of the insomniac patients revealed greater alpha and beta diversities in the non-coating group vs. the thick-coating group. The alpha and beta diversities were higher in orotype1 than orotype2. Collectively, this study highlighted that the lightness of tongue body and tongue coating as well as oral microbial profiles of SR1, Actinobacteria, Clostridia and Lachnospiraceae_unclassified could be considered potential biomarkers of insomnia.

Constructing tongue coating recognition model using deep transfer learning to assist syndrome diagnosis and its potential in noninvasive ethnopharmacological evaluation

ETHNOPHARMACOLOGICAL RELEVANCE

Tongue coating has been used as an effective signature of health in traditional Chinese medicine (TCM). The level of greasy coating closely relates to the strength of dampness or pathogenic qi in TCM theory. Previous empirical studies and our systematic review have shown the relation between greasy coating and various diseases, including gastroenteropathy, coronary heart disease, and coronavirus disease 2019 (COVID-19). However, the objective and intelligent greasy coating and related diseases recognition methods are still lacking. The construction of the artificial intelligent tongue recognition models may provide important syndrome diagnosis and efficacy evaluation methods, and contribute to the understanding of ethnopharmacological mechanisms based on TCM theory.

AIM OF THE STUDY

The present study aimed to develop an artificial intelligent model for greasy tongue coating recognition and explore its application in COVID-19.

MATERIALS AND METHODS

Herein, we developed greasy tongue coating recognition networks (GreasyCoatNet) using convolutional neural network technique and a relatively large (N = 1486) set of tongue images from standard devices. Tests were performed using both cross-validation procedures and a new dataset (N = 50) captured by common cameras. Besides, the accuracy and time efficiency comparisons between the GreasyCoatNet and doctors were also conducted. Finally, the model was transferred to recognize the greasy coating level of COVID-19.

RESULTS

The overall accuracy in 3-level greasy coating classification with cross-validation was 88.8% and accuracy on new dataset was 82.0%, indicating that GreasyCoatNet can obtain robust greasy coating estimates from diverse datasets. In addition, we conducted user study to confirm that our GreasyCoatNet outperforms TCM practitioners, yet only consuming roughly 1% of doctors' examination time. Critically, we demonstrated that GreasyCoatNet, along with transfer learning, can construct more proper classifier of COVID-19, compared to directly training classifier on patient versus control datasets. We, therefore, derived a disease-specific deep learning network by finetuning the generic GreasyCoatNet.

CONCLUSIONS

Our framework may provide an important research paradigm for differentiating tongue characteristics, diagnosing TCM syndrome, tracking disease progression, and evaluating intervention efficacy, exhibiting its unique potential in clinical applications.

Machine Learning Approaches in Traditional Chinese Medicine: A Systematic Review

Machine learning (ML), as a branch of artificial intelligence, acquires the potential and meaningful rules from the mass of data via diverse algorithms. Owing to all research of traditional Chinese medicine (TCM) belonging to the digitalization of clinical records or experimental works, a massive and complex amount of data has become an inextricable part of the related studies. It is thus not surprising that ML approaches, as novel and efficient tools to mine the useful knowledge from data, have created inroads in a diversity of scopes of TCM over the past decade of years. However, by browsing lots of literature, we find that not all of the ML approaches perform well in the same field. Upon further consideration, we infer that the specificity may inhere between the ML approaches and their applied fields. This systematic review focuses its attention on the four categories of ML approaches and their eight application scopes in TCM. According to the function, ML approaches are classified into four categories, including classification, regression, clustering, and dimensionality reduction, and into 14 models as follows in more detail: support vector machine, least square-support vector machine, logistic regression, partial least squares regression, k-means clustering, hierarchical cluster analysis, artificial neural network, back propagation neural network, convolutional neural network, decision tree, random forest, principal component analysis, partial least squares-discriminant analysis, and orthogonal partial least squares-discriminant analysis. The eight common applied fields are divided into two parts: one for TCM, such as the diagnosis of diseases, the determination of syndromes, and the analysis of prescription, and the other for the related researches of Chinese herbal medicine, such as the quality control, the identification of geographic origins, the pharmacodynamic material basis, the medicinal properties, and the pharmacokinetics and pharmacodynamics. Additionally, this paper discusses the function and feature difference among ML approaches when they are applied to the corresponding fields via comparing their principles. The specificity of each approach to its applied fields has also been affirmed, whereby laying a foundation for subsequent studies applying ML approaches to TCM.

Tongue Diagnosis Index of Chronic Kidney Disease

BACKGROUND

To apply non-invasive Automatic Tongue Diagnosis System (ATDS) in analyzing tongue features in patients with chronic kidney disease (CKD).

METHODS

This was a cross-sectional, case-controlled observational study. Patients with CKD who met the inclusion and exclusion criteria were enrolled and divided into the following groups according to renal function and dialysis status: non-dialysis CKD group; end-stage renal disease (ESRD) group; and control group. Tongue images were captured and eight tongue features-shape, color, fur thickness, saliva, fissure, ecchymosis, teeth marks, and red dots-were imaged and analyzed by ATDS.

RESULTS

117 participants (57 men, 60 women) were enrolled in the study, which included 16 in control group, 38 in non-dialysis CKD group, and 63 in ESRD group. We demonstrated significant differences in the fur thickness (p = 0.045), color (p = 0.005), amounts of ecchymosis (p = 0.010), teeth marks (p = 0.016), and red dot (p < 0.001) among three groups. The areas under receiver operating characteristic curve for the amount of ecchymosis was 0.757 ± 0.055 (95% confidence interval, 0.648-0866; p < 0.001). Additionally, with increase in ecchymosis by one point, the risk of CKD dialysis rose by 1.523 times (95% confidence interval, 1.198-1.936; p = 0.001). After hemodialysis, the amount of saliva (p = 0.038), the area of saliva (p = 0.048) and the number of red dots (p = 0.040) were decreased significantly among patients with ESRD. On the contrary, the percentage of coating (p = 0.002) and area of coating (p = 0.026) were increased significantly after hemodialysis.

CONCLUSION

Blood deficiency and stasis with qi deficiency or blood heat syndrome (Zheng pattern) is common in patients with CKD. The risk of CKD dialysis increases with increasing ecchymosis. Hemodialysis can affect saliva, tongue coating, and relieve heat syndrome among ESRD patients.

Panoramic tongue imaging and deep convolutional machine learning model for diabetes diagnosis in humans

Diabetes is a serious metabolic disorder with high rate of prevalence worldwide; the disease has the characteristics of improper secretion of insulin in pancreas that results in high glucose level in blood. The disease is also associated with other complications such as cardiovascular disease, retinopathy, neuropathy and nephropathy. The development of computer aided decision support system is inevitable field of research for disease diagnosis that will assist clinicians for the early prognosis of diabetes and to facilitate necessary treatment at the earliest. In this research study, a Traditional Chinese Medicine based diabetes diagnosis is presented based on analyzing the extracted features of panoramic tongue images such as color, texture, shape, tooth markings and fur. The feature extraction is done by Convolutional Neural Network (CNN)—ResNet 50 architecture, and the classification is performed by the proposed Deep Radial Basis Function Neural Network (RBFNN) algorithm based on auto encoder learning mechanism. The proposed model is simulated in MATLAB environment and evaluated with performance metrics—accuracy, precision, sensitivity, specificity, F1 score, error rate, and receiver operating characteristics (ROC). On comparing with existing models, the proposed CNN based Deep RBFNN machine learning classifier model outperformed with better classification performance and proving its effectiveness.

A Perspective on Tongue Diagnosis in Patients with Breast Cancer

Introduction

Breast cancer (BC) is the most common cancer in women and patients with BC often undergo complex treatment. In Taiwan, nearly 80% of patients with BC seek traditional Chinese medicine (TCM) during adjuvant chemotherapy to relieve discomfort and side effects. This study investigated tongue features and pattern differentiation through noninvasive TCM tongue diagnosis in patients with BC.

Materials and Methods

This cross-sectional, case-controlled, retrospective observational study collected patient data through a chart review. The tongue features were extracted using the automatic tongue diagnosis system (ATDS). Nine tongue features, including tongue shape, tongue color, fur thickness, fur color, saliva, tongue fissures, ecchymoses, teeth marks, and red dots, were analyzed. Results and Discussion. Objective image analysis techniques were used to identify significant differences in the many tongue features between BC patients and non-BC individuals. A significantly larger proportion of patients with BC had a small tongue (p < 0.001), pale tongue (p < 0.001), thick fur (p < 0.001), yellow fur (p < 0.001), wet saliva (p < 0.001), thick tongue fur (p < 0.001), fissures (p=0.040), and ecchymoses in the heart-lung area (p=0.013). According to logistic regression, small tongue shape, pale tongue color, yellow fur color, wet saliva, and the amounts of fissures were associated with a significantly increased odds ratio for BC.

Conclusions

This study showed significant differences in tongue features, such as small tongue shape, pale tongue color, thick fur, yellow fur color, wet saliva, fissure, and ecchymoses in the heart-lung area in patients with BC. These tongue features would imply yin deficiency, deficiencies of blood, stagnation of heat, and phlegm/blood stasis in TCM theory. There is a need to investigate effective and safe treatment to enhance the role of TCM in integrated medical care for patients with BC.

A Nonlinear Association between Tongue Fur Thickness and Tumor Marker Abnormality: A Cross-Sectional Study

Background

Many associations between tongue fur and different physiological and biochemical indexes have been revealed. However, the relationship between tongue fur and tumor markers remains unexplored.

Methods

We collected the medical examination reports of 1625 participants. Participants were residents of Chengdu, China, undergoing routine health checkups at the health management center of the Affiliated Hospital of Chengdu University of Traditional Chinese Medicine between December 2018 and September 2020. The participants' tongue fur thickness was measured using the DAOSH four-diagnostic instrument. Tumor marker levels, including t-PSA, AFP, CEA, CA125, and CA199, were measured in the clinical laboratory. Curve-fitting and multivariable logistic regression were used to analyze the association between tongue fur thickness and tumor marker abnormality.

Results

Curve-fitting showed that the relationship between tongue fur thickness and abnormal tumor marker rate was nonlinear, similar to a U shape. As the tongue fur thickness value increased, the abnormal tumor marker probability initially decreased and then increased. Logistic regression showed that, in the crude model, compared with the thin tongue fur group, the odds ratios (ORs) and 95% confidence intervals (CIs) of the less or peeling tongue fur group and thick tongue fur group for tumor marker abnormality were 1.79 (1.02–3.17) and 1.70 (1.13–2.54), respectively. After adjusting gender, age, body mass index (BMI), smoking history, drinking history, tongue color, the form of the tongue, and fur color, the ORs and 95% CIs of the less or peeling tongue fur group and thick tongue fur group were 1.93 (1.04–3.57) and 1.82 (1.17–2.81), respectively.

Conclusions

Excessive or very little tongue fur is associated with tumor marker abnormality. Further cross-sectional studies are needed to evaluate the clinical value of tongue fur for cancer diagnosis and screening.

Digital tongue image analyses for health assessment

Traditional Chinese Medicine (TCM), as an effective alternative medicine, utilizes tongue diagnosis as a major method to assess the patient's health status by examining the tongue's color, shape, and texture. Tongue images can also give the pre-disease indications without any significant disease symptoms, which provides a basis for preventive medicine and lifestyle adjustment. However, traditional tongue diagnosis has limitations, as the process may be subjective and inconsistent. Hence, computer-aided tongue diagnoses have a great potential to provide more consistent and objective health assessments. This paper reviewed the current trends in TCM tongue diagnosis, including tongue image acquisition hardware, tongue segmentation, feature extraction, color correction, tongue classification, and tongue diagnosis system. We also present a case of TCM constitution classification based on tongue images.

Microbial characteristics across different tongue coating types in a healthy population

Background The physical appearance of tongue coatings is vital for traditional Chinese medicine (TCM) to diagnose health and disease status. The microbiota of different tongue coatings could also influence coating formation and be further associated with specific diseases. Previous studies have focused on bacteria from different tongue coatings in the context of specific diseases, but the normal variations in healthy individuals remain unknown.Aim: We examined the tongue microbiota by metagenomics in 94 healthy individuals classified into eight different tongue types.Results: The overall composition of the tongue coating microbiome is not drastically different among different coating types, similar to the findings of previous studies in healthy populations. Further analysis revealed microbiota characteristics of each coating type, and many of the key bacteria are reported to be implicated in diseases. Moreover, further inclusion of diabetic patients revealed disease-specific enrichment of Capnocytophaga, even though the same tongue coatings were studied.Conclusions: This work revealed the characteristic compositions of distinctive tongue coatings in a healthy population, which serves as a basis for understanding the tongue coating formation mechanism and provides a valuable reference to further investigate disease-specific tongue coating bacterial markers.

Application of computer tongue image analysis technology in the diagnosis of NAFLD

Nonalcoholic fatty liver disease (NAFLD), a leading cause of chronic hepatic disease, can progress to liver fibrosis, cirrhosis, and hepatocellular carcinoma. Therefore, it is extremely important to explore early diagnosis and screening methods. In this study, we developed models based on computer tongue image analysis technology to observe the tongue characteristics of 1778 participants (831 cases of NAFLD and 947 cases of non-NAFLD). Combining quantitative tongue image features, basic information, and serological indexes, including the hepatic steatosis index (HSI) and fatty liver index (FLI), we utilized machine learning methods, including Logistic Regression, Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Adaptive Boosting Algorithm (AdaBoost), Naïve Bayes, and Neural Network for NAFLD diagnosis. The best fusion model for diagnosing NAFLD by Logistic Regression, which contained the tongue image parameters, waist circumference, BMI, GGT, TG, and ALT/AST, achieved an AUC of 0.897 (95% CI, 0.882-0.911), an accuracy of 81.70% with a sensitivity of 77.62% and a specificity of 85.22%; in addition, the positive likelihood ratio and negative likelihood ratio were 5.25 and 0.26, respectively. The application of computer intelligent tongue diagnosis technology can improve the accuracy of NAFLD diagnosis and may provide a convenient technical reference for the establishment of early screening methods for NAFLD, which is worth further research and verification.

Tongue image quality assessment based on a deep convolutional neural network

BACKGROUND

Tongue diagnosis is an important research field of TCM diagnostic technology modernization. The quality of tongue images is the basis for constructing a standard dataset in the field of tongue diagnosis. To establish a standard tongue image database in the TCM industry, we need to evaluate the quality of a massive number of tongue images and add qualified images to the database. Therefore, an automatic, efficient and accurate quality control model is of significance to the development of intelligent tongue diagnosis technology for TCM.

METHODS

Machine learning methods, including Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Adaptive Boosting Algorithm (Adaboost), Naïve Bayes, Decision Tree (DT), Residual Neural Network (ResNet), Convolution Neural Network developed by Visual Geometry Group at University of Oxford (VGG), and Densely Connected Convolutional Networks (DenseNet), were utilized to identify good-quality and poor-quality tongue images. Their performances were made comparisons by using metrics such as accuracy, precision, recall, and F1-Score.

RESULTS

The experimental results showed that the accuracy of the three deep learning models was more than 96%, and the accuracy of ResNet-152 and DenseNet-169 was more than 98%. The model ResNet-152 obtained accuracy of 99.04%, precision of 99.05%, recall of 99.04%, and F1-score of 99.05%. The performances were better than performances of other eight models. The eight models are VGG-16, DenseNet-169, SVM, RF, GBDT, Adaboost, Naïve Bayes, and DT. ResNet-152 was selected as quality-screening model for tongue IQA.

CONCLUSIONS

Our research findings demonstrate various CNN models in the decision-making process for the selection of tongue image quality assessment and indicate that applying deep learning methods, specifically deep CNNs, to evaluate poor-quality tongue images is feasible.

Development and Application of Artificial Intelligence in Auxiliary TCM Diagnosis

As an emerging comprehensive discipline, artificial intelligence (AI) has been widely applied in various fields, including traditional Chinese medicine (TCM), a treasure of the Chinese nation. Realizing the organic combination of AI and TCM can promote the inheritance and development of TCM. The paper summarizes the development and application of AI in auxiliary TCM diagnosis, analyzes the bottleneck of artificial intelligence in the field of auxiliary TCM diagnosis at present, and proposes a possible future direction of its development.

Can Traditional Chinese Medicine Diagnosis Be Parameterized and Standardized? A Narrative Review

The integration of Traditional Chinese Medicine (TCM) in Western health systems and research requires a rational communicable theory, scientific proof of efficacy and safety, and quality control measures. The existence of clear definitions and the diagnosis standardization are critical factors to establish the patient's vegetative functional status accurately and, therefore, systematically apply TCM therapeutics such as the stimulation of reflex skin areas known as acupoints. This science-based conceptualization entails using validated methods, or even developing new systems able to parameterize the diagnosis and assess TCM related effects by objective measurements. Traditionally, tongue and pulse diagnosis and the functional evaluation of action points by pressure sensitivity and physical examination may be regarded as essential diagnostic tools. Parameterizing these techniques is a future key point in the objectification of TCM diagnosis, such as by electronic digital image analysis, mechanical pulse diagnostic systems, or the systematic evaluation of acupoints' electrophysiology. This review aims to demonstrate and critically analyze some achievements and limitations in the clinical application of device-assisted TCM diagnosis systems to evaluate functional physiological patterns. Despite some limitations, tongue, pulse, and electrophysiological diagnosis devices have been reported as a useful tool while establishing a person's functional status.

Tongue diagnosis indices for gastroesophageal reflux disease: A cross-sectional, case-controlled observational study

Traditional Chinese medicine tongue diagnosis can mirror the status of the internal organ, but evidence is lacking regarding the accuracy of tongue diagnosis to gastroesophageal reflux disease (GERD). This study was to investigate the association between GERD and tongue manifestation, and whether tongue imaging could be initial diagnosis of GERD noninvasively.We conducted a cross-sectional, case-controlled observational study at Kaohsiung Chang Gung Memorial Hospital in Taiwan from January 2016 to September 2017. Participants aged over 20 years old with GERD were enrolled and control group without GERD were matched by sex. Tongue imaging were acquired with automatic tongue diagnosis system, then followed by endoscope examination. Nine tongue features were extracted, and a receiver operating characteristic (ROC) curve, analysis of variance, and logistic regression were used.Each group enrolled 67 participants. We found that the saliva amount (P = .009) and thickness of the tongue's fur (P = .036), especially that in the spleen-stomach area (%) (P = .029), were significantly greater in patients with GERD than in those without. The areas under the ROC curve of the amount of saliva and tongue fur in the spleen-stomach area (%) were 0.606 ± 0.049 and 0.615 ± 0.050, respectively. Additionally, as the value of the amount of saliva and tongue fur in the spleen-stomach area (%) increased, the risk of GERD rose by 3.621 and 1.019 times, respectively. The tongue fur in the spleen-stomach area (%) related to severity of GERD from grade 0 to greater than grade B were 51.67 ± 18.72, 58.10 ± 24.60, and 67.29 ± 24.84, respectively.The amount of saliva and tongue fur in the spleen-stomach area (%) might predict the risk and severity of GERD and might be noninvasive indicators of GERD. Further large-scale, multi-center, randomized investigations are needed to confirm the results.Trial registration: NCT03258216, registered August 23, 2017.

Artificial intelligence in tongue diagnosis: Using deep convolutional neural network for recognizing unhealthy tongue with tooth-mark

Tongue diagnosis plays a pivotal role in traditional Chinese medicine (TCM) for thousands of years. As one of the most important tongue characteristics, tooth-marked tongue is related to spleen deficiency and can greatly contribute to the symptoms differentiation and treatment selection. Yet, the tooth-marked tongue recognition for TCM practitioners is subjective and challenging. Most of the previous studies have concentrated on subjectively selected features of the tooth-marked region and gained accuracy under 80%. In the present study, we proposed an artificial intelligence framework using deep convolutional neural network (CNN) for the recognition of tooth-marked tongue. First, we constructed relatively large datasets with 1548 tongue images captured by different equipments. Then, we used ResNet34 CNN architecture to extract features and perform classifications. The overall accuracy of the models was over 90%. Interestingly, the models can be successfully generalized to images captured by other devices with different illuminations. The good effectiveness and generalization of our framework may provide objective and convenient computer-aided tongue diagnostic method on tracking disease progression and evaluating pharmacological effect from a informatics perspective.

Constructing fine-grained entity recognition corpora based on clinical records of traditional Chinese medicine

Background

In this study, we focus on building a fine-grained entity annotation corpus with the corresponding annotation guideline of traditional Chinese medicine (TCM) clinical records. Our aim is to provide a basis for the fine-grained corpus construction of TCM clinical records in future.

Methods

We developed a four-step approach that is suitable for the construction of TCM medical records in our corpus. First, we determined the entity types included in this study through sample annotation. Then, we drafted a fine-grained annotation guideline by summarizing the characteristics of the dataset and referring to some existing guidelines. We iteratively updated the guidelines until the inter-annotator agreement (IAA) exceeded a Cohen’s kappa value of 0.9. Comprehensive annotations were performed while keeping the IAA value above 0.9.

Results

We annotated the 10,197 clinical records in five rounds. Four entity categories involving 13 entity types were employed. The final fine-grained annotated entity corpus consists of 1104 entities and 67,799 tokens. The final IAAs are 0.936 on average (for three annotators), indicating that the fine-grained entity recognition corpus is of high quality.

Conclusions

These results will provide a foundation for future research on corpus construction and named entity recognition tasks in the TCM clinical domain.

Human Tongue Thermography Could Be a Prognostic Tool for Prescreening the Type II Diabetes Mellitus

Diabetes mellitus is one of the life threatening diseases over the globe, and an early prediction of diabetes is of utmost importance in this current scenario. International Diabetes Federation (IDF) reported nearly half of the world's population was undiagnosed and unaware of being developed into diabetes. In 2017, around 84 million individuals were living with diabetes, and it might increase to 156 million by the end of 2045 stated by IDF. Generally, the diagnosis of diabetes relies on the biochemical method that may cause uneasiness and probability of infections to the subjects. To overcome such difficulties, a noninvasive method is much needed around the globe for primary screening. A change in body temperature is an indication of various diseases. Infrared thermal imaging is relatively a novel technique for skin temperature measurement and turned out to be well known in the medical field due to being noninvasive, risk-free, and repeatable. According to traditional Chinese medicine, the human tongue is a sensitive mirror that reflects the body's pathophysiological condition. So, we have (i) analysed and classified diabetes based on thermal variations at human tongue, (ii) segmented the hot spot regions from tongue thermogram by RGB (red, green, blue) based color histogram image segmentation method and extracted the features using gray level co-occurrence matrix algorithm, (iii) classified normal and diabetes using various machine learning algorithms, and (iv) developed computer aided diagnostic system to classify diabetes mellitus. The baseline measurements and tongue thermograms were obtained from 140 subjects. The measured tongue surface temperature of the diabetic group was found to be greater than normal. The statistical correlation between the HbA_1c and the thermal distribution in the tongue region was found to be r² = 0.5688. The Convolutional Neural Network has outperformed the other classifiers with 94.28% accuracy rate. Thus, tongue thermograms could be used as a preliminary screening approach for diabetes prognosis.

Gender- and age-dependent tongue features in a community-based population

This study, an important groundwork for clinical tongue diagnosis and future traditional Chinese medicine (TCM) research, tested the hypothesis that some tongue features vary significantly between different gender and age groups by utilizing an automatic tongue diagnosis system (ATDS).A cross-sectional study of 1487 participants from a community-based population was performed. Study subjects with ages ranging from 20 to 92 were categorized into 3 groups: <40, 40 to 64, and ≥65 years old, and the subjects were also stratified according to gender. Tongue images were collected at the end of each normal health examination routine to further derive the relevant tongue features of every participant by using the ATDS developed by our team. There were a total of nine tongue features that were identified: tongue shape, tongue color, fur thickness, fur color, saliva, tongue fissure, ecchymosis, teeth mark, and red dot. The corresponding tongue features, demography, and physical/laboratory examination data were compared between different gender and age groups.Our study showed that, compared to females, males had enlarged tongue shape, thicker fur, more fissures and fewer teeth marks (all P < .001), and also had more red tongue color (P = .019), normal saliva (P = .001), more red dots (P = .005) and yellower fur (P = .014). In females, increasing age was associated with more enlarged tongue shape, thicker fur, yellower fur, more saliva, fissures and fewer teeth marks (all P < .001), more ecchymoses (P = .009), and more red tongue color (P = .023). These associations of age with more fissures, fewer teeth marks, fewer red dots (P < .001), median tongue shape (P = .029), and wet saliva (P = .014) were also evident in males, but other relationships were not clearly evident.Even though most of the common tongue features derived from a community-based population are consistent with TCM theory, yet some significantly gender- and age-dependent tongue characteristics were identified. These disparities in tongue features associated with gender or age shall be prudently taken into consideration in clinical tongue diagnosis and future TCM research.

The tongue features associated with type 2 diabetes mellitus

Diabetes mellitus (DM) is a public problem closely associated with numerous oral complications, such as coated tongue, xerostomia, salivary dysfunction, etc. Tongue diagnosis plays an important role in clinical prognosis and treatment of diabetes in the traditional Chinese medicine (TCM). This study investigated discriminating tongue features to distinguish between type 2 DM and non-DM individuals through non-invasive TCM tongue diagnosis.The tongue features for 199 patients with type 2 DM, and 372 non-DM individuals, serving as control, are extracted by the automatic tongue diagnosis system (ATDS). A total of 9 tongue features, namely, tongue shape, tongue color, fur thickness, fur color, saliva, tongue fissure, ecchymosis, teeth mark, and red dot. The demography, laboratory, physical examination, and tongue manifestation data between 2 groups were compared.Patients with type 2 DM possessed significantly larger covering area of yellow fur (58.5% vs 22.5%, P < .001), thick fur (50.8% vs 29.2%, P < .001), and bluish tongue (P < .001) than those of the control group. Also, a significantly higher portion (72.7% vs 55.2%, P < .05) of patients with long-term diabetics having yellow fur color than the short-term counterparts was observed.The high prevalence of thick fur, yellow fur color, and bluish tongue in patient with type 2 DM revealed that TCM tongue diagnosis can serve as a preliminary screening procedure in the early detection of type 2 DM in light of its simple and non-invasive nature, followed by other more accurate testing process. To the best of our knowledge, this is the first attempt in applying non-invasive TCM tongue diagnosis to the discrimination of type 2 DM patients and non-DM individuals.

Sublingual Nodules: Diagnostic Markers of Metastatic Breast Cancer

OBJECTIVE

To evaluate the diagnostic significance of sublingual nodules for metastasis of patients with breast cancer and further to explore the mechanisms of sublingual nodules.

METHODS

The image data of 117 in-patients with breast cancer in stage I-IV in Tianjin Medical University Cancer Institute and Hospital from December 2009 to September 2011 were assessed retrospectively. All photos of patients' tongue were recorded by the digital camera of uniform type within 1 month after serological examination and regular re-examined by computed tomography (CT), magnetic resonance imaging and positron emission tomography CT. The presence of sublingual nodules was the positive standard. Chi square test and two-independent-sample test were used to determine the diagnostic value between the status of sublingual nodules and Clinico-pathological characteristics. The optimal cut-off of uric acid (UA) level to diagnose sublingual nodules was determined by receiver operating curve (ROC) analysis.

RESULTS

Breast cancer patients with sublingual nodules had a higher risk of recurrence and/or metastasis than patients without it (P<0.001). Sublingual nodules was significantly correlated with increased serum UA level (P=0.001). The optimal cut-off value of UA level to diagnose sublingual nodules was 290 μmol/L. Furthermore, the elevated serum UA level (≥290 μmol/L) was significantly related to breast cancer recurrence and/or metastasis (P<0.001).

CONCLUSIONS

Sublingual nodules were potential diagnostic markers for metastatic breast cancer. The formation of sublingual nodules was associated with elevated level of serum UA.

A historical evaluation of Chinese tongue diagnosis in the treatment of septicemic plague in the pre-antibiotic era, and as a new direction for revolutionary clinical research applications

Chinese tongue diagnosis was initially developed to quickly and efficiently diagnose and prescribe medicine, while at the same time allowing the doctor to have minimal contact with the patient. At the time of its compiling, the spread of Yersinia pestis, often causing septicaemia and gangrene of the extremities, may have discouraged doctors to come in direct contact with their patients and take the pulse. However, in recent decades, modern developments in the field of traditional Chinese medicine, as well as the spread of antibiotics in conjunction with the advancements of microbiology, have overshadowed the original purpose of this methodology. Nevertheless, the fast approaching post-antibiotic era and the development of artificial intelligence may hold new applications for tongue diagnosis. This article focuses on the historical development of what is the world's earliest tongue diagnosis monograph, and discusses the directions that such knowledge may be used in future clinical research.

Advances in automated tongue diagnosis techniques

Tongue diagnosis can be an effective, noninvasive method to perform an auxiliary diagnosis any time anywhere, which can support the global need in the primary healthcare system. This work reviews the recent advances in tongue diagnosis, which is a significant constituent of traditional oriental medicinal technology, and explores the literature to evaluate the works done on the various aspects of computerized tongue diagnosis, namely preprocessing, tongue detection, segmentation, feature extraction, tongue analysis, especially in traditional Chinese medicine (TCM). In spite of huge volume of work done on automatic tongue diagnosis (ATD), there is a lack of adequate survey, especially to combine it with the current diagnosis trends. This paper studies the merits, capabilities, and associated research gaps in current works on ATD systems. After exploring the algorithms used in tongue diagnosis, the current trend and global requirements in health domain motivates us to propose a conceptual framework for the automated tongue diagnostic system on mobile enabled platform. This framework will be able to connect tongue diagnosis with the future point-of-care health system.

Tongue diagnosis indices for upper gastrointestinal disorders: Protocol for a cross-sectional, case-controlled observational study

BACKGROUND

Upper gastrointestinal disorders are common in clinical practice, for example, gastritis, peptic ulcer disease, and gastroesophageal reflux disease. Panendoscopy or upper gastrointestinal endoscopy is viewed as the primary tool for examining the upper gastrointestinal mucosa, and permitting biopsy and endoscopic therapy. Although panendoscopy is considered to be a safe procedure with minimal complications, there are still some adverse effects, and patients are often anxious about undergoing invasive procedures. Traditional Chinese medicine tongue diagnosis plays an important role in differentiation of symptoms because the tongue reflects the physiological and pathological condition of the body. The automatic tongue diagnosis system (ATDS), which noninvasively captures tongue images, can provide objective and reliable diagnostic information.

METHODS

This protocol is a cross-sectional, case-controlled observational study investigating the usefulness of the ATDS in clinical practice by examining its efficacy as a diagnostic tool for upper gastrointestinal disorders. Volunteers over 20 years old with and without upper gastrointestinal symptoms will be enrolled. Tongue images will be captured and the patients divided into 4 groups according to their panendoscopy reports, including a gastritis group, peptic ulcer disease group, gastroesophageal reflux disease group, and healthy group. Nine primary tongue features will be extracted and analyzed, including tongue shape, tongue color, tooth mark, tongue fissure, fur color, fur thickness, saliva, ecchymosis, and red dots.

OBJECTIVES

The aim of this protocol is to apply a noninvasive ATDS to evaluate tongue manifestations of patients with upper gastrointestinal disorders and examine its efficacy as a diagnostic tool.

Biology of the Tongue Coating and Its Value in Disease Diagnosis

Tongue diagnosis is one of the most important diagnostic tools in traditional Chinese medicine and has been verified for thousands of years. However, its subjectivity and repeatability has been disputed continuously. The tongue coating as the primary coverage of tongue diagnosis provides more objectivity and reproducibility due to its relatively clear molecular basis; it also has a close relationship with many system diseases and may be used as a potentially valuable disease diagnostic tool. This article describes the material basis of the tongue coating, including its biology (epithelial cells, blood cells, vascular endothelial cells, and bacteria) and its metabolites; moreover, we summarize the diseases that are most correlated with the tongue coating. This will be valuable not only for fundamental research of tongue diagnosis but also for the diagnosis and differential diagnosis of disease. We suppose that the tongue coating could serve as a valuable auxiliary diagnosis tool in many diseases, and more research should focus on how to colligate the various information about the tongue and provide useful information for disease diagnosis.

Potential screening and early diagnosis method for cancer: Tongue diagnosis

Tongue diagnosis, as a unique method of traditional Chinese medicine (TCM), was used to discriminate physiological functions and pathological conditions by observing the changes of the tongue and tongue coating. The aims of the present study were to explore a potential screening and early diagnosis method of cancer through evaluating the differences of the images of tongue and tongue coating and the microbiome on the tongue coating. The DS01-B tongue diagnostic information acquisition system was used to photograph and analyze the tongue and tongue coating. The next-generation sequencing technology was used to determine the V2-V4 hypervariable regions of 16S rDNA to investigate the microbiome on the tongue coating. Bioinformatics and statistical methods were used to analyze the microbial community structure and diversity. Comparing with the healthy people, the number of mirror-like tongue, thick tongue coating and the moisture of tongue were increased in cancers. The dominant color of the tongue in the healthy people was reddish while it was purple in the cancers. The relative abundance of Neisseria, Haemophilus, Fusobacterium and Porphyromonas in the healthy people were higher than that in the cancers. We also found 6 kinds of special microorganisms at species level in cancers. The study suggested that tongue diagnosis may provide potential screening and early diagnosis method for cancer.