Traditional Chinese Medicine Syndrome Classification Research Articles

HHO optimized support vector machine classifier for traditional Chinese medicine syndrome differentiation of diabetic retinopathy.

To develop a classifier for traditional Chinese medicine (TCM) syndrome differentiation of diabetic retinopathy (DR), using optimized machine learning algorithms, which can provide the basis for TCM objective and intelligent syndrome differentiation. Collated data on real-world DR cases were collected. A variety of machine learning methods were used to construct TCM syndrome classification model, and the best performance was selected as the basic model. Genetic Algorithm (GA) was used for feature selection to obtain the optimal feature combination. Harris Hawk Optimization (HHO) was used for parameter optimization, and a classification model based on feature selection and parameter optimization was constructed. The performance of the model was compared with other optimization algorithms. The models were evaluated with accuracy, precision, recall, and F1 score as indicators. Data on 970 cases that met screening requirements were collected. Support Vector Machine (SVM) was the best basic classification model. The accuracy rate of the model was 82.05%, the precision rate was 82.34%, the recall rate was 81.81%, and the F1 value was 81.76%. After GA screening, the optimal feature combination contained 37 feature values, which was consistent with TCM clinical practice. The model based on optimal combination and SVM (GA_SVM) had an accuracy improvement of 1.92% compared to the basic classifier. SVM model based on HHO and GA optimization (HHO_GA_SVM) had the best performance and convergence speed compared with other optimization algorithms. Compared with the basic classification model, the accuracy was improved by 3.51%. HHO and GA optimization can improve the model performance of SVM in TCM syndrome differentiation of DR. It provides a new method and research idea for TCM intelligent assisted syndrome differentiation.

TCM syndrome differentiation in colorectal cancer patients assisted by differences in gut microbiota: An exploratory study

ObjectiveTo explore the difference in gut microbiota between different traditional Chinese Medicine (TCM) syndromes in patients with colorectal cancer (CRC) and its internal relationship. MethodsFrom June 2020 to August 2021, 109 colorectal cancer patients with a clear pathological diagnosis who had not yet undergone surgery or chemotherapy were classified according to the TCM syndrome classification, and the feces samples of 109 patients with preoperative colorectal cancer were collected. 16s rRNA gene sequencing was used to determine gut microbiota diversity and abundance in CRC patients with different TCM syndrome, and LEfSe analysis was made to screen different TCM syndrome for differential representative microbiota. Results109 patients were divided into 5 syndromes by TCM syndrome classification, which were Liver and Kidney Yin Deficiency Syndrome (LKYDS, n = 19), Spleen Deficient Qi Stagnation Syndrome (SDQSS, n = 30), Stasis and Poison Obstruction Syndrome (SPOS, n = 17), Damp-Heat Syndrome (DHS, n = 30), Qi and Blood Deficiency Syndrome (QBDS, n = 13). Alpha diversity index showed significant differences among the five groups of TCM syndromes, with Shannon index being highest in the SDQSS group and lowest in the LKYDS (p = 0.003). ACE index being highest in the SDQSS group and lowest in the SPOS (p = 0.010). PD whole tree index being highest in the SDQSS group and lowest in the SPOS (p = 0.017). Similarly, beta diversity showed significant differences among the five groups of TCM syndromes, with principal coordinate analysis (PCo1 = 31.86 %, PCo2 = 5.62 %) showing separation and coincidence between the groups, and Adonis group differences showing coincidence between the QBDS-LKYDS (p = 0.702), QBDS-DHS (p = 0.133), and SDQSS-DHS (p = 0.260) groups. LEfSe analysis revealed that the representative microbiota of DHS patients was Dialister sp Marseille P5638 (LDA = 3.05, p＜0.001), the representative microbiota of SPOS patients was Oscillospirales (LDA = 4.78, p = 0.029), the representative microbiota of SDQSS patients was Selenomonadaceae (LDA = 3.94, p = 0.003), the representative microbiota of LKYDS patients was Dialister (LDA = 4.19, p = 0.001), and the representative microbiota of QBDS patients was Akkermansia muciniphila (LDA = 4.23, p = 0.006). ConclusionsThere are significant differences in gut microbiota between different TCM syndromes in CRC patients. The five microbiota, Dialister sp Marseille P5638, Oscillospirales, Selenomonadaceae, Dialister, and Akkermansia muciniphila, may be differential markers of TCM syndrome in CRC and are expected to be one of the bases for accurate TCM syndrome differentiation of CRC.

An exploratory study on TCM syndrome differentiation in preoperative patients with colorectal cancer assisted by laboratory indicators

ObjectiveThis paper aims to explore the relationship between the syndrome differentiation of traditional Chinese medicine (TCM) in colorectal cancer and the clinical laboratory indicators of patients, and to further seek the laboratory indicators to assist TCM syndrome differentiation. MethodsFrom May 2020 to June 2021, 122 colorectal cancer patients with a clear pathological diagnosis who had not undergone surgery or chemotherapy were classified according to the TCM syndrome classification. The clinical laboratory indicators of 122 patients with preoperative colorectal cancer were collected, and the correlation between preoperative colorectal cancer TCM syndromes and Karnofsky score and clinical laboratory indicators was analyzed. The indicators affecting TCM syndromes were included in the disordered multivariate logistic regression analysis model to analyze the relative risk of the influencing factors. ResultsThe syndromes of colorectal cancer patients were classified into excess syndrome, deficiency syndrome, and syndrome of intermingled deficiency & excess. The differences in total bilirubin (TBIL), hemoglobin (HB), uric acid (UA), and hematocrit (HCT) between the three groups were statistically significant (P < 0.05). The indexes such as TBIL, HB, UA, and HCT in preoperative patients with excess syndrome of colorectal cancer were higher than those in patients with syndrome of intermingled deficiency & excess and deficiency syndrome, and the comparison between groups using the LSD method showed that UA and HCT were different between the excess syndrome and deficiency syndrome groups (P < 0.05). Multivariate logistic regression analysis indicated that Gender, Tumor location, TNM stage, Total protein (TP), Red blood cell (RBC), HB, HCT, Platelet (PLT) and Fibrinogen (FIB) were all risk factors affecting TCM syndromes of preoperative colorectal cancer (P < 0.05). ConclusionThere is a correlation between the TCM syndromes of colorectal cancer and the clinical laboratory indicators of the patients. Gender, Tumor location, TNM stage, TP, RBC, HB, HCT, PLT and FIB are the risk factors of TCM syndrome differentiation in preoperative patients with colorectal cancer. TBIL, UA, HB, and HCT may be the four relevant indicators of TCM syndrome differentiation in colorectal cancer.

Epidemiological investigation and proteomic profiling of typical TCM syndrome in HIV/AIDS immunological nonresponders.

HIV/AIDS pandemic remains the world's most severe public health challenge, especially for HIV/AIDS immunological nonresponders (HIV/AIDS-INRs), who tend to have higher mortality. Due to the advantages in promoting patients' immune reconstitution, Traditional Chinese medicine (TCM) has become one of the mainstays of complementary treatments for HIV/AIDS-INRs. Given that effective TCM treatments largely depend on precise syndrome differentiation, there is an increasing interest in exploring biological evidence for the classification of TCM syndromes in HIV/AIDS-INRs. In our study, to identify the typical HIV/AIDS-INRs syndrome, an epidemiological survey was first conducted in the Liangshan prefecture (China), a high HIV/AIDS prevalence region. The key TCM syndrome, Yang deficiency of spleen and kidney (YDSK), was evaluated by using a tandem mass tag combined with liquid chromatography-tandem mass spectrometry (TMT-LC-MS/MS). A total of 62 differentially expressed proteins (DEPs) of YDSK syndrome compared with healthy people were screened out. Comparative bioinformatics analyses showed that DEPs in YDSK syndrome were mainly associated with response to wounding and acute inflammatory response in the biological process. The pathway annotation is mainly enriched in complement and coagulation cascades. Finally, the YDSK syndrome-specific DEPs such as HP and S100A9 were verified by ELISA, and confirmed as potential biomarkers for YDSK syndrome. Our study may lay the biological and scientific basis for the specificity of TCM syndromes in HIV/AIDs-INRs, and may provide more opportunities for the deep understanding of TCM syndromes and the developing more effective and stable TCM treatment for HIV/AIDS-INRs.

A Traditional Chinese Medicine Syndrome Classification Model Based on Cross-Feature Generation by Convolution Neural Network: Model Development and Validation.

BackgroundNowadays, intelligent medicine is gaining widespread attention, and great progress has been made in Western medicine with the help of artificial intelligence to assist in decision making. Compared with Western medicine, traditional Chinese medicine (TCM) involves selecting the specific treatment method, prescription, and medication based on the dialectical results of each patient’s symptoms. For this reason, the development of a TCM-assisted decision-making system has lagged. Treatment based on syndrome differentiation is the core of TCM treatment; TCM doctors can dialectically classify diseases according to patients’ symptoms and optimize treatment in time. Therefore, the essence of a TCM-assisted decision-making system is a TCM intelligent, dialectical algorithm. Symptoms stored in electronic medical records are mostly associated with patients’ diseases; however, symptoms of TCM are mostly subjectively identified. In general electronic medical records, there are many missing values. TCM medical records, in which symptoms tend to cause high-dimensional sparse data, reduce algorithm accuracy.ObjectiveThis study aims to construct an algorithm model compatible for the multidimensional, highly sparse, and multiclassification task of TCM syndrome differentiation, so that it can be effectively applied to the intelligent dialectic of different diseases.MethodsThe relevant terms in electronic medical records were standardized with respect to symptoms and evidence-based criteria of TCM. We structuralized case data based on the classification of different symptoms and physical signs according to the 4 diagnostic examinations in TCM diagnosis. A novel cross-feature generation by convolution neural network model performed evidence-based recommendations based on the input embedded, structured medical record data.ResultsThe data set included 5273 real dysmenorrhea cases from the Sichuan TCM big data management platform and the Chinese literature database, which were embedded into 60 fields after being structured and standardized. The training set and test set were randomly constructed in a ratio of 3:1. For the classification of different syndrome types, compared with 6 traditional, intelligent dialectical models and 3 click-through-rate models, the new model showed a good generalization ability and good classification effect. The comprehensive accuracy rate reached 96.21%.ConclusionsThe main contribution of this study is the construction of a new intelligent dialectical model combining the characteristics of TCM by treating intelligent dialectics as a high-dimensional sparse vector classification task. Owing to the standardization of the input symptoms, all the common symptoms of TCM are covered, and the model can differentiate the symptoms with a variety of missing values. Therefore, with the continuous improvement of disease data sets, this model has the potential to be applied to the dialectical classification of different diseases in TCM.

Determining diabetic kidney disease severity using traditional Chinese medicine syndrome classification.

Determining diabetic kidney disease severity using traditional Chinese medicine syndrome classification.

Research on Correlation between TCM Syndrome Distribution Characteristics and Prognosis of Hypertensive Intracerebral Hemorrhage Operation

Objective: This study is to analyze correlation between traditional Chinese medicine (TCM) syndrome distribution characteristics and prognosis of hypertensive intracerebral hemorrhage (HICH) operation. Methods: In this study, a total of 150 patients who had received HICH operation from April, 2017 to December, 2020 in our hospital and conformed to inclusion standards were selected. According to classification of TCM syndromes, amount of bleeding of patients was recorded through multiple radiological technologies, baseline information was collected, and prognosis was investigated. The final event was long-term follow-up visit of all-cause mortalities. Moreover, correlation between prognosis and TCM syndromes was analyzed. Results: It found through investigations that there are no statistically significant differences in composition ratio of TCM syndromes among patients with different genders and different age ranges (P > 0.05). Among so many TCM syndromes, bleeding amount of patients with declining vitality and distraction is the highest, while bleeding amount of patients with stirring wind due to yin deficiency is the lowest. With respect NIHSS scores, the patients with declining vitality and distraction show the highest NIHSS scores at admission and 10 d of the course of the disease, followed by patients with upward disturbance of wind-fire. There are statistically significant differences among these two groups (P < 0.05). In this study, follow-up visits are performed to all 150 patients and the average follow-up visit time ranges within 2 - 15 months. A total of 13 deaths are reported. Number of all-cause deaths has statistically significant differences among different syndromes (P < 0.05). Conclusions: Evolutionary characteristics of TCM syndromes of HICH are manifested by development from evidence-based symptoms to deficiency syndromes. Different syndromes are correlated with prognosis of patients. On the one hand, this can be used as an objective index for TCM syndrome classification. On the other hand, this is conducive to judge prognosis recovery of patients and to apply the corresponding symptomatic treatment.

Plasma metabolic profiling on postoperative colorectal cancer patients with different traditional Chinese medicine syndromes

ObjectivesThis study aims to investigate the metabolic profiles of postoperative colorectal cancer (PCRC) patients with different traditional Chinese medicine (TCM) syndromes and to discuss the metabolic mechanism under PCRC progression and TCM syndrome classification. MethodsFifty healthy controls (HC) and 70 PCRC patients, including 10 Dampness and heat syndrome (DHS), 33 Spleen deficiency syndrome (SDS), 19 Liver and kidney Yin deficiency syndrome (LKYDS) and 8 with non-TCM syndrome (NS) were enrolled. Plasma metabolic profiles were detected by Gas chromatography-mass spectrometry (GC–MS) and analyzed by principal component analysis (PCA) and partial least squares-discriminate analysis (PLS-DA). Furthermore, pathway enrichment was analyzed based on KEGG and DAVID databases and metabolic network was constructed via metaboanalyst and cytoscape. ResultsThe top-3 metabolites with higher abundance in PCRC compared with HC were terephthalic acid (165.417-fold), ornithine (24.484-fold) and aminomalonic acid (21.346-fold). And the cholesterol (0.588-fold) level was decreased in PCRC. l-Alanine, 1, 2-ethanediamine, urea, glycerol, glycine, aminomalonic acid, creatinine and palmitic acid were specifically altered in the DHS, while d-tryptophan was exclusively changed in SDS, and l-proline, 1, 2, 3-propanetricarboxylic acid, d-galactose and 2-indolecarboxylic acids in LKYDS. ConclusionsThe plasma metabolic profiles were perturbed in PCRC patients. Increased levels of terephthalic acid might indicate high risk of relapse and elevated ornithine may contribute to the post-operational recovery or may raise the susceptibility to PCRC recurrence. The metabolic profiles of DHS, SDS, LKYDS and NS were almost separately clustered, indicating the possibility of explaining TCM syndromes classification using metabolomics. Furthermore, creatinine and aminomalonic acid alternation might correlate with the formation of DHS, while d-tryptophan may associate with SDS and d-galactose and 1, 2, 3-propanetricarboxylic acid may relate to LKYDS. As numbers of patients in each TCM syndrome are small, further study is needed to verify those results.

MiRNA-target network analysis identifies potential biomarkers for Traditional Chinese Medicine (TCM) syndrome development evaluation in hepatitis B caused liver cirrhosis

Hepatitis B is one of most etiologies of Liver cirrhosis in China, and clinically lacks the effective strategy for Hepatitis B caused cirrhosis (HBC) therapy. As a complementary and alternative medicine, Chinese Traditional Medicine (TCM) has special therapeutic effects for HBC. Here, we focus on the evolution process of HBC TCM syndromes, which was from Excessive (Liver-Gallbladder Dampness-Heat Syndrome, LGDHS) to Deficient (Liver-Kidney Deficiency Syndrome, LKYDS) via Excessive-Deficient syndrome (Liver-Depression and Spleen-Deficiency Syndrome, LDSDS). Using R package, 16 miRNAs in LGDHS/Normal, 48 miRNAs in LDSDS/LGDHS, and 16 miRNAs in LKYDS/LDSDS were identified, respectively. The miRNA-target networks show that the LDSDS was most stability and complicated. Subsequently, 4 kernel miRNAs with LGDHS-LDSDS process, and 5 kernel miRNAs with LDSDS-LKYDS process were screened. Using RT-qPCR data, p1 (hsa-miR-17-3p, -377-3p, -410-3p and -495) and p2 miRNA panel (hsa-miR-377-3p, -410-3p, -27a-3p, 149-5p and 940) were identified by Logistic Regression Model, which clearly improve the accuracy of TCM syndrome classification. The rebuilt miRNA-target network shows that the LDSDS is a critical point and might determine the evolution directions of HBC TCM syndrome. This study suggests that the identified kernel miRNAs act as potential biomarkers and benefit to evaluate the evolution tendency of HBC TCM syndromes.

Identification and classification of traditional Chinese medicine syndrome types among senior patients with vascular mild cognitive impairment using latent tree analysis

ObjectiveTo treat patients with vascular mild cognitive impairment (VMCI) using traditional Chinese medicine (TCM), it is necessary to classify the patients into TCM syndrome types and to apply different treatments to different types. In this paper, we investigate how to properly carry out the classification for patients with VMCI aged 50 or above using a novel data-driven method known as latent tree analysis (LTA). MethodA cross-sectional survey on VMCI was carried out in several regions in Northern China between February 2008 and February 2012 which resulted in a data set that involves 803 patients and 93 symptoms. LTA was performed on the data to reveal symptom co-occurrence patterns, and the patients were partitioned into clusters in multiple ways based on the patterns. The patient clusters were matched up with syndrome types, and population statistics of the clusters are used to quantify the syndrome types and to establish classification rules. ResultsEight syndrome types are identified: Qi deficiency, Qi stagnation, Blood deficiency, Blood stasis, Phlegm-dampness, Fire-heat, Yang deficiency, and Yin deficiency. The prevalence and symptom occurrence characteristics of each syndrome type are determined. Quantitative classification rules are established for determining whether a patient belongs to each of the syndrome types. ConclusionA solution for the TCM syndrome classification problem for patients with VMCI and aged 50 or above is established based on the LTA of unlabeled symptom survey data. The results can be used as a reference in clinic practice to improve the quality of syndrome differentiation and to reduce diagnosis variances across physicians. They can also be used for patient selection in research projects aimed at finding biomarkers for the syndrome types and in randomized control trials aimed at determining the efficacy of TCM treatments of VMCI.

The Correlation between High-Sensitivity C-Reactive Protein, Matrix Metallopeptidase 9, and Traditional Chinese Medicine Syndrome in Patients with Hypertension

Hypertension is a common disease affecting millions of people throughout the world. Currently, there is a growing interest in the traditional Chinese medicine (TCM) for patients with hypertension mainly due to the personalized therapy of TCM in many countries. Clinical treatment of patients relies on the successful differentiation of a specific TCM syndrome for hypertension. However, it is difficult to understand that TCM syndrome classifications depend on the clinical experience of a TCM practitioner. Therefore, discovering an objective biomarker associated with TCM syndrome may be beneficial for TCM syndrome classifications. This paper focused on high sensitivity C-reactive protein (HCRP), matrix metallopeptidase 9 (MMP9), and TCM syndrome, and aimed to investigate the relationships between TCM syndrome and the two inflammatory biomarkers in patients with essential hypertension. The result showed that both HCRP and MMP9 are positively correlated with syndrome of wind and phlegm turbidity. Detection of the serum levels of HCRP and MMP9 is beneficial for TCM syndrome classification and prediction of cardiovascular and cerebrovascular risk events in hypertensive patients.

Chromaticity and optical spectrum colorimetry of the tongue color in different syndromes of primary hepatic carcinoma

In this study, the optical data of tongue color of different syndromes in primary hepatic carcinoma (PHC) were detected by optical spectrum colorimetry, and the chromaticity of tongue color was compared and analyzed. The tongue color characteristics of different syndromes in PHC and the relationship between different syndromes and tongue color were also investigated. Tongue color data from 133 eligible PHC patients were collected by optical spectrum colorimetry and the patients were divided into 4 syndrome groups according to their clinical features. The syndrome groups were liver depression and spleen deficiency (LDSD), accumulation of damp-heat (ADH), deficiency of liver and kidney yin (DLKY), and qi stagnation and blood stasis (QSBS). The variation characteristics of chromaticity coordinates, dominant wavelength, excitation purity and the distribution in the International Commission on Illumination (CIE) LAB uniform color space were measured. At the same time, the differences of overall chromatism, clarity, chroma, saturation and hue were also calculated and analyzed. PHC patients in different syndrome groups exhibited differences in chromaticity coordinates. The dominant wavelength of QSBS was distinctly different from that of the other 3 syndromes. Excitation purity in the syndromes of LDSD, ADH and DLKY showed gradual increases (P<0.01). Different syndromes in the CIE LAB color three-dimensional space showed differences in tongue color distribution areas. The CIE hue-angle value of QSBS was negative, and different from that of the other 3 syndromes (P<0.01). CIE chroma in the syndromes of LDSD, ADH and DLKY showed gradual increases (P<0.01), the same as excitation purity. In the comparison of chromatism, tongue color variations in different syndromes were quantified by human observation. This study shows that tongue color diagnosis according to the syndrome classifications of traditional Chinese medicine can be quantified with optical spectrum colorimetry technology. Different syndromes in PHC exhibit distinct chromatisms of tongue color through the calculation and analysis of chromaticity parameters of CIE, combined with colorimetric system and CIE LAB color space, and these are consistent with the characteristics of clinical tongue color. Applying optical spectrum colorimetry technology to tongue color differentiation has the potential to serve as a reference point in standardizing traditional Chinese medicine syndrome classification in PHC.

Classification of Traditional Chinese Medicine Syndromes in Patients with Chronic Hepatitis B by SELDI-Based ProteinChip Analysis

Traditional Chinese medicine (TCM) syndrome, also called ZHENG, is the basis concept of TCM theory. It plays an important role in TCM practice. There are excess and deficiency syndromes in TCM syndrome. They are the common syndromes in chronic hepatitis B (CHB) patients. Here we aim to explore serum protein profiles and potential biomarkers for classification of TCM syndromes in CHB patients. 24 healthy controls and two cohorts of CHB patients of excess syndrome (n = 25) or deficiency syndrome (n = 19) were involved in this study. Protein profiles were obtained by surface-enhanced laser desorption ionization time-flight mass spectrometry (SELDI-TOF/MS) and multiple analyses were performed. Based on SELDI ProteinChip data, healthy controls and CHB patients or excess and deficiency syndromes in CHB patients were obviously differentiated by orthogonal partial least square (OPLS) analysis. Two significant serum proteins (m/z 4187 and m/z 5032) for classifying excess and deficiency syndromes were found. Moreover, the area under the receiver operating characteristic (ROC) curve was 0.887 for classifying excess and nonexcess syndrome, and 0.700 for classifying deficiency and nondeficiency syndrome, respectively. Therefore, the present study provided the possibility of TCM syndrome classification in CHB patients using a universally acceptable scientific approach.

Correlative analysis of the parameters of eTRACKING detection of femoral artery and the syndrome types of traditional Chinese medicine in type 2 diabetic patients

To explore the correlation between the parameters of eTRACKING detection of femoral artery and the syndrome types of traditional Chinese medicine (TCM) in type 2 diabetic patients so as to provide clinical evidence for early prevention and treatment of diabetic lower extremity arterial disease. A total of 147 cases of type 2 diabetic patients were included. Basic data and TCM clinical information were collected, and eTRACKING detection of common femoral arteries was performed. Differentiation of symptoms and signs for classification of TCM syndromes was performed in all patients. The correlations between TCM syndrome and pressure-strain elastic modulus (Ep), stiffness parameter beta, arterial compliance (AC), pulse wave velocity beta (PWVbeta), and augmentation index (AI) in common femoral arteries were observed. In the patients with deficiency of both yin and yang, the Ep value was higher than that in the patients with deficiency of both qi and yin, the stiffness parameter beta was higher than that in the other three syndrome types (deficiency of both qi and yin, excessive heat due to yin deficiency, accumulation of damp-beat in spleen), the AC value was lower than that in the patients with excessive heat due to yin deficiency, the PWVbeta value was higher than that in the patients with excessive heat due to yin deficiency and deficiency of both qi and yin, and the AI value was higher than that in the patients with excessive heat due to yin deficiency. The stiffness parameter beta in the patients with deficiency of both qi and yin was higher than that in the patients with accumulation of damp-heat in spleen. In the patients with blood stasis, the Ep value was higher and the AC value was lower than that in the patients without blood stasis. The decrease of elasticity in lower extremities can be detected by eTRACKING. This study reveals that type 2 diabetic patients with deficiency of both yin and yang, accumulation of damp-heat in spleen and blood stasis have more severe lower extremity arteriosclerosis. In eTRACKING parameters, stiffness parameter beta, AC and PWVbeta may become the objective indexes in evaluating early diabetic lower extremity arteriosclerosis.