Tongue images and tongue coating microbiome in patients with colorectal cancer

Characteristics of tongue coating microbiota in diabetic and non-diabetic kidney patients receiving hemodialysis

BACKGROUND

Tongue-coating microbiota, especially known as the tongue microbiome, holds significant value as both a prospective clinical diagnostic biomarker and therapeutic target, which plays a crucial role in the oral microecological health. However, there is limited understanding of the composition and function of tongue coating microbiota in chronic kidney disease patients undergoing hemodialysis.

METHODS

Thirty-one non-diabetic hemodialysis patients (nonDM_HD), 29 diabetic hemodialysis patients (DM_HD) and 33 healthy controls (HC) were enrolled. Swabs from tongue coating were collected. The 16S rDNA (V3-V4 region) was sequenced to scrutinize the tongue-coating bacterial microbiome difference.

RESULTS

Both nonDM_HD and DM_HD showed distinct bacterial communities of oral microbiota compared to HC. The abundance of Streptococcus, Lactobacillus, Ruminococcaceae G1, Ligilactobacillus and Abiotrophia showed a significant increase (p < 0.05) in DM_HD and nonDM_HD compared to HC, while Haemophilus, Lachnoanaerobaculum, Peptostreptococcaceae G1, Peptostreptococcus showed a significant decrease (p < 0.05) respectively. Veillonella, Lactobacillus, Limosilactobacillus etc. may serve as potential biomarkers for DM_HD. While Streptococcus, Ruminococcaceae G1, Actinobacillus, Abiotrophia can be considered alternative biomarkers for nonDM_HD. Moreover, the enriched Haemophilus, Actinomyces, Lachnoanaerobaculum were prominent features of the tongue coating microbiota in HC, which could be used as the potential therapeutic targets of chronic kidney disease. Network analysis revealed a less complex interaction relationship among the tongue coating bacterial microbiota of nonDM_HD and DM_HD. Furthermore, correlations were identified between the microbiome composition and clinical parameters of the individuals.

CONCLUSION

In conclusion, deciphering the tongue coating microbiota of kidney patients undergoing hemodialysis will helpful in assessing the role of oral microbiota in pathobiology and development of kidney disease, which is expected to become a potential biomarkers and adjuvant therapeutic target.

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.

Application of intelligent tongue image analysis in Conjunction with microbiomes in the diagnosis of MAFLD

Background

Metabolic associated fatty liver disease (MAFLD) is a widespread liver disease that can lead to liver fibrosis and cirrhosis. Therefore, it is essential to develop early diagnosic and screening methods.

Methods

We performed a cross-sectional observational study. In this study, based on data from 92 patients with MAFLD and 74 healthy individuals, we observed the characteristics of tongue images, tongue coating and intestinal flora. A generative adversarial network was used to extract tongue image features, and 16S rRNA sequencing was performed using the tongue coating and intestinal flora. We then applied tongue image analysis technology combined with microbiome technology to obtain an MAFLD early screening model with higher accuracy. In addition, we compared different modelling methods, including Extreme Gradient Boosting (XGBoost), random forest, neural networks(MLP), stochastic gradient descent(SGD), and support vector machine(SVM).

Results

The results show that tongue-coating Streptococcus and Rothia, intestinal Blautia, and Streptococcus are potential biomarkers for MAFLD. The diagnostic model jointly incorporating tongue image features, basic information (gender, age, BMI), and tongue coating marker flora (Streptococcus, Rothia), can have an accuracy of 96.39%, higher than the accuracy value except for bacteria.

Conclusion

Combining computer-intelligent tongue diagnosis with microbiome technology enhances MAFLD diagnostic accuracy and provides a convenient early screening reference.

Artificial intelligence in tongue diagnosis: classification of tongue lesions and normal tongue images using deep convolutional neural network

OBJECTIVE

This study aims to classify tongue lesion types using tongue images utilizing Deep Convolutional Neural Networks (DCNNs).

METHODS

A dataset consisting of five classes, four tongue lesion classes (coated, geographical, fissured tongue, and median rhomboid glossitis), and one healthy/normal tongue class, was constructed using tongue images of 623 patients who were admitted to our clinic. Classification performance was evaluated on VGG19, ResNet50, ResNet101, and GoogLeNet networks using fusion based majority voting (FBMV) approach for the first time in the literature.

RESULTS

In the binary classification problem (normal vs. tongue lesion), the highest classification accuracy performance of 93,53% was achieved utilizing ResNet101, and this rate was increased to 95,15% with the application of the FBMV approach. In the five-class classification problem of tongue lesion types, the VGG19 network yielded the best accuracy rate of 83.93%, and the fusion approach improved this rate to 88.76%.

CONCLUSION

The obtained test results showed that tongue lesions could be identified with a high accuracy by applying DCNNs. Further improvement of these results has the potential for the use of the proposed method in clinic applications.

Distinct microbiome of tongue coating and gut in type 2 diabetes with yellow tongue coating

The gut microbiome plays a critical role in the pathogenesis of type 2 diabetes mellitus (T2DM). However, the inconvenience of obtaining fecal samples hinders the clinical application of gut microbiome analysis. In this study, we hypothesized that tongue coating color is associated with the severity of T2DM. Therefore, we aimed to compare tongue coating, gut microbiomes, and various clinical parameters between patients with T2DM with yellow (YC) and non-yellow tongue coatings (NYC). Tongue coating and gut microbiomes of 27 patients with T2DM (13 with YC and 14 with NYC) were analyzed using 16S rDNA gene sequencing technology. Additionally, we measured glycated hemoglobin (HbA1c), random blood glucose (RBG), fasting blood glucose (FBG), postprandial blood glucose (PBG), insulin (INS), glucagon (GC), body mass index (BMI), and homeostasis model assessment of β-cell function (HOMA-β) levels for each patient. The correlation between tongue coating and the gut microbiomes was also analyzed. Our findings provide evidence that the levels of Lactobacillus spp. are significantly higher in both the tongue coating and the gut microbiomes of patients with YC. Additionally, we observed that elevated INS and GC levels, along with decreased BMI and HOMA-β levels, were indicative of a more severe condition in patients with T2DM with YC. Moreover, our results suggest that the composition of the tongue coating may reflect the presence of Lactobacillus spp. in the gut. These results provide insights regarding the potential relationship between tongue coating color, the gut microbiome, and T2DM.

In-depth metaproteomics analysis of tongue coating for gastric cancer: a multicenter diagnostic research study

BACKGROUND

Our previous study revealed marked differences in tongue images between individuals with gastric cancer and those without gastric cancer. However, the biological mechanism of tongue images as a disease indicator remains unclear. Tongue coating, a major factor in tongue appearance, is the visible layer on the tongue dorsum that provides a vital environment for oral microorganisms. While oral microorganisms are associated with gastric and intestinal diseases, the comprehensive function profiles of oral microbiota remain incompletely understood. Metaproteomics has unique strength in revealing functional profiles of microbiota that aid in comprehending the mechanism behind specific tongue coating formation and its role as an indicator of gastric cancer.

METHODS

We employed pressure cycling technology and data-independent acquisition (PCT-DIA) mass spectrometry to extract and identify tongue-coating proteins from 180 gastric cancer patients and 185 non-gastric cancer patients across 5 independent research centers in China. Additionally, we investigated the temporal stability of tongue-coating proteins based on a time-series cohort. Finally, we constructed a machine learning model using the stochastic gradient boosting algorithm to identify individuals at high risk of gastric cancer based on tongue-coating microbial proteins.

RESULTS

We measured 1432 human-derived proteins and 13,780 microbial proteins from 345 tongue-coating samples. The abundance of tongue-coating proteins exhibited high temporal stability within an individual. Notably, we observed the downregulation of human keratins KRT2 and KRT9 on the tongue surface, as well as the downregulation of ABC transporter COG1136 in microbiota, in gastric cancer patients. This suggests a decline in the defense capacity of the lingual mucosa. Finally, we established a machine learning model that employs 50 microbial proteins of tongue coating to identify individuals at a high risk of gastric cancer, achieving an area under the curve (AUC) of 0.91 in the independent validation cohort.

CONCLUSIONS

We characterized the alterations in tongue-coating proteins among gastric cancer patients and constructed a gastric cancer screening model based on microbial-derived tongue-coating proteins. Tongue-coating proteins are shown as a promising indicator for identifying high-risk groups for gastric cancer. Video Abstract.

Alterations of the salivary microbiota in gastroesophageal reflux disease

OBJECTIVES

Gastroesophageal reflux disease (GERD) is among the most prevalent gastrointestinal disorders. The oral microbiota plays an important role in human health and may be altered by the presence of GERD. Here, we aimed to investigate the alterations of salivary microbiota in GERD patients.

METHODS

We collected clinical information and salivary samples from 60 individuals. All participants underwent combined pH/impedance monitoring measurement and submitted samples for salivary microbiota sequencing. According to acid exposure time and DeMeester score, participants were divided into two groups: GERD + (Group G) and GERD - (Group C).

RESULTS

There was no significant difference in alpha diversity between study groups. Regarding beta diversity, principal coordinate analysis plots indicated that the microbiota composition data of the participants were grouped within partial overlapping clusters. The statistical analysis of the distance matrices was performed using the Adonis test (p = 0.017). Based on linear discriminant analysis effect size, the relative abundances of the phylum Bacteroidetes, class Bacteroidia, order Bacteroidales, family Prevotellaceae, and genus unidentified_Prevotellaceae were enriched in Group G. Compared with Group C, the phylum Actinobacteria, classes unidentified_Actinobacteria and Bacilli, orders Micrococcales and Lactobacillales, families Micrococcaceae and Streptococcaceae, and genuses Rothia and Streptococcus were decreased in Group G. At the genus level, the abundances of Streptococcus and Rothia were negatively correlated with DeMeester score and acid exposure time.

CONCLUSIONS

This study revealed alterations of the salivary microbiota in GERD patients, suggesting that acid reflux changes the oral ecosystem.

Establishment of a Standard Tongue Coating Collection Method for Microbiome Studies

Objective: Recently, researchers have been focusing on characterizing the tongue coating microbiome from patients with digestive tract disease. However, to the best of our knowledge, the tongue coating collection methods have not been standardized until now. This article focuses on bridging this gap by exploring and validating the conditions suitable for the collection of tongue coating samples. Methods: One hundred forty-one healthy subjects were involved in the standardization of the tongue coating collection method. We conducted our standardization experiment by comparing different sampling tools, different preservation solutions, different scraping times, and different storage days with preservation at room temperature. The tongue coating samples from 59 normal individuals were analyzed using 16S ribosomal RNA (rRNA) gene-sequencing technology. The assessment of the quality of extracted DNA was used to verify our established method. We separated the 59 subjects into two groups (aged and younger), and the sequencing results were used to explore the age-related changes in microbiome. Results: Sterile oral swab B is suitable for the collection of tongue coating samples. To obtain a sufficient amount of DNA from a tongue coating sample, we recommend 30 times of tongue coating scraping. Normal saline, phosphate-buffered saline, and commercial preservation solution are all suitable for short-term sample storage (<1 hour). The commercial long-term preservation solution, which stores samples at room temperature (0 hour to 7 days) and can provide for fast commercial transportation, ensures the integrity of the sample DNA as well as the stability of the DNA quality. By using the established method, extracted DNA from all the 59 normal individuals' tongue coating samples passed an appropriate quality bar for microbiome studies. The average value of OD 260/280 is 1.72 ± 0.10; the average total DNA amount is 334.92 ng (±183.81 ng). The bacterial diversity of the tongue coating is increased and the bacterial community composition changes greatly in the NC group (aged normal subjects). Fusobacteriota is found as the dominant bacteria phyla in aged normal subjects with the 16S rRNA gene-sequencing technology. At the genus level, the relative abundance of Fusobacterium, Haemophilus, and Leptotrichia are significantly higher in aged individuals (all p < 0.05), and Neisseria, Streptococcus, and Porphyromonas are significantly higher in younger individuals (all p < 0.05). Conclusion: A participant-friendly tongue coating collection method for microbiome analyses can be established with good reliability and reproducibility. By taking advantage of our established method and 16S rRNA gene sequencing, significant differences were found in diversity and composition of tongue coating microbiota between aged and younger individuals, which contributes to a better understanding of the age-related composition of tongue coating microbiota.

Development of a tongue image-based machine learning tool for the diagnosis of gastric cancer: a prospective multicentre clinical cohort study

BACKGROUND

Tongue images (the colour, size and shape of the tongue and the colour, thickness and moisture content of the tongue coating), reflecting the health state of the whole body according to the theory of traditional Chinese medicine (TCM), have been widely used in China for thousands of years. Herein, we investigated the value of tongue images and the tongue coating microbiome in the diagnosis of gastric cancer (GC).

METHODS

From May 2020 to January 2021, we simultaneously collected tongue images and tongue coating samples from 328 patients with GC (all newly diagnosed with GC) and 304 non-gastric cancer (NGC) participants in China, and 16 S rDNA was used to characterize the microbiome of the tongue coating samples. Then, artificial intelligence (AI) deep learning models were established to evaluate the value of tongue images and the tongue coating microbiome in the diagnosis of GC. Considering that tongue imaging is more convenient and economical as a diagnostic tool, we further conducted a prospective multicentre clinical study from May 2020 to March 2022 in China and recruited 937 patients with GC and 1911 participants with NGC from 10 centres across China to further evaluate the role of tongue images in the diagnosis of GC. Moreover, we verified this approach in another independent external validation cohort that included 294 patients with GC and 521 participants with NGC from 7 centres. This study is registered at ClinicalTrials.gov, NCT01090362.

FINDINGS

For the first time, we found that both tongue images and the tongue coating microbiome can be used as tools for the diagnosis of GC, and the area under the curve (AUC) value of the tongue image-based diagnostic model was 0.89. The AUC values of the tongue coating microbiome-based model reached 0.94 using genus data and 0.95 using species data. The results of the prospective multicentre clinical study showed that the AUC values of the three tongue image-based models for GCs reached 0.88-0.92 in the internal verification and 0.83-0.88 in the independent external verification, which were significantly superior to the combination of eight blood biomarkers.

INTERPRETATION

Our results suggest that tongue images can be used as a stable method for GC diagnosis and are significantly superior to conventional blood biomarkers. The three kinds of tongue image-based AI deep learning diagnostic models that we developed can be used to adequately distinguish patients with GC from participants with NGC, even early GC and precancerous lesions, such as atrophic gastritis (AG).

FUNDING

The National Key R&D Program of China (2021YFA0910100), Program of Zhejiang Provincial TCM Sci-tech Plan (2018ZY006), Medical Science and Technology Project of Zhejiang Province (2022KY114, WKJ-ZJ-2104), Zhejiang Provincial Research Center for Upper Gastrointestinal Tract Cancer (JBZX-202006), Natural Science Foundation of Zhejiang Province (HDMY22H160008), Science and Technology Projects of Zhejiang Province (2019C03049), National Natural Science Foundation of China (82074245, 81973634, 82204828), and Chinese Postdoctoral Science Foundation (2022M713203).

A survey of artificial intelligence in tongue image for disease diagnosis and syndrome differentiation

The rapid development of artificial intelligence technology has gradually extended from the general field to all walks of life, and intelligent tongue diagnosis is the product of a miraculous connection between this new discipline and traditional disciplines. We reviewed the deep learning methods and machine learning applied in tongue image analysis that have been studied in the last 5 years, focusing on tongue image calibration, detection, segmentation, and classification of diseases, syndromes, and symptoms/signs. Introducing technical evolutions or emerging technologies were applied in tongue image analysis; as we have noticed, attention mechanism, multiscale features, and prior knowledge were successfully applied in it, and we emphasized the value of combining deep learning with traditional methods. We also pointed out two major problems concerned with data set construction and the low reliability of performance evaluation that exist in this field based on the basic essence of tongue diagnosis in traditional Chinese medicine. Finally, a perspective on the future of intelligent tongue diagnosis was presented; we believe that the self-supervised method, multimodal information fusion, and the study of tongue pathology will have great research significance.

Species composition and overall diversity are significantly correlated between the tongue coating and gastric fluid microbiomes in gastritis patients

BACKGROUND

In traditional Chinese medicine, it is believed that the "tongue coating is produced by fumigation of stomach gas", and that tongue coating can reflect the health status of humans, especially stomach health. Therefore, studying the relationship between the microbiome of the tongue coating and the gastric fluid is of great significance for understanding the biological basis of tongue diagnosis.

METHODS

This paper detected the microbiomes of the tongue coating and the gastric fluid in 35 gastritis patients using metagenomic sequencing technology, systematically constructed the microbial atlas of tongue coating and gastric juice, and first described the similar characteristics between the two sites.

RESULTS

There was a significant correlation between tongue coating and gastric juice in terms of microbial species composition and overall diversity. In terms of species composition, it was found that the two sites were dominated by five phyla, namely, Actinobacteria, Bacteroidetes, Firmicutes, Fusobacteria and Proteobacteria, and that most of the gastric microbial species could be detected from the patient's own tongue coating. In terms of overall diversity, a significant correlation was found between the alpha diversity of the tongue coating microbiome and the gastric juice microbiome. Furthermore, in terms of abundance, 4 classes, 2 orders, 4 families, 18 genera and 46 species were found to significantly correlate between the tongue coating and the gastric fluid.

CONCLUSIONS

The results provide microbiome-based scientific evidence for tongue diagnosis, and offer a new perspective for understanding the biological basis of tongue diagnosis.

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.

Tongue-coating microbiome as a cancer predictor: A scoping review

OBJECTIVE

The tongue microbiome has emerged as a non-invasive diagnostic and tracking prognostic tool in the detection of diseases mainly cancer. This scoping review aimed to identify the association between tongue microbiome and pre-cancer or cancer lesions.

DESIGN

A comprehensive electronic database search including PubMed, Web of Science, and Scopus was undertaken up to March 2021, without language or date restrictions. This review was conducted following the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) guideline. All observational studies that compared microbial community on the dorsal surface of the tongue between cancer or precancerous cases and healthy controls using NGS techniques were included.

RESULTS

Of 274 records identified, nine studies were eligible to be included. Despite the inconsistent observations in terms of diversity and richness, most studies reported alteration in bacterial communities between pre-cancer or cancer cases and control groups. The bacterial profile among cases was so far correlated at the phylum level with a noticeable diverse degree at the genus level. The majority of included studies reported a higher abundance of certain kinds of microorganisms as compared to healthy participants including Firmicutes, Fusobacteria and Actinobacteria at phyla level as well as Streptococcus, Actinomyces, Leptotrichia, Campylobacter, and Fusobacterium at the genus level.

CONCLUSION

The alteration of the tongue microbial community has been associated with several diseases mainly cancer. So, the tongue microbiome may serve as a promising diagnostic tool or as a long-term monitor in precancerous or cancer cases.

Variations of tongue coating microbiota in children with Henoch-Schönlein purpura nephritis

BACKGROUND

Variations in the oral microbiota have been significantly correlated with the progress of autoimmune diseases, such as immunoglobulin A nephropathy and Henoch-Schönlein purpura (HSP). However, there is no report outlining the character of tongue coating microbiota variations in children with Henoch-Schönlein purpura nephritis (HSPN).

METHOD

A total of 20 children with HSPN and 14 healthy controls were recruited for this research. Tongue coating samples of two groups were collected for 16S rRNA gene sequencing. The diversity, principal component analysis (PCA), nonmetric multidimensional scaling (NMDS), partial least squares discriminant analysis (PLS-DA), and linear discriminant analysis (LDA) effect size (LEfSe) were performed. Microbial function was assessed using the PICRUST.

RESULTS

The ACE and Chao indices were greatly lower in the HSPN group than in the HG (P = 0.001). The Shannon and Simpson indices were dramatically reduced in children with HSPN compared with those in the healthy controls (P = 0.005). Bacteroidales, Selenomonadales, Lactobacillales, Fusobacteriales, Neisseriales, and Actinomycetales composed more than 80% of all sequences, while Bacteroidales was the most generous order in both groups. PCA, NMDS and PLS-DA showed a marked difference between the control and HSPN groups. LEfSe analysis showed alteration of tongue coating microbiota in the HSPN group. There were 30 metabolic functions significantly differed between the two groups.

CONCLUSIONS

Children with HSPN have substantially various tongue coating microbiota compared to healthy controls. Even though this research does not indicate causality, it is beneficial to enhance the possibility for coming microbial-based treatments to enhance the clinical effects of HSPN in children.

Oral, Tongue-Coating Microbiota, and Metabolic Disorders: A Novel Area of Interactive Research

Interactions between colonizing microbiota and the host have been fully confirmed, among which the tongue-coating microbiota have a moderate rate of renewal and disease sensitivity and are easily obtained, making them an ideal research subject. Oral microbiota disorders are related to diabetes, obesity, cardiovascular disease, cancer, and other systemic diseases. As an important part of the oral cavity, tongue-coating microbiota can promote gastritis and digestive system tumors, affecting the occurrence and development of multiple chronic diseases. Common risk factors include diet, age, and immune status, among others. Metabolic regulatory mechanisms may be similar between the tongue and gut microbiota. Tongue-coating microbiota can be transferred to the respiratory or digestive tract and create a new balance with local microorganisms, together with the host epithelial cells forming a biological barrier. This barrier is involved in the production and circulation of nitric oxide (NO) and the function of taste receptors, forming the oral-gut-brain axis (similar to the gut-brain axis). At present, the disease model and mechanism of tongue-coating microbiota affecting metabolism have not been widely studied, but they have tremendous potential.

Task-Coupling Elastic Learning for Physical Sign-based Medical Image Classification

Physical signs of patients indicate crucial evidence for diagnosing both location and nature of the disease, where there is a sequential relationship between the two tasks. Thus their joint learning can utilize intrinsic association by transferring related knowledge across relevant tasks. Choosing the right time to transfer is a critical problem for joint learning. However, how to dynamically adjust when tasks interact to capture the right time for transferring related knowledge is still an open issue. To this end, we propose a Task-Coupling Elastic Learning (TCEL) framework to model the task relatedness for classifying disease-location and disease-nature based on physical sign images. The main idea is to dynamically transfer relevant knowledge by progressively shifting task-coupling from loose to tight during the multi-stage training. In the early stage of training, we relax the constraints of modeling relations to focus more in learning the generic task-common features. In the later stage, the semantic guidance will be strengthened to learn the task-specific features. Specifically, a dynamic sequential module (DSM) is proposed to explicitly model the sequential relationship and enable multi-stage training. Moreover, to address the side effect of DSM, a new loss regularization is proposed. The extensive experiments on these two clinical datasets show the superiority of the proposed method over the baselines, and demonstrate the effectiveness of the proposed task-coupling elastic mechanism.

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.

Does the Microbiome Affect the Outcome of Renal Transplantation?

The role of the human microbiome in health and disease is becoming increasingly apparent. Emerging evidence suggests that the microbiome is affected by solid organ transplantation. Kidney transplantation is the gold standard treatment for End-Stage Renal Disease (ESRD), the advanced stage of Chronic Kidney Disease (CKD). The question of how ESRD and transplantation affect the microbiome and vice versa includes how the microbiome is affected by increased concentrations of toxins such as urea and creatinine (which are elevated in ESRD), whether restoration of renal function following transplantation alters the composition of the microbiome, and the impact of lifelong administration of immunosuppressive drugs on the microbiome. Changes in microbiome composition and activity have been reported in ESRD and in therapeutic immunosuppression, but the effect on the outcome of transplantation is not well-understood. Here, we consider the current evidence that changes in kidney function and immunosuppression following transplantation influence the oral, gut, and urinary microbiomes in kidney transplant patients. The potential for changes in these microbiomes to lead to disease, systemic inflammation, or rejection of the organ itself is discussed, along with the possibility that restoration of kidney function might re-establish orthobiosis.

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.

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.

13C-DNA-SIP Distinguishes the Prokaryotic Community That Metabolizes Soybean Residues Produced Under Different CO2 Concentrations

The amendment of crop residues produced under elevated CO₂ (eCO₂) may alter soil microbial community structure and their functions on residue decomposition and carbon (C) cycling in soil. The key to understanding this process is to elucidate the structure of prokaryotic communities that metabolize crop residues derived from eCO₂. A soil incubation experiment was conducted to explore the response of soil microbial community to the amendment of ¹³C-labeled soybean residues produced under ambient CO₂ (aCO₂) and eCO_2. The residues were applied to a Mollisol, followed by ¹³C-DNA stable isotope probing (SIP) and Illumina sequencing on soil prokaryotic community over time. The structure of residue-metabolizing community differed in response to the amendment of eCO₂- and aCO₂-derived residues after 28 days of incubation. In particular, genera Actinomadura, Nocardia, Non-omuraea, and Shimazuella were the dominant members of the residue-metabolizing bacteria, which contributed to this difference. The relative abundances of genera Actinomadura, Nocardia and Shimazuella were 118–144%, 71–113%, and 2–4-fold higher in the Mollisol amended with aCO₂-derived than eCO₂-derived residue. In contrast, the relative abundance of Non-omuraea was 87–90% greater in the eCO₂-residue treatment. However, during the incubation period, there was no difference between the two residue treatments in the community structure as a whole without SIP. These results implied that a pioneering prokaryotic community metabolized the residue initially prior to the entire community. Those bacteria genera being inhibited with the amendment of the eCO₂-derived residue, compared to aCO₂-derived residue, were likely preferential to metabolize recalcitrant C, which might be associated with changes of chemical composition of the residue under eCO₂.

Beyond Head and Neck Cancer: The Relationship Between Oral Microbiota and Tumour Development in Distant Organs

An altered oral microbiota has been linked with the development of several oral diseases, such as dental caries, periodontal disease, and oral stomatitis. Moreover, poor oral health has been linked to head and neck cancer, particularly oral cancer. In recent years a growing number of studies indicate that oral microbiota could be involved in the development of primary tumours outside of head and neck region. The aim of this article is to review the recent studies based on high-throughput technology to present evidences of a relationship between oral microbiota and "non-head and neck tumours." Oral dysbiosis seem to be more pronounced in patients with tumours of gastrointestinal tract, in particular oesophageal, gastric, pancreatic, and colorectal cancers, paving the way for developing specific oral microbiota test to allow early cancer detection. Regarding other tumour types, the results are promising but highly preliminary and still debated. Currently, there are several factors that limit the generalization of the results, such as the small sample size, the lack of adequate clinical information about patients, the different sequencing techniques used, and biological sample heterogeneity. Although only at the beginning, the analysis of oral microbiota could be the next step in the evolution of cancer therapy and will help clinicians to develop individualised approaches to cancer prevention and treatment.

Oral microbiota and gastrointestinal cancer

The microbiota inhabiting the oral cavity is a complex ecosystem and responsible for resisting pathogens, maintaining homeostasis, and modulating the immune system. Some components of the oral microbiota contribute to the etiology of some oral diseases. Accumulating evidence suggests that the human oral microbiota is implicated in the development and progression of gastrointestinal cancer. In this review, we described the current understanding of possible roles and mechanisms of oral microbiota in the gastrointestinal cancers studied to date. The perspectives for oral microbiota as the biomarkers for early detection and new therapeutic targets were also discussed.

Neural network analysis of Chinese herbal medicine prescriptions for patients with colorectal cancer

Traditional Chinese Medicine (TCM) is an experiential form of medicine with a history dating back thousands of years. The present study aimed to utilize neural network analysis to examine specific prescriptions for colorectal cancer (CRC) in clinical practice to arrive at the most effective prescription strategy. The study analyzed the data of 261 CRC cases recruited from a total of 141,962 cases of renowned veteran TCM doctors collected from datasets of both the DeepMedic software and TCM cancer treatment books. The DeepMedic software was applied to normalize the symptoms/signs and Chinese herbal medicine (CHM) prescriptions using standardized terminologies. Over 20 percent of CRC patients demonstrated symptoms of poor appetite, fatigue, loose stool, and abdominal pain. By analyzing the prescription patterns of CHM, we found that Atractylodes macrocephala (Bai-zhu) and Poria (Fu-ling) were the most commonly prescribed single herbs identified through analysis of medical records, and supported by the neural network analysis; although there was a slight difference in the sequential order. The study revealed an 81.9% degree of similarity of CHM prescriptions between the medical records and the neural network suggestions. The patterns of nourishing Qi and eliminating dampness were the most common goals of clinical prescriptions, which corresponds with treatments of CRC patients in clinical practice. This is the first study to employ machine learning, specifically neural network analytics to support TCM clinical diagnoses and prescriptions. The DeepMedic software may be used to deliver accurate TCM diagnoses and suggest prescriptions to treat CRC.

Microbial biomarkers of common tongue coatings in patients with gastric cancer

PURPOSE

The study aims to explore the characteristic microorganisms of the common tongue coatings in patients with gastric cancer (GC).

METHODS

A total of 115 GC patients were assigned to four groups: White-thin coating (W-thin) group, White-thick coating (W-thick) group, Yellow-thin coating (Y-thin) group and Yellow-thick coating (Y-thick) group. Thirty-five healthy volunteers with White-thin coating were recruit as controls. High-throughput sequencing was used to describe the microbial community of the tongue coatings based on 16S rRNA and 18S rRNA genes. Multi-factors statistical analysis was carried out to present the microbial biomarkers of the tongue coating in GC patients.

RESULTS

At bacterial phylum level, Saccharibacteria had higher relative abundance in W-thick group than W-thin group, Proteobacteria was more abundant in W-thin group than Y-thick group and less abundant in Y-thick group than Y-thin group. At fungal genus level, Guehomyces and Aspergillus presented to be significantly different among the common tongue coatings. Forteen significantly increased taxa were sorted out as the microbial biomarkers of common tongue coatings by LEfSe and ROC analysis. At species level, bacterial Capnocytophaga leadbetteri and fungal Ampelomyces_sp_IRAN_1 may be the potential biomarkers of W-thin coating, four bacterial species (Megasphaera micronuciformis, Selenomonas sputigena ATCC 35185, Acinetobacter ursingii, Prevotella maculosa) may be the potential biomarkers of W-thick coating. In general, the white coatings held more complex commensal relationship than the yellow coatings.

CONCLUSION

The common tongue coating owned characteristic microorganisms and special commensal relationship in the GC patients.

Biodegradation of methamphetamine and ketamine in aquatic ecosystem and associated shift in bacterial community

Methamphetamine (METH) and ketamine (KET) are widely detected in surface waters and thus may pose threat to aquatic organisms. However, their degradation in aquatic systems and the effects on bacterial community were unknown. The present study investigated the biodegradation process of METH and KET in river waters and sediments. Three microcosms were examined over 40-days' incubation under (i) aerobic and illumination conditions, (ii) anaerobic condition exposed to light, (iii) anaerobic-dark condition. Statistically significant biodegradation of METH and KET (1 mg L^-1) was observed in all treatments. The half-lives under the examined conditions indicate that the two drugs were refractory in aquatic environment. Moreover, there were no pronounced absorption and photolysis observed in this work. Illumina MiSeq sequencing analysis revealed that Methylophilaceae, Saprospiraceae, WCHB1-69, Desulfobulbaceae, Porphyromonadaceae, FamilyXI, Peptococcaceae, and Rhizobiaceae were the predominant candidatus families during KET and METH biodegradation, and the preponderance would impair other microorganisms' prosperity since them were scarcely detected in the wild. Meanwhile, canonical correlation analysis (CCA) indicates that METH as an environmental factor may affect bacterial community structure in field water samples.

Biological films adhering to the oral soft tissues: Structure, composition, and potential impact on taste perception

The role of free-flowing saliva in taste perception is increasingly recognized, but saliva is also present in the mouth as films intimately associated to soft or hard tissues. On mucosal surfaces, particularly on the tongue, the structure and composition of such films (including its microbial constitutive part) may play a particular role in the sense of taste due to their proximity with the taste anatomical structures. This review compiles the current knowledge on the structure of biological films adhering to oral mucosae and on their biochemical and microbiological composition, before presenting possible implications for taste perception. PRACTICAL APPLICATIONS: The understanding of the role of oral biological films on taste perception may provide new avenues of research and development for the industry or academia interested broadly in chemosensation.

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.

Microbial association with the dynamics of particulate organic carbon in response to the amendment of elevated CO2-derived wheat residue into a Mollisol

As the chemical quality of crop residue is likely to be affected by elevated CO₂ (eCO₂), residue amendments may influence soil organic carbon (SOC) sequestration. However, in Mollisols, the dynamics of the SOC fractions in response to amendment with wheat residue produced under eCO₂ and the corresponding microbial community composition remain unknown. Such investigation is essential to residue management, which affects the soil quality and productivity of future farming systems. To narrow this knowledge gap, ¹³C-labeled shoot and root residue derived from ambient CO₂ (aCO₂) or eCO₂ were amended into Mollisols and incubated for 200days. The soil was sampled during the incubation period to determine the residue-C retained in the three SOC fractions, i.e., coarse intra-aggregate particulate organic C (coarse iPOC), fine iPOC and mineral-associated organic C (MOC). The soil bacterial community was assessed using a MiSeq sequencing instrument. The results showed that the increase in SOC concentrations attributable to the application of the wheat residue primarily occurred in the coarse iPOC fraction. Compared with the aCO₂-derived shoot residue, the amendment of eCO₂-derived shoot residue resulted in greater SOC concentrations, whereas no significant differences (P>0.05) were observed between the aCO₂- and eCO₂-derived roots. Principal coordinates analysis (PCoA) showed that the residue amendment significantly (P≤0.05) altered the bacterial community composition compared with the non-residue amendment. Additionally, the bacterial community in the aCO₂-derived shoot treatment differed from those in the other residue treatments until day 200 of the incubation period. The eCO₂-derived shoot treatment significantly increased (P≤0.05) the relative abundances of the genera Acidobacteriaceae_(Subgroup_1)_uncultured, Bryobacter, Candidatus_Solibacter, Gemmatimonas and Nitrosomonadaceae_uncultured, whereas the opposite trend was observed in Nonomuraea, Actinomadura, Streptomyces and Arthrobacter (P≤0.05). These results imply that the response of the microbial community to the eCO₂-derived shoot treatment is associated with its contribution to the POC fractions.

Tannerella forsythia and coating color on the tongue dorsum, and fatty food liking associate with fat accumulation and insulin resistance in adult catch-up fat

BACKGROUND/OBJECTIVES

We aimed to determine the alteration of Tannerella forsythia and coating color on the dorsal tongue, and fatty food liking in catch-up fat in adult (CUFA), as well as the probable associations between fat accumulation, insulin resistance (IR) and these changes.

SUBJECTS/METHODS

T. forsythia on the tongue dorsum, fatty food liking, fat accumulation and insulin sensitivity were investigated in CUFA humans and rats, and tongue-coating color was observed in CUFA individuals. We further determined the changes of fatty food liking, fat accumulation and IR in T. forsythia-infected rodents by oral lavage.

RESULTS

Increases in fat accumulation, IR, percentage of subjects with yellow tongue coating and that with T. forsythia detected were observed in CUFA individuals. Additionally, the fat ranking scores were significantly lower and the hedonic ratings of low-fat options of sampled food were lower, while the ratings of high-fat options were remarkably higher in CUFA subjects. Additionally, T. forsythia level elevated in CUFA rats, and fatty food liking, fat accumulation and IR increased in CUFA and T. forsythia-infected animals, with the increases in T. forsythia infection and fatty food liking preceding the occurrence of fat accumulation and IR.

CONCLUSIONS

T. forsythia and yellow coating on the dorsal tongue and fatty food liking associate fat accumulation and IR in CUFA. Moreover, we tentatively put forward that T. forsythia, which is very important in yellow tongue-coating microbiota, and its consequent increases in fatty food liking, might be crucial in the development of fat accumulation and IR in CUFA.

Evaluation of the Bacterial Diversity in the Human Tongue Coating Based on Genus-Specific Primers for 16S rRNA Sequencing

The characteristics of tongue coating are very important symbols for disease diagnosis in traditional Chinese medicine (TCM) theory. As a habitat of oral microbiota, bacteria on the tongue dorsum have been proved to be the cause of many oral diseases. The high-throughput next-generation sequencing (NGS) platforms have been widely applied in the analysis of bacterial 16S rRNA gene. We developed a methodology based on genus-specific multiprimer amplification and ligation-based sequencing for microbiota analysis. In order to validate the efficiency of the approach, we thoroughly analyzed six tongue coating samples from lung cancer patients with different TCM types, and more than 600 genera of bacteria were detected by this platform. The results showed that ligation-based parallel sequencing combined with enzyme digestion and multiamplification could expand the effective length of sequencing reads and could be applied in the microbiota analysis.

miR-203 Expression in Exfoliated Cells of Tongue Coating Represents a Sensitive and Specific Biomarker of Gastroesophageal Reflux Disease

Background and Aim. MicroRNAs (miRNAs) have been implicated in the pathophysiology of numerous human diseases including gastroesophageal reflux disease (GERD). The objective of this study was to investigate the miRNA expression of exfoliated cells of the tongue in patients with GERD versus healthy controls (Ctrls). Methods. Using quantitative reverse-transcription PCR (qRT-PCR), expression levels of six candidate miRNAs (miR-143, miR-145, miR-192, miR-194, miR-203, and miR-205) were examined across a discovery cohort of patients with GERD (n = 24) versus Ctrls (n = 24). These findings were confirmed across a validation cohort (GERD, n = 142; Ctrls, n = 48). Differences in miRNA expression levels were evaluated using the Mann-Whitney U test while the specificity and sensitivity were obtained using receiver-operator characteristic (ROC) curves. Results. miR-203 was significantly downregulated in GERD patients as compared to Ctrls (P < 0.0001) with ROC curve of 0.94 (95% CI: 0.90-0.97). The sensitivity and the specificity of miR-203 were 91.7% and 87.3%, respectively, in the GERD and Ctrls. These results suggest that miR-203 may be a useful diagnostic marker for discriminating GERD from Ctrls. Conclusions. miR-203 testing may assist in the diagnosis of patients with symptoms suggestive of GERD.

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.