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.

Deciphering the Pharmacological Mechanisms of Ma Xing Shi Gan Decoction against COVID-19 through Integrating Network Pharmacology and Experimental Exploration.

The outbreak of new infectious pneumonia caused by SARS-CoV-2 has posed a significant threat to public health, but specific medicines and vaccines are still being developed. Traditional Chinese medicine (TCM) has thousands of years of experience in facing the epidemic disease, such as influenza and viral pneumonia. In this study, we revealed the efficacy and pharmacological mechanism of Ma Xing Shi Gan (MXSG) Decoction against COVID-19. First, we used liquid chromatography-electrospray ionization tandem mass spectrometry (LC-ESI-MS/MS) to analyze the chemical components in MXSG and identified a total of 97 components from MXSG. Then, the intervention pathway of MXSG based on these components was analyzed with network pharmacology, and it was found that the pathways related to the virus infection process were enriched in some of MXSG component targets. Simultaneously, through literature research, it was preliminarily determined that MXSG, which is an essential prescription for treating COVID-19, shared the feature of antiviral, improving clinical symptoms, regulating immune inflammation, and inhibiting lung injury. The regulatory mechanisms associated with its treatment of COVID-19 were proposed. That MXSG might directly inhibit the adsorption and replication of SARS-CoV-2 at the viral entry step. Besides, MXSG might play a critical role in inflammation and immune regulatory, that is, to prevent cytokine storm and relieve lung injury through toll-like receptors signaling pathway. Next, in this study, the regulatory effect of MXSG on inflammatory lung injury was validated through transcriptome results. In summary, MXSG is a relatively active and safe treatment for influenza and viral pneumonia, and its therapeutic effect may be attributed to its antiviral and anti-inflammatory effects.

Treating Different Diseases With the Same Method-A Traditional Chinese Medicine Concept Analyzed for Its Biological Basis.

INTRODUCTION: The fundamental theory of traditional Chinese medicine (TCM) implies that when different diseases have the same pathogen, the syndromes of these individual diseases will be the same. "Treating different diseases with the same method" is a TCM principle suggesting that when different diseases have similar pathological changes during different stages of their development, the same method of treatment can be applied. Our study aims to analyze the concept "treating different diseases with the same method" from a molecular perspective, in order to clarify its biological basis and to objectively standardize future TCM syndrome research. OBJECTIVE: The TCM syndromes Qi deficiency and blood stasis have similar pathogenesis in relation to coronary heart disease (CHD) and stroke. We aim to use big data technology and complex network theory to mine the genes specifically relevant to these TCM syndromes. This study aims to explore the correlation between the biological indicators of CHD and stroke from a scientific perspective. METHODS: Mining the relevant neuroendocrine-immune (NEI) genes by means of gene entity recognition, complex network construction, network integration, and decomposition to categorize relevant syndrome terms and establish a digital dictionary of gene specifically related to individual diseases. We analyzed the biological basis of "treating different diseases with the same method" from a molecular level using the TCMIP v2.0 platform in order to categorize the TCM syndromes most relevant to CHD and stroke. RESULTS: We found 46 genes were involved in the TCM syndromes of Qi deficiency and blood stasis of CHD and stroke. The same genes and their molecular mechanism also appeared to be in close relation to inflammatory response, apoptosis, and proliferation. CONCLUSION: By using information extraction and complex network technology, we discovered the biological indicators of the TCM syndromes Qi deficiency and blood stasis of CHD and stroke. In the era of big data, our results can provide a new method for the researchers of TCM syndrome differentiation, as well as an effective and specific methodology for standardization of TCM.

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.