Discrimination of TCM constitutions by biochemical and routine urine indexes

Objective:To investigate whether the specific traditional Chinese medicine(TCM)constitution of individuals can be defined by certain biological indexes instead of answering the questionnaire,and to explore the possibility of discriminating nine TCM constitutions from each other simultaneously using biological indexes.Methods:Blood and urine samples from 152 individuals with nine TCM constitutions were collected,and the related biological indexes were analyzed combining ANOVA,multiple comparison,discriminant analysis,and support vector machine.Results:We found that 4 out of 24 blood routine indexes,7 out of 10 urine routine indexes,and 12 out of 32 biochemical indexes showed differences among the constitutions.High-sensitivity C-reactive protein,apolipoprotein A1,and alkaline phosphatase were potential candidates for screening out individuals with unbalanced constitutions.Combining uric acid,high-density lipoprotein,apolipoprotein A1,creatine kinase,total protein,aspartate aminotransferase,total bile acid,dehydrogenase,sodium,and calcium levels had the potential to directly distinguish the nine TCM constitutions from each other.Among these indexes,the highest ratio of discriminant analysis between two constitutions was 95.5%,while the lowest was 66.1%.Conclusion:Our results suggest that some biochemical and urine indexes are related to various TCM constitutions,and thus they have the potential to be used for TCM constitution classification.

Classifying Chinese Medicine Constitution Using Multimodal Deep-Learning Model

Objective:To develop a multimodal deep-learning model for classifying Chinese medicine constitution,i.e.,the balanced and unbalanced constitutions,based on inspection of tongue and face images,pulse waves from palpation,and health information from a total of 540 subjects.Methods:This study data consisted of tongue and face images,pulse waves obtained by palpation,and health information,including personal information,life habits,medical history,and current symptoms,from 540 subjects(202 males and 338 females).Convolutional neural networks,recurrent neural networks,and fully connected neural networks were used to extract deep features from the data.Feature fusion and decision fusion models were constructed for the multimodal data.Results:The optimal models for tongue and face images,pulse waves and health information were ResNet18,Gate Recurrent Unit,and entity embedding,respectively.Feature fusion was superior to decision fusion.The multimodal analysis revealed that multimodal data compensated for the loss of information from a single mode,resulting in improved classification performance.Conclusions:Multimodal data fusion can supplement single model information and improve classification performance.Our research underscores the effectiveness of multimodal deep learning technology to identify body constitution for modernizing and improving the intelligent application of Chinese medicine.

Expression profiling-based clustering of healthy subjects recapitulates classifications defined by clinical observation in Chinese medicine

Differences between healthy subjects and associated disease risks are of substantial interest in clinical medicine. Based on clinical presentations, Traditional Chinese Medicine （TCM） classifies healthy people into nine constitutions： Balanced, Qi, Yang or Yin deficiency, Phlegm-dampness, Damp-heat, Blood stasis, Qi stagnation, and Inherited special constitutions. In particular, Yang and Yin deficiency constitutions exhibit cold and heat aversion, respectively. However, the intrinsic molecular characteristics of unbal- anced phenotypes remain unclear. To determine whether gene expression-based clustering can reca- pitulate TCM-based classification, peripheral blood mononudear cells （PBMCs） were collected from Chinese Han individuals with Yang/Yin deficiency （n = 12 each） and Balanced （n = 8） constitutions, and global gene expression profiles were determined using the Affymetrix HC-UI33A Plus 2.0 array. Notably, we found that gene expression-based classifications reflected distinct TCM-based subtypes. Consistent with the clinical observation that subjects with Yang deficiency tend toward obesity, series-clustering analysis detected several key lipid metabolic genes （diacylglycerol acyltransferase （DGAT2）, acyl-CoA synthetase （ACSL1）, and ATP-hinding cassette subfamily A member 1 （ABCAI）） to be down- and up- regulated in Yin and Yang deficiency constitutions, respectively. Our findings suggest that Yin]Yang deficiency and Balanced constitutions are unique entities in their mRNA expression profiles. Moreover, the distinct physical and clinical characteristics of each unbalanced constitution can be explained, in part, by specific gene expression signatures.

Construction and optimization of traditional Chinese medicine constitution prediction models based on deep learning

Objective To cater to the demands for personalized health services from a deep learning per-spective by investigating the characteristics of traditional Chinese medicine(TCM)constitu-tion data and constructing models to explore new prediction methods.Methods Data from students at Chengdu University of Traditional Chinese Medicine were collected and organized according to the 24 solar terms from January 21,2020,to April 6,2022.The data were used to identify nine TCM constitutions,including balanced constitution,Qi deficiency constitution,Yang deficiency constitution,Yin deficiency constitution,phlegm dampness constitution,damp heat constitution,stagnant blood constitution,Qi stagnation constitution,and specific-inherited predisposition constitution.Deep learning algorithms were employed to construct multi-layer perceptron(MLP),long short-term memory(LSTM),and deep belief network(DBN)models for the prediction of TCM constitutions based on the nine constitution types.To optimize these TCM constitution prediction models,this study in-troduced the attention mechanism(AM),grey wolf optimizer(GWO),and particle swarm op-timization(PSO).The models’performance was evaluated before and after optimization us-ing the F1-score,accuracy,precision,and recall.Results The research analyzed a total of 31655 pieces of data.(i)Before optimization,the MLP model achieved more than 90%prediction accuracy for all constitution types except the balanced and Qi deficiency constitutions.The LSTM model's prediction accuracies exceeded 60%,indicating that their potential in TCM constitutional prediction may not have been fully realized due to the absence of pronounced temporal features in the data.Regarding the DBN model,the binary classification analysis showed that,apart from slightly underperforming in predicting the Qi deficiency constitution and damp heat constitution,with accuracies of 65%and 60%,respectively.The DBN model demonstrated considerable discriminative power for other constitution types,achieving prediction accuracy rates and area under the receiver op-erating characteristic(ROC)curve(AUC)values exceeding 70%and 0.78,respectively.This indicates that while the model possesses a certain level of constitutional differentiation abili-ty,it encounters limitations in processing specific constitutional features,leaving room for further improvement in its performance.For multi-class classification problem,the DBN model’s prediction accuracy rate fell short of 50%.(ii)After optimization,the LSTM model,enhanced with the AM,typically achieved a prediction accuracy rate above 75%,with lower performance for the Qi deficiency constitution,stagnant blood constitution,and Qi stagna-tion constitution.The GWO-optimized DBN model for multi-class classification showed an increased prediction accuracy rate of 56%,while the PSO-optimized model had a decreased accuracy rate to 37%.The GWO-PSO-DBN model,optimized with both algorithms,demon-strated an improved prediction accuracy rate of 54%.Conclusion This study constructed MLP,LSTM,and DBN models for predicting TCM consti-tution and improved them based on different optimisation algorithms.The results showed that the MLP model performs well,the LSTM and DBN models were effective in prediction but with certain limitations.This study also provided a new technology reference for the es-tablishment and optimisation strategies of TCM constitution prediction models,and a novel idea for the treatment of non-disease.

Enlightenment about using TCM constitutions for individualized medicine and construction of Chinese-style precision medicine:research progress with TCM constitutions

TCM constitution is a new branch of TCM.It provides enlightenment on individualized medicine,including the development of new models of individualized research based on nine constitutions,the acquisition of comprehensive health information for individuals,and establishment of a consistent individualized diagnosis and treatment system.Further,we propose a Chinesestyle“precision medicine”based on individualization using the TCM constitutions.

Study on Insulin Resistance and Genetic Polymorphisms in Essential Hypertension Patients of Two Different Kinds of TCM Constitution

Objective： To investigate the relationship of insulin resistance and the polymorphisms of insulin receptor-related genes in essential hypertension patients of two different kinds of TCM constitution. Methods： Oral glucose tolerance test （OGTT） and insulin release test （InRT） were conducted in 217 essential hypertensive patients of either sluggish meticulous （SM） constitution （139 cases） or prosperous impetuous （PI） constitution （78 cases）, and the polymorphism of three genes, including insulin-like growth factor-1 receptor （IGF-1R）, insulin receptor substrate-1 （IRS-1） and 2 （IRS-2） genes were detected. Results： （1） OGTT, InRT and insulin resistance index （Homa-IR） were higher and insulin sensitive index （ISI） was lower in the patients of SM constitution than those in patients of PI constitution. （2） Significant difference of ISI and Homa-IR was shown in patients of both constitutions with genotype G of the 3 genes. Conclusion： Decrease of insulin sensitivity and increase of insulin resistance are more obvious in hypertensive patients with genotype G of the 3 genes of SM constitution than in those of PI constitution. Therefore, the difference in constitution might be one of the genetic characteristics for insulin resistance in hypertensive patients.